stdio-to-http mcp protocol bridging with transparent request forwarding, league of legends champion and summoner data querying with field-level filtering, installation and deployment via smithery, npm, or docker, teamfight tactics meta composition and augment analysis with play style filtering, valorant agent, map, and leaderboard data retrieval with region-specific filtering, esports schedule and tournament data aggregation across multiple games, dynamic mcp capability discovery and tool registry mirroring at startup, response payload optimization via field-level filtering at api boundary, multi-game gaming data aggregation under unified mcp interface, streamable http client transport for remote mcp endpoint connectivity, stdio server transport for local mcp client communication

OP.GG

MCP ServerFree

** - Access real-time gaming data across popular titles like League of Legends, TFT, and Valorant, offering champion analytics, esports schedules, meta compositions, and character statistics.

Open Source

/ 100

11 capabilities

Capabilities11 decomposed

stdio-to-http mcp protocol bridging with transparent request forwarding

Medium confidence

Implements a bidirectional Model Context Protocol proxy that accepts stdio connections from local MCP clients (Claude Desktop, Cursor, etc.) and transparently forwards all tool calls over Streamable HTTP to a remote OP.GG MCP endpoint at https://mcp-api.op.gg/mcp. Uses StdioServerTransport for local consumer communication and StreamableHTTPClientTransport for outbound HTTP, with dynamic capability discovery at startup to mirror remote tools into the local server's tool registry without hardcoding tool definitions.

Solves for

Connect local AI agents to remote gaming data APIs without modifying client codeRun OP.GG gaming tools inside Claude Desktop or other stdio-based MCP clientsProxy MCP requests through a local process to avoid direct HTTP exposure in client configs

Best for

AI agent developers integrating gaming data into Claude or Cursor workflows

Teams deploying MCP servers in restricted network environments requiring local proxies

Builders wanting transparent HTTP-to-stdio adaptation without custom integration code

Requires

Node.js runtime (version not specified in docs, but dist/index.js implies Node 14+)

Network access to https://mcp-api.op.gg/mcp endpoint

MCP client supporting stdio transport (Claude Desktop, Cursor, or custom MCP client)

Limitations

Adds network round-trip latency for every tool call (remote HTTP request to https://mcp-api.op.gg/mcp)

No local caching or request deduplication — each tool call results in a fresh HTTP request

Requires network connectivity to remote OP.GG endpoint; no offline fallback or graceful degradation

What makes it unique

Uses dynamic capability discovery at startup (reads serverCapabilities from remote endpoint) and conditionally registers request/notification handlers on the local MCP Server, enabling the proxy to work with any remote MCP endpoint without hardcoding tool definitions. This contrasts with static tool registries that require rebuilding when upstream tools change.

vs alternatives

Simpler than building custom HTTP client integrations in each AI framework because it leverages standard MCP protocol, making it compatible with any stdio-based MCP client without modification.

league of legends champion and summoner data querying with field-level filtering

Medium confidence

Exposes 15 tools for querying League of Legends game data including champion statistics, summoner profiles, match history, resource guides, pro player stats, and esports schedules. Each tool accepts a desired_output_fields parameter to filter response payloads at the API level, reducing bandwidth and token consumption by excluding unnecessary fields. Tools are prefixed with 'lol_' and cover champion analytics, summoner rank/win rates, match timelines, and competitive esports data.

Solves for

Fetch real-time champion win rates, ban rates, and meta build recommendations for a specific rank tierLook up summoner profiles and match history to analyze player performance patternsQuery esports schedules, team rosters, and pro player statistics for competitive League contentRetrieve champion ability descriptions and item build guides for in-game decision support

Best for

Gaming content creators building League of Legends analysis tools or guides

Esports analysts automating match research and player performance tracking

AI agents providing real-time meta recommendations to players during champion select

Requires

Valid summoner name and region (e.g., 'NA', 'EUW', 'KR') for summoner-specific queries

Champion name or ID for champion-specific analytics

Optional: desired_output_fields array to specify which response fields to include (e.g., ['winRate', 'pickRate', 'banRate'])

Limitations

Data freshness depends on OP.GG's update frequency (typically 5-15 minute delay from live matches)

Summoner lookups require exact summoner name and region; fuzzy matching not supported

Match history limited to recent matches (typically last 100-200 matches); full historical data not available

What makes it unique

Implements field-level response filtering via desired_output_fields parameter, allowing clients to specify exactly which data fields to return. This reduces payload size by excluding unnecessary fields at the API level rather than post-processing, which is particularly valuable for token-constrained LLM contexts where every byte matters.

vs alternatives

More efficient than generic League APIs (Riot's official API, third-party REST endpoints) because it provides pre-computed meta analytics (win rates, pick rates, build recommendations) rather than raw match data, reducing the computation burden on the client side.

installation and deployment via smithery, npm, or docker

Medium confidence

Supports three deployment methods: (1) Smithery configuration via smithery.yaml for automated process spawning, (2) manual npm/npx invocation (npx opgg-mcp or node dist/index.js), and (3) Docker deployment for containerized environments. All methods ultimately execute dist/index.js as a local stdio MCP server process. Enables flexible deployment across different environments (local development, CI/CD pipelines, containerized infrastructure) without code changes.

Solves for

Deploy the OP.GG MCP proxy in local development environments using npm/npxIntegrate the proxy into Smithery-based MCP client configurations for automated process managementDeploy the proxy in containerized environments (Docker, Kubernetes) for production useSupport multiple deployment patterns without requiring code modifications

Best for

Individual developers integrating OP.GG data into Claude Desktop or Cursor

Teams using Smithery for MCP server management and orchestration

Organizations deploying MCP proxies in containerized infrastructure (Docker, Kubernetes)

Requires

For Smithery: Smithery client installed, smithery.yaml configuration file

For npm/npx: Node.js 14+ and npm, or npx (bundled with npm 5.2+)

For Docker: Docker runtime, Dockerfile (provided in repo), and Docker image build capability

Limitations

Smithery installation requires Smithery client and smithery.yaml configuration; not suitable for non-Smithery environments

npm/npx installation requires Node.js and npm; not suitable for environments without Node.js runtime

Docker deployment requires Docker runtime and image building; adds complexity for simple use cases

What makes it unique

Supports three distinct deployment methods (Smithery, npm/npx, Docker) from a single codebase, enabling flexible deployment across different environments and use cases. This multi-method approach reduces friction for different deployment scenarios compared to single-method-only tools.

vs alternatives

More flexible than tools supporting only one deployment method because it accommodates Smithery-based orchestration, manual npm invocation, and containerized deployments without code changes.

teamfight tactics meta composition and augment analysis with play style filtering

Medium confidence

Provides 6 tools for querying Teamfight Tactics (TFT) game data including meta deck compositions, item builds, augment recommendations, and play style classifications. Tools are prefixed with 'tft_' and return structured data about optimal team compositions for the current TFT set, itemization strategies, and augment synergies. Supports filtering by play style (e.g., 'aggressive', 'control', 'economy') and rank tier to surface meta-relevant recommendations.

Solves for

Get current meta deck compositions and win rates for the active TFT setQuery optimal item builds and augment combinations for specific team compositionsFilter meta recommendations by play style (aggressive vs. economy-focused) and rank tierBuild AI coaching agents that recommend real-time team pivots based on current meta

Best for

TFT content creators and streamers building real-time meta guides

AI agents providing in-game coaching recommendations during TFT matches

Esports analysts tracking meta shifts across tournament patches

Requires

Current TFT set identifier (e.g., 'Set 11') — OP.GG typically supports 1-2 active sets

Optional: rank tier filter (string: 'IRON', 'BRONZE', 'SILVER', 'GOLD', 'PLATINUM', 'DIAMOND', 'MASTER', 'CHALLENGER')

Optional: play style filter (string: 'aggressive', 'control', 'economy', or similar OP.GG-defined categories)

Limitations

Meta data updates only when TFT set changes or OP.GG refreshes statistics (typically daily)

Play style classifications are OP.GG-defined categories; custom play style filters not supported

Augment recommendations are statistical aggregates, not contextual to current game state (player items, remaining units, etc.)

What makes it unique

Organizes meta data by play style (aggressive, control, economy) rather than just raw win rates, enabling AI agents to recommend compositions that match player preferences and game state. This contextual filtering is rarely exposed in generic TFT APIs, which typically return only statistical aggregates.

vs alternatives

Provides pre-computed meta compositions and augment synergies rather than requiring clients to aggregate raw match data, making it significantly faster for real-time coaching use cases compared to building custom analytics on top of raw TFT match APIs.

valorant agent, map, and leaderboard data retrieval with region-specific filtering

Medium confidence

Exposes 6 tools for querying Valorant competitive data including agent statistics (pick rates, win rates, ban rates), map-specific meta, leaderboard rankings, and player match history. Tools are prefixed with 'valorant_' and support filtering by region (NA, EU, APAC, etc.) and rank tier to surface region-specific meta variations. Returns structured data about agent viability, map-specific strategies, and competitive player rankings.

Solves for

Fetch current agent meta and pick/ban rates for a specific rank tier and regionQuery map-specific agent recommendations and economy strategiesLook up player leaderboard rankings and recent match performanceBuild region-aware AI agents that recommend agent selections based on local meta

Best for

Valorant esports analysts and content creators covering regional competitive scenes

AI coaching agents providing agent selection recommendations during agent select phase

Competitive players researching region-specific meta before tournaments

Requires

Region code (string: 'NA', 'EU', 'APAC', 'BR', 'LATAM', 'KR', 'JP') for region-specific queries

Optional: rank tier filter (string: 'IRON', 'BRONZE', 'SILVER', 'GOLD', 'PLATINUM', 'DIAMOND', 'ASCENDANT', 'IMMORTAL', 'RADIANT')

Optional: agent name for agent-specific analytics

Limitations

Region-specific data may have sparse samples at high ranks (Radiant/Immortal) due to small player pools

Agent meta updates reflect historical data (typically 24-48 hours old) rather than real-time pick rates

Map-specific strategies are statistical aggregates; no contextual recommendations based on team composition or opponent agents

What makes it unique

Supports region-specific meta filtering (NA, EU, APAC, etc.), recognizing that Valorant competitive scenes have distinct agent preferences and strategies by region. This regional decomposition is rarely exposed in generic Valorant APIs, which typically aggregate global data.

vs alternatives

Provides pre-computed agent meta and leaderboard rankings rather than requiring clients to aggregate raw match data, making it significantly faster for competitive analysis compared to building custom analytics on top of raw Valorant match APIs.

esports schedule and tournament data aggregation across multiple games

Medium confidence

Aggregates esports schedule, team roster, and tournament data across League of Legends, Teamfight Tactics, and Valorant competitive scenes. Returns structured data about upcoming matches, team information, player rosters, tournament brackets, and historical match results. Supports filtering by game title, region, and tournament tier (e.g., regional leagues, international events). Data is updated periodically as tournaments progress.

Solves for

Fetch upcoming esports match schedules and broadcast times for a specific region or gameLook up team rosters and player information for esports organizationsQuery historical tournament results and match statistics for competitive analysisBuild esports content aggregators or Discord bots that announce upcoming matches

Best for

Esports content platforms and news aggregators covering multiple gaming titles

Tournament organizers and esports teams tracking match schedules and results

AI agents generating esports match previews and predictions

Requires

Game title filter (string: 'lol', 'tft', 'valorant') to specify which esports scene to query

Optional: region code (string: 'NA', 'EU', 'KR', 'CN', etc.) for region-specific tournaments

Optional: tournament tier filter (string: 'regional', 'international', 'challenger', etc.)

Limitations

Tournament data updates are periodic (typically daily or per-match-day) rather than real-time

Historical data availability varies by tournament tier; regional league data more complete than international events

No live match data (current score, round-by-round progression) — only pre-match and post-match information

What makes it unique

Aggregates esports data across three distinct games (League of Legends, TFT, Valorant) under a unified tool interface, allowing single queries to span multiple competitive scenes. Most esports APIs are game-specific; this unified approach reduces integration complexity for multi-game esports platforms.

vs alternatives

Consolidates esports schedules and rosters from multiple games into a single MCP interface, eliminating the need to integrate separate APIs for each game's esports data.

dynamic mcp capability discovery and tool registry mirroring at startup

Medium confidence

At startup, the proxy fetches serverCapabilities from the remote OP.GG MCP endpoint and dynamically registers corresponding request/notification handlers on the local MCP Server. This enables the proxy to work with any remote MCP endpoint without hardcoding tool definitions. When the remote endpoint adds, removes, or modifies tools, the local proxy automatically reflects these changes on the next startup without code changes. Implementation reads capabilities once at initialization and conditionally registers handlers based on what the remote server advertises.

Solves for

Support upstream tool changes without requiring proxy code modifications or redeploymentEnable the proxy to work with multiple remote MCP endpoints by dynamically discovering their capabilitiesReduce maintenance burden by eliminating hardcoded tool registries that must be manually synchronized with upstream

Best for

Teams maintaining long-lived MCP proxies that need to adapt to upstream API changes

Builders creating generic MCP proxy infrastructure that should work with any remote endpoint

Developers who want to avoid manual tool registry synchronization between local and remote servers

Requires

Network connectivity to remote MCP endpoint at startup time

Remote endpoint must implement MCP serverCapabilities protocol (standard MCP feature)

Node.js runtime with @modelcontextprotocol/sdk library for MCP protocol implementation

Limitations

Capability discovery happens only at startup; tool changes on the remote endpoint require proxy restart to take effect

No caching of discovered capabilities; each startup incurs a network round-trip to fetch serverCapabilities

If the remote endpoint is unavailable at startup, the proxy fails to initialize (no graceful degradation with cached capabilities)

What makes it unique

Uses dynamic capability discovery at startup (reads serverCapabilities from remote endpoint) and conditionally registers handlers, eliminating the need for hardcoded tool definitions. This contrasts with static tool registries that require code changes when upstream tools change. Implementation in src/proxy-server.ts reads capabilities once and registers handlers based on what the remote server advertises.

vs alternatives

More maintainable than static tool registries because upstream tool changes are automatically reflected without proxy code modifications, reducing synchronization burden compared to manually-maintained tool definitions.

response payload optimization via field-level filtering at api boundary

Medium confidence

All 27 tools across League of Legends, Teamfight Tactics, and Valorant support a desired_output_fields parameter that filters response payloads at the remote API level. Clients specify which fields to include in the response (e.g., ['winRate', 'pickRate', 'banRate']), and the remote endpoint returns only those fields, reducing payload size and token consumption. This filtering happens server-side before the response is transmitted back through the proxy, minimizing bandwidth usage and LLM context overhead.

Solves for

Reduce token consumption in LLM contexts by excluding unnecessary fields from API responsesMinimize network bandwidth usage when querying large datasets (e.g., full leaderboards)Optimize response latency by reducing payload size transmitted over the networkBuild efficient AI agents that only request the specific data fields needed for decision-making

Best for

Token-constrained LLM applications where every byte of context matters

High-volume data aggregation scenarios where bandwidth optimization is critical

Mobile or edge deployments with limited network bandwidth

Requires

Knowledge of available field names for the specific tool being queried (documented in tool schemas)

Optional: desired_output_fields array parameter (if omitted, full response is returned)

Remote OP.GG endpoint must support field filtering (standard feature of all 27 tools)

Limitations

Requires knowledge of available field names for each tool; no schema introspection or field discovery API

Field filtering is all-or-nothing; partial field selection not supported (either include a field or exclude it entirely)

No computed fields or field transformations; only raw fields returned by the remote API can be filtered

What makes it unique

Implements server-side field filtering at the remote API boundary, allowing clients to specify exactly which response fields to include. This reduces payload size before transmission, contrasting with client-side filtering that requires transmitting the full response and then discarding unwanted fields.

vs alternatives

More efficient than client-side filtering because it reduces payload size at the source, saving bandwidth and token consumption compared to receiving full responses and filtering locally.

multi-game gaming data aggregation under unified mcp interface

Medium confidence

Consolidates gaming data from three distinct titles (League of Legends, Teamfight Tactics, Valorant) under a single MCP interface with 27 tools organized by game prefix (lol_, tft_, valorant_). Enables single MCP clients to query data across all three games without managing separate API integrations. Tools share common patterns (desired_output_fields filtering, region/tier filtering, structured response schemas) while maintaining game-specific data models and tool names.

Solves for

Query gaming data across multiple titles from a single MCP client without separate integrationsBuild multi-game content platforms that aggregate meta data, esports schedules, and player statsCreate AI agents that can provide recommendations across League, TFT, and Valorant ecosystemsReduce integration complexity by consolidating three game APIs into one MCP interface

Best for

Multi-game esports platforms and content aggregators

Gaming communities that span multiple titles (e.g., esports organizations with teams in multiple games)

AI agents providing cross-game recommendations or analysis

Requires

MCP client capable of handling 27 tools with game-specific prefixes

Knowledge of which game's tools to query for specific use cases (lol_ for League, tft_ for TFT, valorant_ for Valorant)

Optional: region codes and rank tiers specific to each game

Limitations

Tool naming requires game prefixes (lol_, tft_, valorant_) to avoid collisions; no unified tool naming across games

Data models are game-specific; no common schema for cross-game comparisons (e.g., 'win rate' definitions vary by game)

Meta data freshness may differ by game (League updates more frequently than TFT or Valorant)

What makes it unique

Consolidates 27 tools across three distinct games under a single MCP interface with consistent patterns (field filtering, region/tier filtering, structured schemas), eliminating the need for separate API integrations per game. Most gaming APIs are game-specific; this unified approach reduces integration complexity for multi-game platforms.

vs alternatives

Provides a single MCP interface for three games instead of requiring separate integrations for each game's API, reducing complexity for multi-game platforms compared to managing three independent API clients.

streamable http client transport for remote mcp endpoint connectivity

Medium confidence

Uses StreamableHTTPClientTransport from the @modelcontextprotocol/sdk library to establish HTTP connections to the remote OP.GG MCP endpoint at https://mcp-api.op.gg/mcp. This transport handles HTTP request/response serialization, error handling, and connection management for MCP protocol messages. Enables the local proxy to communicate with the remote endpoint over standard HTTP without custom HTTP client code, leveraging the SDK's built-in transport abstraction.

Solves for

Connect to remote MCP endpoints over HTTP without implementing custom HTTP client logicLeverage standard MCP protocol serialization and deserialization for HTTP communicationHandle HTTP connection lifecycle (connection pooling, error recovery, timeouts) automatically

Best for

Builders creating MCP proxies that need to connect to remote HTTP-based MCP endpoints

Teams wanting to avoid custom HTTP client implementation and rely on standard MCP transport abstractions

Developers integrating MCP clients with remote services over HTTP

Requires

@modelcontextprotocol/sdk library (version not specified, but latest recommended)

Node.js runtime with native fetch API or polyfill for HTTP requests

Network connectivity to remote MCP endpoint (https://mcp-api.op.gg/mcp)

Limitations

StreamableHTTPClientTransport is a specific SDK implementation; switching to different HTTP libraries requires code changes

No built-in request caching or response memoization; each tool call results in a fresh HTTP request

HTTP connection pooling and timeout behavior depends on SDK defaults; limited customization options

What makes it unique

Leverages @modelcontextprotocol/sdk's StreamableHTTPClientTransport abstraction, which handles MCP protocol serialization, HTTP connection management, and error handling automatically. This eliminates the need for custom HTTP client code and ensures compatibility with the MCP protocol specification.

vs alternatives

Simpler than implementing custom HTTP clients because it uses standard MCP transport abstractions from the SDK, reducing code complexity and ensuring protocol compliance.

stdio server transport for local mcp client communication

Medium confidence

Uses StdioServerTransport from the @modelcontextprotocol/sdk library to expose the local MCP Server over stdin/stdout to local MCP clients (Claude Desktop, Cursor, custom MCP clients). This transport handles JSON-RPC 2.0 message serialization over stdio, connection lifecycle management, and error handling. Enables the proxy to present itself as a standard MCP server to any stdio-based MCP client without custom protocol implementation.

Solves for

Expose the local proxy as a standard MCP server to Claude Desktop and other stdio-based MCP clientsHandle JSON-RPC 2.0 message serialization and deserialization over stdin/stdout automaticallyManage stdio connection lifecycle (initialization, message handling, error recovery) without custom code

Best for

Builders creating MCP servers that need to integrate with Claude Desktop or other stdio-based MCP clients

Teams wanting to avoid custom stdio protocol implementation and rely on standard MCP transport abstractions

Developers building MCP proxies that need to expose themselves as local servers

Requires

@modelcontextprotocol/sdk library (version not specified, but latest recommended)

Node.js runtime with stdio access (standard for Node.js processes)

MCP client supporting stdio transport (Claude Desktop, Cursor, or custom MCP client)

Limitations

StdioServerTransport is stdio-specific; switching to other transports (WebSocket, HTTP) requires code changes

Single-threaded stdio processing means concurrent requests from multiple clients will queue sequentially

No built-in request queueing or priority handling; all requests processed in FIFO order

What makes it unique

Uses StdioServerTransport from @modelcontextprotocol/sdk, which handles JSON-RPC 2.0 message serialization over stdio and connection lifecycle management. This eliminates custom stdio protocol implementation and ensures compatibility with standard MCP clients like Claude Desktop.

vs alternatives

Simpler than implementing custom stdio protocol handlers because it uses standard MCP transport abstractions from the SDK, reducing code complexity and ensuring compatibility with all stdio-based MCP clients.

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Related Artifactssharing capabilities

Artifacts that share capabilities with OP.GG, ranked by overlap. Discovered automatically through the match graph.

MCP Server25

@modelcontextprotocol/node

Model Context Protocol implementation for TypeScript - Node.js middleware

stdio-transport-server-setuphttp-sse-transport-server-setup

2 shared capabilities

MCP Server41

supergateway

Run MCP stdio servers over SSE, Streamable HTTP or visa versa

stdio-to-streamable http protocol bridgingstdio-to-sse protocol bridging

2 shared capabilities

MCP Server45

mcp-proxy

A TypeScript SSE proxy for MCP servers that use stdio transport.

stdio-to-sse transport bridging for mcp servers

1 shared capability

MCP Server36

inspector

Visual testing tool for MCP servers

mcp server protocol bridging via express proxy

1 shared capability

MCP Server25

ECharts

** - Generate visual charts using [ECharts](https://echarts.apache.org) with AI MCP dynamically, used for chart generation and data analysis.

multi-transport protocol bridging (stdio, sse, http)

1 shared capability

MCP Server23

tea-color-to-vars-mcp-server

A basic MCP server example using @modelcontextprotocol/sdk

stdio-based bidirectional message transport

1 shared capability

Best For

✓AI agent developers integrating gaming data into Claude or Cursor workflows
✓Teams deploying MCP servers in restricted network environments requiring local proxies
✓Builders wanting transparent HTTP-to-stdio adaptation without custom integration code
✓Gaming content creators building League of Legends analysis tools or guides
✓Esports analysts automating match research and player performance tracking
✓AI agents providing real-time meta recommendations to players during champion select
✓Developers building Discord bots or Twitch extensions with live League data
✓Individual developers integrating OP.GG data into Claude Desktop or Cursor

Known Limitations

⚠Adds network round-trip latency for every tool call (remote HTTP request to https://mcp-api.op.gg/mcp)
⚠No local caching or request deduplication — each tool call results in a fresh HTTP request
⚠Requires network connectivity to remote OP.GG endpoint; no offline fallback or graceful degradation
⚠Single-threaded stdio processing means concurrent requests from multiple clients will queue sequentially
⚠Data freshness depends on OP.GG's update frequency (typically 5-15 minute delay from live matches)
⚠Summoner lookups require exact summoner name and region; fuzzy matching not supported

Requirements

Node.js runtime (version not specified in docs, but dist/index.js implies Node 14+)Network access to https://mcp-api.op.gg/mcp endpointMCP client supporting stdio transport (Claude Desktop, Cursor, or custom MCP client)Optional: Smithery configuration file (smithery.yaml) for automated process spawning, or manual npm/npx invocationValid summoner name and region (e.g., 'NA', 'EUW', 'KR') for summoner-specific queriesChampion name or ID for champion-specific analyticsOptional: desired_output_fields array to specify which response fields to include (e.g., ['winRate', 'pickRate', 'banRate'])For Smithery: Smithery client installed, smithery.yaml configuration file

Input / Output

Accepts: MCP tool call requests (JSON-RPC 2.0 format over stdin), Tool parameters matching remote OP.GG tool schemas, Summoner name (string), Region code (string: 'NA', 'EUW', 'KR', etc.), Champion name or ID (string or integer), Rank tier filter (string: 'DIAMOND', 'PLATINUM', etc.), desired_output_fields (array of field names for response filtering), Smithery configuration (smithery.yaml with opgg-mcp server definition), npm/npx command invocation (npx opgg-mcp or node dist/index.js), Docker image and container configuration, TFT set identifier (string), Rank tier (string), Play style category (string), desired_output_fields (array of field names), Region code (string), Agent name (string), Map name (string), Player name/tag for leaderboard lookups, Game title (string), Tournament tier (string), Team name or player name for roster lookups, Remote MCP endpoint URL (https://mcp-api.op.gg/mcp), MCP serverCapabilities response (JSON structure describing available tools and their schemas), desired_output_fields (array of strings, e.g., ['winRate', 'pickRate', 'banRate']), Game-prefixed tool names (lol_*, tft_*, valorant_*), Game-specific parameters (summoner names, agent names, deck compositions, etc.), Remote endpoint URL (https://mcp-api.op.gg/mcp), MCP protocol messages (JSON-RPC 2.0 format), JSON-RPC 2.0 messages over stdin from local MCP client

Produces: MCP tool call responses (JSON-RPC 2.0 format over stdout), Structured gaming data (champion stats, match history, leaderboards, esports schedules), Champion statistics (win rate, pick rate, ban rate, average KDA, item builds), Summoner profile data (rank, LP, win rate, main champions, match history), Match details (participants, kills/deaths/assists, items built, duration, outcome), Pro player stats and esports schedule data (team, tournament, match results), Running MCP server process listening on stdio, MCP tools available to local clients (Claude Desktop, Cursor, etc.), Meta deck compositions (unit names, synergies, average placement, win rate), Item build recommendations (optimal items, item combinations, synergy descriptions), Augment data (augment names, tier, synergy effects, pick rates), Play style classifications and tier-specific meta shifts, Agent statistics (pick rate, ban rate, win rate, average combat score, average kills/deaths/assists), Map-specific meta (agent viability per map, economy strategies, site-specific tactics), Leaderboard rankings (player name, rank, rating points, recent match results), Player match history (agents played, map, result, performance metrics), Match schedules (match ID, teams, scheduled time, region, tournament name), Team rosters (team name, players, roles, organization), Tournament brackets and standings (team rankings, win-loss records, points), Historical match results (teams, final score, MVP, match statistics), Registered request/notification handlers on local MCP Server, Tool definitions available to local MCP clients (automatically mirrored from remote), Filtered JSON response containing only specified fields, Reduced payload size compared to full response, Game-specific structured data (champion stats, agent meta, deck compositions, etc.), Unified response format (JSON with desired_output_fields filtering applied), MCP protocol responses (JSON-RPC 2.0 format over HTTP), JSON-RPC 2.0 messages over stdout to local MCP client

UnfragileRank

Adoption15%(30% weight)

Quality30%(25% weight)

Ecosystem30%(25% weight)

Match Graph10%(15% weight)

Freshness75%(5% weight)

UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.

Type: MCP Server

11 capabilities

Visit OP.GG→

About

** - Access real-time gaming data across popular titles like League of Legends, TFT, and Valorant, offering champion analytics, esports schedules, meta compositions, and character statistics.

Alternatives to OP.GG

IntelliCode50Extension

AI-assisted development

Compare →

GitHub Copilot Chat53Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot52Extension

Your AI pair programmer

Compare →

Claude Code for VS Code52Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

Are you the builder of OP.GG?

Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.

Claim this artifact →Verification via email

Get the weekly brief

New tools, rising stars, and what's actually worth your time. No spam.

Data Sources

github awesome

Looking for something else?

Search →

Capabilities11 decomposed

stdio-to-http mcp protocol bridging with transparent request forwarding

Medium confidence

Solves for

Best for

AI agent developers integrating gaming data into Claude or Cursor workflows

Teams deploying MCP servers in restricted network environments requiring local proxies

Builders wanting transparent HTTP-to-stdio adaptation without custom integration code

Requires

Node.js runtime (version not specified in docs, but dist/index.js implies Node 14+)

Network access to https://mcp-api.op.gg/mcp endpoint

MCP client supporting stdio transport (Claude Desktop, Cursor, or custom MCP client)

Limitations

Adds network round-trip latency for every tool call (remote HTTP request to https://mcp-api.op.gg/mcp)

No local caching or request deduplication — each tool call results in a fresh HTTP request

Requires network connectivity to remote OP.GG endpoint; no offline fallback or graceful degradation

What makes it unique

vs alternatives

Simpler than building custom HTTP client integrations in each AI framework because it leverages standard MCP protocol, making it compatible with any stdio-based MCP client without modification.

league of legends champion and summoner data querying with field-level filtering

Medium confidence

Solves for

Best for

Gaming content creators building League of Legends analysis tools or guides

Esports analysts automating match research and player performance tracking

AI agents providing real-time meta recommendations to players during champion select

Requires

Valid summoner name and region (e.g., 'NA', 'EUW', 'KR') for summoner-specific queries

Champion name or ID for champion-specific analytics

Optional: desired_output_fields array to specify which response fields to include (e.g., ['winRate', 'pickRate', 'banRate'])

Limitations

Data freshness depends on OP.GG's update frequency (typically 5-15 minute delay from live matches)

Summoner lookups require exact summoner name and region; fuzzy matching not supported

Match history limited to recent matches (typically last 100-200 matches); full historical data not available

What makes it unique

vs alternatives

installation and deployment via smithery, npm, or docker

Medium confidence

Solves for

Best for

Individual developers integrating OP.GG data into Claude Desktop or Cursor

Teams using Smithery for MCP server management and orchestration

Organizations deploying MCP proxies in containerized infrastructure (Docker, Kubernetes)

Requires

For Smithery: Smithery client installed, smithery.yaml configuration file

For npm/npx: Node.js 14+ and npm, or npx (bundled with npm 5.2+)

For Docker: Docker runtime, Dockerfile (provided in repo), and Docker image build capability

Limitations

Smithery installation requires Smithery client and smithery.yaml configuration; not suitable for non-Smithery environments

npm/npx installation requires Node.js and npm; not suitable for environments without Node.js runtime

Docker deployment requires Docker runtime and image building; adds complexity for simple use cases

What makes it unique

vs alternatives

More flexible than tools supporting only one deployment method because it accommodates Smithery-based orchestration, manual npm invocation, and containerized deployments without code changes.

teamfight tactics meta composition and augment analysis with play style filtering

Medium confidence

Solves for

Best for

TFT content creators and streamers building real-time meta guides

AI agents providing in-game coaching recommendations during TFT matches

Esports analysts tracking meta shifts across tournament patches

Requires

Current TFT set identifier (e.g., 'Set 11') — OP.GG typically supports 1-2 active sets

Optional: rank tier filter (string: 'IRON', 'BRONZE', 'SILVER', 'GOLD', 'PLATINUM', 'DIAMOND', 'MASTER', 'CHALLENGER')

Optional: play style filter (string: 'aggressive', 'control', 'economy', or similar OP.GG-defined categories)

Limitations

Meta data updates only when TFT set changes or OP.GG refreshes statistics (typically daily)

Play style classifications are OP.GG-defined categories; custom play style filters not supported

Augment recommendations are statistical aggregates, not contextual to current game state (player items, remaining units, etc.)

What makes it unique

vs alternatives

valorant agent, map, and leaderboard data retrieval with region-specific filtering

Medium confidence

Solves for

Best for

Valorant esports analysts and content creators covering regional competitive scenes

AI coaching agents providing agent selection recommendations during agent select phase

Competitive players researching region-specific meta before tournaments

Requires

Region code (string: 'NA', 'EU', 'APAC', 'BR', 'LATAM', 'KR', 'JP') for region-specific queries

Optional: rank tier filter (string: 'IRON', 'BRONZE', 'SILVER', 'GOLD', 'PLATINUM', 'DIAMOND', 'ASCENDANT', 'IMMORTAL', 'RADIANT')

Optional: agent name for agent-specific analytics

Limitations

Region-specific data may have sparse samples at high ranks (Radiant/Immortal) due to small player pools

Agent meta updates reflect historical data (typically 24-48 hours old) rather than real-time pick rates

Map-specific strategies are statistical aggregates; no contextual recommendations based on team composition or opponent agents

What makes it unique

vs alternatives

esports schedule and tournament data aggregation across multiple games

Medium confidence

Solves for

Best for

Esports content platforms and news aggregators covering multiple gaming titles

Tournament organizers and esports teams tracking match schedules and results

AI agents generating esports match previews and predictions

Requires

Game title filter (string: 'lol', 'tft', 'valorant') to specify which esports scene to query

Optional: region code (string: 'NA', 'EU', 'KR', 'CN', etc.) for region-specific tournaments

Optional: tournament tier filter (string: 'regional', 'international', 'challenger', etc.)

Limitations

Tournament data updates are periodic (typically daily or per-match-day) rather than real-time

Historical data availability varies by tournament tier; regional league data more complete than international events

No live match data (current score, round-by-round progression) — only pre-match and post-match information

What makes it unique

vs alternatives

Consolidates esports schedules and rosters from multiple games into a single MCP interface, eliminating the need to integrate separate APIs for each game's esports data.

dynamic mcp capability discovery and tool registry mirroring at startup

Medium confidence

Solves for

Best for

Teams maintaining long-lived MCP proxies that need to adapt to upstream API changes

Builders creating generic MCP proxy infrastructure that should work with any remote endpoint

Developers who want to avoid manual tool registry synchronization between local and remote servers

Requires

Network connectivity to remote MCP endpoint at startup time

Remote endpoint must implement MCP serverCapabilities protocol (standard MCP feature)

Node.js runtime with @modelcontextprotocol/sdk library for MCP protocol implementation

Limitations

Capability discovery happens only at startup; tool changes on the remote endpoint require proxy restart to take effect

No caching of discovered capabilities; each startup incurs a network round-trip to fetch serverCapabilities

If the remote endpoint is unavailable at startup, the proxy fails to initialize (no graceful degradation with cached capabilities)

What makes it unique

vs alternatives

response payload optimization via field-level filtering at api boundary

Medium confidence

Solves for

Best for

Token-constrained LLM applications where every byte of context matters

High-volume data aggregation scenarios where bandwidth optimization is critical

Mobile or edge deployments with limited network bandwidth

Requires

Knowledge of available field names for the specific tool being queried (documented in tool schemas)

Optional: desired_output_fields array parameter (if omitted, full response is returned)

Remote OP.GG endpoint must support field filtering (standard feature of all 27 tools)

Limitations

Requires knowledge of available field names for each tool; no schema introspection or field discovery API

Field filtering is all-or-nothing; partial field selection not supported (either include a field or exclude it entirely)

No computed fields or field transformations; only raw fields returned by the remote API can be filtered

What makes it unique

vs alternatives

More efficient than client-side filtering because it reduces payload size at the source, saving bandwidth and token consumption compared to receiving full responses and filtering locally.

multi-game gaming data aggregation under unified mcp interface

Medium confidence

Solves for

Best for

Multi-game esports platforms and content aggregators

Gaming communities that span multiple titles (e.g., esports organizations with teams in multiple games)

AI agents providing cross-game recommendations or analysis

Requires

MCP client capable of handling 27 tools with game-specific prefixes

Knowledge of which game's tools to query for specific use cases (lol_ for League, tft_ for TFT, valorant_ for Valorant)

Optional: region codes and rank tiers specific to each game

Limitations

Tool naming requires game prefixes (lol_, tft_, valorant_) to avoid collisions; no unified tool naming across games

Data models are game-specific; no common schema for cross-game comparisons (e.g., 'win rate' definitions vary by game)

Meta data freshness may differ by game (League updates more frequently than TFT or Valorant)

What makes it unique

vs alternatives

streamable http client transport for remote mcp endpoint connectivity

Medium confidence

Solves for

Best for

Builders creating MCP proxies that need to connect to remote HTTP-based MCP endpoints

Teams wanting to avoid custom HTTP client implementation and rely on standard MCP transport abstractions

Developers integrating MCP clients with remote services over HTTP

Requires

@modelcontextprotocol/sdk library (version not specified, but latest recommended)

Node.js runtime with native fetch API or polyfill for HTTP requests

Network connectivity to remote MCP endpoint (https://mcp-api.op.gg/mcp)

Limitations

StreamableHTTPClientTransport is a specific SDK implementation; switching to different HTTP libraries requires code changes

No built-in request caching or response memoization; each tool call results in a fresh HTTP request

HTTP connection pooling and timeout behavior depends on SDK defaults; limited customization options

What makes it unique

vs alternatives

Simpler than implementing custom HTTP clients because it uses standard MCP transport abstractions from the SDK, reducing code complexity and ensuring protocol compliance.

stdio server transport for local mcp client communication

Medium confidence

Solves for

Best for

Builders creating MCP servers that need to integrate with Claude Desktop or other stdio-based MCP clients

Teams wanting to avoid custom stdio protocol implementation and rely on standard MCP transport abstractions

Developers building MCP proxies that need to expose themselves as local servers

Requires

@modelcontextprotocol/sdk library (version not specified, but latest recommended)

Node.js runtime with stdio access (standard for Node.js processes)

MCP client supporting stdio transport (Claude Desktop, Cursor, or custom MCP client)

Limitations

StdioServerTransport is stdio-specific; switching to other transports (WebSocket, HTTP) requires code changes

Single-threaded stdio processing means concurrent requests from multiple clients will queue sequentially

No built-in request queueing or priority handling; all requests processed in FIFO order

What makes it unique

vs alternatives

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Alternatives to OP.GG

IntelliCode50Extension

AI-assisted development

Compare →

GitHub Copilot Chat53Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot52Extension

Your AI pair programmer

Compare →

Claude Code for VS Code52Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

OP.GG

Capabilities11 decomposed

stdio-to-http mcp protocol bridging with transparent request forwarding

league of legends champion and summoner data querying with field-level filtering

installation and deployment via smithery, npm, or docker

teamfight tactics meta composition and augment analysis with play style filtering

valorant agent, map, and leaderboard data retrieval with region-specific filtering

esports schedule and tournament data aggregation across multiple games

dynamic mcp capability discovery and tool registry mirroring at startup

response payload optimization via field-level filtering at api boundary

multi-game gaming data aggregation under unified mcp interface

streamable http client transport for remote mcp endpoint connectivity

stdio server transport for local mcp client communication

Related Artifactssharing capabilities

@modelcontextprotocol/node

supergateway

mcp-proxy

inspector

ECharts

tea-color-to-vars-mcp-server

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

About

Categories

Alternatives to OP.GG

Are you the builder of OP.GG?

Get the weekly brief

Data Sources

OP.GG

Capabilities11 decomposed

stdio-to-http mcp protocol bridging with transparent request forwarding

league of legends champion and summoner data querying with field-level filtering

installation and deployment via smithery, npm, or docker

teamfight tactics meta composition and augment analysis with play style filtering

valorant agent, map, and leaderboard data retrieval with region-specific filtering

esports schedule and tournament data aggregation across multiple games

dynamic mcp capability discovery and tool registry mirroring at startup

response payload optimization via field-level filtering at api boundary

multi-game gaming data aggregation under unified mcp interface

streamable http client transport for remote mcp endpoint connectivity

stdio server transport for local mcp client communication

Related Artifactssharing capabilities

@modelcontextprotocol/node

supergateway

mcp-proxy

inspector

ECharts

tea-color-to-vars-mcp-server

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

About

Categories

Alternatives to OP.GG

Are you the builder of OP.GG?

Get the weekly brief

Data Sources