Awesome Remote MCP Servers by JAW9C
MCP ServerFree** - A curated list of **remote** MCP servers, including their authentication support by **[JAW9C](https://github.com/jaw9c)**
Capabilities9 decomposed
curated remote mcp server discovery and directory lookup
Medium confidenceMaintains a hand-curated, quality-filtered directory of remote MCP servers accessible via HTTP endpoints (/sse for SSE transport, /mcp for streamed HTTP preferred). The directory enforces four legitimacy criteria: domain verification against official vendors, permissioned authentication scope, URL-based ease of use without local installation, and web client compatibility. Servers are indexed with their authentication methods (OAuth 2.1, API Key, Open) and transport endpoints, enabling developers to discover and validate remote MCP servers before integration.
Exclusively focuses on remote HTTP-accessible MCP servers (not local processes), enforcing vendor legitimacy verification and authentication transparency as core curation criteria. Provides dual transport endpoint support (/sse deprecated, /mcp preferred) and explicitly maps authentication types to consumption paths (MCP clients vs. LLM API libraries), enabling developers to make informed integration decisions upfront.
More authoritative and security-focused than generic MCP server lists because it verifies domain legitimacy, documents authentication requirements per server, and explicitly excludes local servers that lack vendor transparency — making it safer for production integrations.
mcp client configuration guide and url-based server connection
Medium confidenceProvides step-by-step integration instructions for connecting remote MCP servers to MCP-aware clients (Cursor, VS Code, Claude Desktop, Claude.ai, Claude Code, Windsurf, Cline, Gemini CLI, ChatGPT) via configuration files or UI. Clients accept a server URL directly; for OAuth-protected servers, the client manages the token acquisition flow natively without developer code. Configuration mechanisms vary by client: Cursor and VS Code use JSON config files (~/.cursor/mcp.json, settings.json), Claude Desktop uses UI settings, Claude Code uses CLI (claude mcp add --transport http), and web clients accept URLs through connector UI.
Abstracts away transport protocol complexity (SSE vs. streamed HTTP) and OAuth token lifecycle management by delegating to the client — developers provide only a URL and credentials, and the client handles connection, token refresh, and capability discovery. Provides client-specific configuration templates (JSON, CLI, UI) rather than a one-size-fits-all approach.
Simpler than programmatic SDK integration because clients manage OAuth flows natively and require no code — just URL + credentials in config. Faster to set up than local MCP servers because no package installation or subprocess management is needed.
llm api library integration with remote mcp server specification
Medium confidenceEnables developers to specify remote MCP servers directly in Anthropic SDK, OpenAI SDK, and Gemini SDK API requests. Unlike MCP clients (which manage OAuth natively), the developer is responsible for authentication — OAuth token management must be handled manually in code, while API Key authentication is simpler. This path is used when building programmatic LLM workflows that need access to remote MCP server tools and resources, rather than interactive AI assistant workflows.
Shifts authentication responsibility from the client to the developer — requires manual OAuth token management in code, but provides fine-grained control over token lifecycle and enables programmatic agentic workflows. Supports API Key authentication as a simpler alternative, making it practical for applications that don't require OAuth's permission model.
More flexible than MCP client integration for agentic workflows because the developer controls tool invocation logic, token refresh, and error handling. Simpler than building custom tool calling code because the SDK abstracts MCP protocol details — developer just passes URL and credentials.
authentication method documentation and capability mapping
Medium confidenceDocuments four authentication models used by remote MCP servers (OAuth 2.1 with dynamic registration, OAuth 2.1 without dynamic registration, API Key, and Open/no auth) and maps each to practical consumption paths. OAuth servers are marked with 🔐 symbol and may require pre-registration. The documentation explains which auth types work best with MCP clients (native OAuth flow support) vs. LLM API libraries (manual token management required). This enables developers to understand upfront whether a server's authentication model fits their integration path.
Explicitly maps authentication types to consumption paths (MCP clients vs. LLM API libraries) and documents pre-registration requirements per server, enabling developers to assess compatibility before integration. Uses visual symbols (🔐) to flag OAuth servers requiring pre-registration, making authentication friction visible upfront.
More transparent than generic MCP documentation because it documents real-world authentication friction (pre-registration, manual token management) and maps auth types to practical integration paths. Helps developers avoid integration failures due to unexpected authentication requirements.
http transport endpoint standardization and protocol selection
Medium confidenceDocuments two HTTP transport endpoints used by remote MCP servers: /sse (Server-Sent Events, being deprecated) and /mcp (streamed HTTP, preferred standard). The directory lists both endpoint formats in the README, and some clients may auto-discover the full URL from a base prefix in the future. This capability helps developers understand which transport protocol a server uses and whether their client supports it, avoiding connection failures due to endpoint mismatch.
Explicitly documents the transition from deprecated /sse to preferred /mcp transport endpoints and acknowledges that both are currently in use. Provides clarity on which endpoint format is standard, helping developers avoid connection failures due to endpoint mismatch and supporting migration to the preferred protocol.
More transparent than generic MCP documentation because it explicitly flags /sse as deprecated and /mcp as preferred, helping developers make informed choices about which servers to integrate and when to migrate. Reduces connection troubleshooting by documenting both endpoint formats upfront.
remote vs. local mcp server comparison and legitimacy verification
Medium confidenceExplains why this directory is restricted to remote (HTTP-accessible) MCP servers and excludes local NPM-based servers. Remote servers provide four advantages: (1) domain visibility in the URL enables verification against official vendors, (2) authentication methods determine data access scope transparently, (3) URL-based access requires no local package installation, and (4) remote servers are the only kind compatible with web-based MCP clients. This capability helps developers understand the security and usability benefits of remote servers and how to verify vendor legitimacy.
Explicitly restricts the directory to remote servers and documents the security and usability advantages (domain visibility, authentication transparency, no local installation, web client compatibility) that justify this scope. Provides a clear rationale for why remote servers are safer and more verifiable than local NPM packages.
More security-focused than generic MCP server lists because it restricts to remote servers with visible domains, enabling vendor verification. Explains why web-based clients require remote servers, helping developers understand the architectural constraints of different client types.
submission and contribution guidelines for new remote mcp servers
Medium confidenceProvides structured guidelines for submitting new remote MCP servers to the curated directory, including submission format, pull request process, and quality criteria. Servers must meet legitimacy criteria (domain verification, authentication transparency, URL-based access, web client compatibility) before inclusion. The contribution process is documented to enable community curation while maintaining quality standards and preventing spam or unvetted servers from entering the directory.
Enforces quality criteria and legitimacy verification as part of the contribution process, ensuring that only vetted remote servers enter the directory. Provides structured submission format and pull request process to enable community curation while maintaining standards.
More rigorous than open registries because it requires manual review and quality verification before inclusion, preventing spam and unvetted servers. Provides clear submission guidelines, reducing friction for contributors while maintaining directory quality.
faq and troubleshooting documentation for remote mcp server integration
Medium confidenceProvides frequently asked questions and troubleshooting guidance for common integration scenarios, including transport endpoint selection (/sse vs. /mcp), OAuth token management, client configuration, and SDK integration. FAQs address real-world integration friction points and help developers resolve connection issues, authentication failures, and capability discovery problems without requiring direct support.
Addresses real-world integration friction points (transport endpoint confusion, OAuth token management, capability discovery) with practical troubleshooting guidance. Provides self-service support for common issues, reducing support burden on maintainers.
More practical than generic MCP documentation because it focuses on common integration failures and provides step-by-step troubleshooting. Reduces time-to-integration by addressing predictable issues upfront.
code of conduct and community governance for directory contributions
Medium confidenceEstablishes community standards and governance for the awesome-remote-mcp-servers repository, including code of conduct, license terms, and contribution expectations. This capability ensures that the directory remains a welcoming, inclusive, and legally compliant community resource. The code of conduct sets expectations for respectful interaction, and license terms clarify how the directory and contributed servers can be used.
Establishes explicit community standards and governance for the directory, ensuring that contributions are respectful, inclusive, and legally compliant. Provides clarity on license terms and contribution expectations upfront.
More transparent than unmoderated registries because it establishes clear community standards and governance. Reduces friction and conflict by setting expectations upfront and providing a code of conduct for respectful interaction.
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 Awesome Remote MCP Servers by JAW9C, ranked by overlap. Discovered automatically through the match graph.
AllInOneMCP
MCP of MCPs. A central hub for MCP servers. Helps you discover available MCP servers and learn how to install and use them. REMOTE! Use the url [https://mcp.pfvc.io/mcp/](https://mcp.pfvc.io/mcp/) to add the server. **Remember the final backslash\*\*.
1mcpserver
** - MCP of MCPs. Automatic discovery and configure MCP servers on your local machine. Fully REMOTE! Just use [https://mcp.1mcpserver.com/mcp/](https://mcp.1mcpserver.com/mcp/)
C# MCP SDK
[Go MCP SDK](https://github.com/modelcontextprotocol/go-sdk)
MCPVerse
** - A portal for creating & hosting authenticated MCP servers and connecting to them securely.
mcps-playground
** a playground for Remote MCP servers
mcp.natoma.ai
** – A Hosted MCP Platform to discover, install, manage and deploy MCP servers by **[Natoma Labs](https://www.natoma.ai)**
Best For
- ✓developers integrating remote MCP servers into Cursor, VS Code, Claude Desktop, or ChatGPT
- ✓teams evaluating which remote MCP servers meet their security and authentication requirements
- ✓non-technical users seeking pre-vetted, official MCP server URLs without manual validation
- ✓developers using Cursor, VS Code, or Claude Desktop who want zero-code MCP server integration
- ✓non-technical users setting up AI assistants with custom MCP server connectors
- ✓teams managing multiple MCP server connections across different clients
- ✓developers building LLM agents or agentic workflows that need external tool access
- ✓teams using Anthropic, OpenAI, or Gemini SDKs and wanting to extend them with remote MCP servers
Known Limitations
- ⚠Directory is curated manually — new servers may have latency before inclusion
- ⚠Only covers remote HTTP-accessible servers; excludes local NPM-based MCP servers
- ⚠Authentication support varies by server; some require manual OAuth token management in API library paths
- ⚠Transport endpoint standardization is ongoing — /sse is deprecated but still present in some servers
- ⚠Configuration format is client-specific — no unified config standard across all MCP clients
- ⚠OAuth token management is client-dependent; some clients may require pre-registration or manual token refresh
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
About
** - A curated list of **remote** MCP servers, including their authentication support by **[JAW9C](https://github.com/jaw9c)**
Categories
Alternatives to Awesome Remote MCP Servers by JAW9C
Are you the builder of Awesome Remote MCP Servers by JAW9C?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →