{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-convex","slug":"convex","name":"Convex","type":"mcp","url":"https://stack.convex.dev/convex-mcp-server","page_url":"https://unfragile.ai/convex","categories":["mcp-servers"],"tags":[],"pricing":{"model":"unknown","free":false,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-convex__cap_0","uri":"capability://tool.use.integration.deployed.app.introspection.via.mcp","name":"deployed-app-introspection-via-mcp","description":"Enables Claude and other MCP clients to introspect live Convex deployments by exposing app schema, data models, and configuration through the Model Context Protocol. Uses MCP's resource and tool abstractions to surface Convex-specific metadata (tables, functions, auth config) as queryable resources, allowing AI agents to understand app structure without manual documentation or API exploration.","intents":["I want Claude to understand my Convex app's data schema so it can help me write queries","I need to debug my deployed Convex functions by inspecting their signatures and dependencies","I want an AI agent to explore my app's structure and suggest optimizations","I need to generate boilerplate code that matches my actual Convex schema"],"best_for":["Convex developers using Claude or MCP-compatible AI editors","Teams building AI-assisted development workflows on Convex","Solo developers wanting AI-powered code generation for Convex apps"],"limitations":["Read-only introspection — cannot modify deployed functions or data directly through MCP","Requires active Convex deployment — cannot introspect local development instances without deployment","MCP client must support Convex-specific resource types; generic MCP clients may have limited utility","No real-time streaming of logs or execution traces — snapshot-based introspection only"],"requires":["Convex project deployed to Convex cloud","MCP-compatible client (Claude, VS Code with MCP extension, etc.)","Valid Convex API credentials or deployment token","Network access to Convex cloud API endpoints"],"input_types":["MCP resource requests (table names, function names, schema queries)","Natural language queries from Claude about app structure"],"output_types":["JSON schema definitions for Convex tables","Function signatures with parameter types and return types","Deployment metadata (environment variables, auth config)","Structured introspection results compatible with MCP protocol"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-convex__cap_1","uri":"capability://tool.use.integration.convex.query.execution.via.mcp.tools","name":"convex-query-execution-via-mcp-tools","description":"Exposes Convex query and mutation functions as callable MCP tools, allowing Claude and other AI agents to execute read and write operations against a live Convex deployment. Implements tool schema mapping where each Convex function becomes an MCP tool with parameter validation, return type coercion, and error handling that translates between Convex's TypeScript function signatures and MCP's JSON-RPC tool calling protocol.","intents":["I want Claude to fetch data from my Convex database and summarize it","I need an AI agent to execute mutations (create, update, delete) on my Convex data","I want to run complex queries through Claude without writing custom API endpoints","I need to automate data operations by having Claude call my Convex functions"],"best_for":["Developers building AI agents that need read/write access to Convex data","Teams automating data workflows with Claude as the orchestrator","Rapid prototyping of AI-driven CRUD operations without custom API layers"],"limitations":["Execution latency includes MCP serialization overhead (~50-200ms per call depending on payload size)","No transaction support across multiple function calls — each tool invocation is atomic but independent","Authentication relies on deployment-level credentials; fine-grained access control must be implemented in Convex function logic","Tool parameter validation happens at MCP layer, not Convex layer — type mismatches may not surface until execution"],"requires":["Convex deployment with public or authenticated query/mutation functions","MCP client with tool-calling capability (Claude, etc.)","Valid Convex API key or deployment token with appropriate permissions","Convex functions must be exported and callable (not internal utilities)"],"input_types":["MCP tool call requests with JSON parameters","Natural language instructions from Claude to execute specific functions"],"output_types":["JSON results from Convex query/mutation execution","Structured error responses with Convex error codes","Typed return values matching Convex function signatures"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-convex__cap_2","uri":"capability://memory.knowledge.live.deployment.context.for.ai.agents","name":"live-deployment-context-for-ai-agents","description":"Maintains a live, queryable context of a Convex deployment's state (schema, functions, data samples, auth rules) that AI agents can reference during reasoning and code generation. Implements context caching and incremental updates so agents can reason about app structure without re-fetching full introspection data on every interaction, reducing latency and token usage in multi-turn conversations.","intents":["I want Claude to remember my app's schema across multiple conversation turns","I need an AI agent to generate code that's consistent with my actual Convex deployment","I want to avoid re-explaining my data model to Claude in every message","I need the agent to catch schema mismatches before executing queries"],"best_for":["Developers in long-running AI conversations about their Convex app","Teams using Claude for iterative development and debugging","Scenarios where token efficiency and latency matter (cost-sensitive deployments)"],"limitations":["Context becomes stale if schema changes in deployment — requires manual refresh or polling mechanism","Context size grows with app complexity; very large schemas may exceed MCP message size limits","No built-in conflict detection if multiple agents operate on same deployment simultaneously","Cache invalidation strategy not specified — unclear how often context syncs with live deployment"],"requires":["Convex deployment with stable schema","MCP client supporting context/resource caching","Sufficient memory in MCP server to maintain deployment context"],"input_types":["Initial deployment introspection request","Schema change notifications (if polling enabled)","Agent queries referencing cached context"],"output_types":["Cached schema and function definitions","Context summaries for agent reasoning","Invalidation signals when deployment changes"],"categories":["memory-knowledge","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-convex__cap_3","uri":"capability://code.generation.editing.schema.aware.code.generation.for.convex","name":"schema-aware-code-generation-for-convex","description":"Generates type-safe Convex code (queries, mutations, components) by analyzing live deployment schema and function signatures. Uses the introspected schema as context for Claude's code generation, ensuring generated code matches actual table structures, field types, and function parameters without manual type definitions or boilerplate.","intents":["I want Claude to generate a query function that matches my actual table schema","I need to create a mutation that respects my data model's constraints","I want to scaffold a new Convex component with correct types","I need to refactor existing code to match schema changes"],"best_for":["Convex developers using Claude for rapid prototyping","Teams onboarding new developers who need schema-aware code generation","Scenarios where type safety and schema consistency are critical"],"limitations":["Generated code may not follow project-specific conventions or patterns","No validation that generated code actually works until deployed","Schema introspection only captures structure, not business logic or validation rules","Cannot generate code for complex Convex patterns (e.g., custom indexes, vector search) without explicit documentation"],"requires":["Convex deployment with queryable schema","Claude or MCP-compatible AI model","Live connection to Convex deployment for schema introspection"],"input_types":["Natural language requests for code generation","Introspected schema and function signatures","Existing code snippets for refactoring"],"output_types":["TypeScript code for Convex queries and mutations","Component definitions with correct prop types","Type definitions matching schema"],"categories":["code-generation-editing","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-convex__cap_4","uri":"capability://tool.use.integration.deployment.aware.debugging.and.diagnostics","name":"deployment-aware-debugging-and-diagnostics","description":"Provides Claude and AI agents with diagnostic information about a live Convex deployment (function execution logs, error traces, performance metrics) through MCP resources. Enables agents to analyze deployment issues, suggest fixes, and explain error patterns by correlating logs with schema and function definitions.","intents":["I want Claude to help me debug a failing Convex function by analyzing logs","I need to understand why a query is slow and get optimization suggestions","I want an AI agent to identify common error patterns in my deployment","I need to correlate function errors with schema changes"],"best_for":["Developers troubleshooting production Convex deployments","Teams using AI-assisted debugging and optimization","Scenarios where rapid diagnosis of deployment issues is critical"],"limitations":["Log access depends on Convex deployment's logging configuration — may be incomplete or missing","Real-time log streaming not specified — may only support historical log queries","Performance metrics may be aggregated or sampled, not granular per-request","No built-in correlation between logs and specific code changes or deployments"],"requires":["Convex deployment with logging enabled","API access to Convex logs and diagnostics","Sufficient log retention in Convex cloud"],"input_types":["Function names or error patterns to investigate","Time ranges for log queries","Performance metrics requests"],"output_types":["Structured log entries with timestamps and error details","Performance metrics (latency, error rates)","Diagnostic summaries and recommendations"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":25,"verified":false,"data_access_risk":"high","permissions":["Convex project deployed to Convex cloud","MCP-compatible client (Claude, VS Code with MCP extension, etc.)","Valid Convex API credentials or deployment token","Network access to Convex cloud API endpoints","Convex deployment with public or authenticated query/mutation functions","MCP client with tool-calling capability (Claude, etc.)","Valid Convex API key or deployment token with appropriate permissions","Convex functions must be exported and callable (not internal utilities)","Convex deployment with stable schema","MCP client supporting context/resource caching"],"failure_modes":["Read-only introspection — cannot modify deployed functions or data directly through MCP","Requires active Convex deployment — cannot introspect local development instances without deployment","MCP client must support Convex-specific resource types; generic MCP clients may have limited utility","No real-time streaming of logs or execution traces — snapshot-based introspection only","Execution latency includes MCP serialization overhead (~50-200ms per call depending on payload size)","No transaction support across multiple function calls — each tool invocation is atomic but independent","Authentication relies on deployment-level credentials; fine-grained access control must be implemented in Convex function logic","Tool parameter validation happens at MCP layer, not Convex layer — type mismatches may not surface until execution","Context becomes stale if schema changes in deployment — requires manual refresh or polling mechanism","Context size grows with app complexity; very large schemas may exceed MCP message size limits","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.2,"ecosystem":0.25,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-06-17T09:51:03.036Z","last_scraped_at":"2026-05-03T14:00:15.503Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=convex","compare_url":"https://unfragile.ai/compare?artifact=convex"}},"signature":"2aIMlCfts1Xdg+4RV4p8Fukxguea508dMgyu+oPY5fEFYzR/IkIyu1PZPoFeTyIqdNa6r536q4p284YB6El+Cg==","signedAt":"2026-06-20T19:58:56.956Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/convex","artifact":"https://unfragile.ai/convex","verify":"https://unfragile.ai/api/v1/verify?slug=convex","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}