Composio documents MCP server creation through its SDK and dashboard at docs.composio.dev: developers call `composio.mcp.create()` with toolkit names, auth config IDs, and an `allowed_tools` list, then generate per-user MCP URLs via `composio.mcp.generate(user_id, mcp_config_id)`. Hosted endpoints follow the pattern `https://backend.composio.dev/v3/mcp/{SERVER_ID}?user_id=...` and require an `x-api-key` header when `require_mcp_api_key` is enabled (default for new orgs). Docs show wiring these URLs into OpenAI Responses API, Anthropic MCP client beta, Mastra MCPClient, Claude Desktop, and Cursor. Composio notes that dynamic sessions are recommended for most use cases, while single-toolkit MCP configs suit fixed integration surfaces.
Use cases
- Expose Gmail, GitHub, Slack, or other Composio toolkits to agents through one MCP URL per user
- Restrict agent surface area with explicit `allowed_tools` instead of entire toolkit catalogs
- Connect OpenAI or Anthropic MCP clients using documented `x-api-key` header patterns
- Manage MCP configs from the Composio dashboard alongside SDK-created servers
- Prototype SaaS integrations where each end user authenticates toolkits before MCP URL generation
Key features
- Cursor
- Claude Desktop
- OpenAI Agents
- Anthropic Claude
- Codex
Frequently Asked Questions
- Do users need to authenticate toolkits first?
- Docs state users must authenticate with configured toolkits before MCP URL generation works.
- Is x-api-key always required?
- Required when require_mcp_api_key is enabled; docs call this the default for newly created organizations.
- Single-toolkit MCP vs sessions?
- Docs recommend dynamic sessions for most cases; single-toolkit MCP is for fixed integration surfaces.
Related
Related
3 Indexed items
Langfuse MCP Server
Langfuse documents two MCP surfaces: a hosted Prompt Management server at `https://cloud.langfuse.com/api/public/mcp` (streamable HTTP, built into the platform per langfuse.com/docs/prompt-management/features/mcp-server) with tools such as `createTextPrompt`, `createChatPrompt`, `getPrompt`, and `updatePromptLabels`; and a public Docs MCP at `https://langfuse.com/api/mcp` for semantic search over Langfuse documentation (`searchLangfuseDocs`) without authentication. The legacy `langfuse/mcp-server-langfuse` Node server remains for local command-based setups with LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY. Langfuse positions MCP for agentic onboarding—IDE agents can add tracing to OpenAI, Anthropic, or LangChain codebases from the Get Started agentic tab.
Mem0 MCP Server
Mem0 documents a hosted Model Context Protocol server at https://mcp.mem0.ai/mcp that exposes Platform memory tools (`add_memory`, `search_memories`, `get_memories`, `update_memory`, `delete_memory`, `delete_all_memories`, `delete_entities`, `list_entities`, `list_events`, `get_event_status`) to Claude, Claude Code, Codex, Cursor, Windsurf, VS Code, and OpenCode. Setup uses `npx mcp-add` with HTTP transport or manual JSON/TOML client configs; Codex requires `MEM0_API_KEY` as bearer token per docs.mem0.ai/platform/mem0-mcp. The cloud server needs a Mem0 Platform API key from the dashboard and Node.js for the installer—no local vector database required for the hosted path.
Apify MCP Server
Apify documents an official Model Context Protocol server hosted at https://mcp.apify.com that speaks Streamable HTTP in line with the current MCP specification; Apify warns that SSE transport was deprecated for removal April 1, 2026. Hosted clients authenticate through browser OAuth or by supplying Bearer tokens sourced from Console → Settings → Integrations (`APIFY_TOKEN`), can pin tool bundles via URL query (`?tools=actors,docs,apify/rag-web-browser` style examples reproduce Apify wording), optionally append `telemetry-enabled=false`, and benefit from inferred structured-output schemas surfaced for Actor tooling on hosted endpoints unlike the default stdio server. When MCP clients refuse remote transports, docs recommend `npx -y @apify/actors-mcp-server` with `APIFY_TOKEN` for stdio, Node.js ≥18, and adherence to documented per-user throughput (Apify cites up to thirty requests per second across Actor runs plus storage/documentation calls). Specialized payment modes (open x402 on Base plus Skyfire) appear as optional adjunct pages inside the broader integration handbook.