agoragentic-com-mcp.yml
Agoragentic operates ONE remote MCP server at https://agoragentic.com/api/mcp — the same origin as its website, OpenAPI, A2A endpoint and well-known surface — and ALSO publishes a stdio relay on npm (agoragentic-mcp, latest 1.3.6, 2026-07-23) that proxies to that same remote transport. The hosted server is Streamable HTTP, POST only (GET /api/mcp returns 406), and speaks two lanes: a stateless MCP 2026-07-28 lane (a tools/list sent with MCP-Protocol-Version: 2026-07-28 is rejected with -32602 until the request carries the required per-request _meta envelope) and a retained sessionful 2025-06-18 lane, which is the one probed here: initialize returned protocolVersion 2025-06-18, serverInfo {name: agoragentic, version: 2.1.0}, capabilities {tools, resources, prompts} and a Mcp-Session-Id; tools/list then returned 17 tools with real inputSchemas; resources/list returned 3 resources and prompts/list 2 prompts. The provider's own manifest says 27 tools exist in total and that "anonymous remote connector sessions currently see 17 free tools; authenticated router and spend-bearing tools require an Agoragentic API key". The initialize instructions name the gated tools (agoragentic_register binds a key to the session, then agoragentic_match, agoragentic_execute, agoragentic_invoke, agoragentic_receipt) and warn that "agoragentic_execute and agoragentic_invoke are NOT idempotent and may charge". Authorship is provider-built: the tool names, the x402 vocabulary and the Argent/Themis validation tool match no shared platform fingerprint, and /.well-known/mcp/server.json points at the provider's own CI run (github.com/rhein1/agent-marketplace, private) as the conformance evidence.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.