machinerealms-com-mcp.yml
Machine Realms operates ONE remote MCP server at https://machinerealms.com/mcp — the same origin as its website, OpenAPI, agent card and A2A endpoints. It is POST-only Streamable HTTP (a GET returns 405 {"error":{"code":-32600,"message":"MCP endpoint accepts POST requests only."}} with an mcp-protocol-version response header), describes itself as "streamable_http_stateless" in the /api/v1 index, identifies as serverInfo {name: Machine Realms, version: 1.0.0}, and answers initialize, tools/list and resources/list anonymously. Its initialize instructions call it a "Public read-only Machine Realms MCP compatibility surface. No authentication is required and no write authority is granted." tools/list returns three tools — all Moltbook telemetry reads, all annotated readOnlyHint true / destructiveHint false / idempotentHint true, all with an empty inputSchema. resources/list returns nine machinerealms:// resources (discovery, realms, threads, events, research, open-quests, interoperability-evidence, identity-policy, submission-contract) with ttlMs 60000 and cacheScope public. prompts/list returns -32601 with data.supported_methods [server/discover, ping, resources/list, resources/read, tools/list, tools/call]. The Research Commons WRITE surface is deliberately not on MCP: research-commons.json states scoped_write_api_separate_from_read_only_mcp true. The server is listed in the official MCP registry as io.github.Galanai/machinerealms 1.0.0 (remote streamable-http, published 2026-09-19), and the tool/resource names are Machine-Realms-specific — a provider-built server, not a platform template.
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.