deusproof-com-mcp.yml
DEUSPROOF ships the same MCP server two ways: a hosted Streamable HTTP endpoint at https://deusproof.com/mcp (the apex host — also the website, the REST /api and the A2A /a2a host) that answers initialize, tools/list, resources/list and prompts/list anonymously, and a local stdio package (PyPI deusproof-mcp 0.3.3, run as `uvx deusproof-mcp`) listed in the official MCP registry as io.github.Abracadabrastartup/deusproof-mcp with the same remote URL declared in its server.json. The live tools/list returned 11 tools, each with an inputSchema and MCP annotations (readOnlyHint / destructiveHint / openWorldHint); resources and prompts are empty lists. GET on the endpoint returns a JSON self-description (service, transport, protocolVersions, tools, "auth: none — free, no account") rather than 405. The provider's own docs explain the split: over the URL the server cannot hold the agent's private key, so records start "witnessed"; the local package generates an Ed25519 key at ~/.deusproof/ and signs, reaching the "signed" tier. Authorship is knowable because tools/list enumerates: the tool set (birth_certificate, notarize_hash, certify_creation, council_vote ...) is DEUSPROOF-specific and matches no shared platform fingerprint — a provider-built server.
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.