MCP server for TrustRAG — trust-verified RAG exposed as tools for Claude Desktop, Cursor, and other MCP clients
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"trustrag-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# trustrag-mcp MCP server for TrustRAG — trust-verified RAG exposed as tools for Claude Desktop, Cursor, and other MCP clients. ## Installation ```bash pip install trustrag-mcp ``` ## Usage ### Claude Desktop Add to `claude_desktop_config.json`: ```json { "mcpServers": { "trustrag": { "command": "uvx", "args": ["trustrag-mcp"], "env": { "TRUSTRAG_BACKEND_URL": "http://localhost:8000" } } } } ``` ### Direct ```bash # Via entry point trustrag-mcp # Via module python -m trustrag_mcp ``` ## Tools | Tool | Description | |------|-------------| | `trustrag_query` | Ask the knowledge base with trust filtering | | `trustrag_upload_document` | Upload a PDF to the knowledge base | | `trustrag_get_audit_log` | Fetch recent query audit entries | ## Configuration Set `TRUSTRAG_BACKEND_URL` environment variable (default: `http://localhost:8000`).
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.