$ loading_
Expose a read-only provenance-backed fact graph for AI agents to search and verify.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "provgraf-mcp" yet — see the docs or source repo.
Search provgraf-mcp for verified facts related to “Project Alpha release date” and return the fact content with its provenance.
A list of matching facts with sources, relationships, or provenance details for verification.
Please verify whether this claim is supported in provgraf-mcp: “Version 2.1 was released by Team B.” If found, show the related provenance.
A confirmation of whether the claim exists in the graph, along with the associated provenance.
List available facts in provgraf-mcp related to the topic “vendor contracts,” organized by relevance.
A relevant fact list that helps quickly review verified information on the topic.
Researchers or analysts can use this tool to search verified facts and inspect their provenance before asking an AI to answer factual questions, reducing unsupported responses. Because the server is read-only, queries do not modify the data.
Developers can connect it to AI agent workflows so agents can list, search, and check facts instead of writing directly to the knowledge base. Writes are restricted to the CLI, helping keep data update boundaries clear.
When a team needs to confirm whether a statement is backed by a source, they can use this tool to inspect the fact and its provenance. It fits scenarios where tracing fact origin and relationships matters.
It is a read-only MCP server that exposes a W3C PROV knowledge graph of facts. AI agents can use it to list, search, and check verified facts with provenance.
No. The description explicitly says it is read-only, and writes remain limited to the CLI.
It exposes a W3C PROV knowledge graph for representing facts and their provenance. For more implementation details, see the source repository.
Lets AI agents inspect fact-check scope, evidence gaps, and review requirements.
Build auditable knowledge-graph reasoning for reproducible, contradiction-aware AI answers.
Query codebase knowledge graphs directly for faster, lower-token code understanding.
Provides an MCP server for RAG and knowledge graph integration.
Turn facts into formal proofs with deterministic Prolog-based logical reasoning.
Assess invoices before payment with risk decisions, confidence scores, and verification.