What it does
This MCP server provides a vector-based knowledge graph that an agent can write to and query. Its documented tools are add_node, add_edge and semantic_node_search, which add nodes, connect them with edges and search nodes by meaning.
It is intended for AI agents that need to record connected information and look it up later. The publisher describes it as an AI-powered knowledge graph server for agents.
It is available on PyPI and runs as a command over stdio transport. It is added to the configuration of an MCP client such as Claude Desktop, after which the assistant can be asked to use the tools by name.
Limitations and requirements
Requires an MCP client, such as Claude Desktop, to be configured to launch the server over stdio.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSOAI-ORG/vector-knowledge-graph-mcp
AI-powered vector knowledge graph MCP server for agents. Supports add node, add edge, semantic node
v1.0.10As shown on registry.modelcontextprotocol.io when we last read it