$ loading_
Adds nodes, edges, and semantic retrieval to agent knowledge graphs.
This MCP tool has limited documentation, but it is an open-source project from an official registry source and has been updated within the last year, with no clear high-risk red flags observed. As an MCP server, it inherently executes locally and processes knowledge-graph/vector data, so it should be used in a least-privilege environment with its actual read/write scope verified.
The materials explicitly state that no keys or environment variables are required, and there is no indication that API tokens, account credentials, or other sensitive authentication secrets are needed, so credential exposure and abuse risk appears low.
The materials list no remote host endpoints, and the README does not describe any external API, cloud service, or telemetry destination; based on the available information, there is no clear indication of user data egress.
The system checks confirm that it executes code; as an MCP server, it typically starts a local service process and handles agent requests. This is a normal capability for this type of tool, and the current materials do not show system privileges beyond its stated purpose, but it should still be isolated as a local executable component.
The description says it supports adding nodes, adding edges, and semantic nodes, implying that it processes and may persist knowledge-graph/vector-related data. The materials do not specify storage locations, file read/write scope, or access to other local resources, so its actual data persistence and access boundaries should be checked, but there is no clear over-permission red flag at present.
Positive signals include an official registry source, an auditable open-source repository, and updates within the last year; these factors materially reduce supply-chain risk. However, the README is essentially absent, the license is not declared, and community adoption is low (0 stars), so the available audit context and maturity signals are limited; this supports a caution rating rather than high risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.CSOAI-ORG/vector-knowledge-graph-mcp" MCP server from askskill: Run: claude mcp add 'io-github-csoai-org-vector-knowledge-graph-mcp' -- npx -y vector-knowledge-graph-mcp
Use this MCP tool to write the following into a knowledge graph: 1) User A owns project X; 2) Project X depends on service Y; 3) User A also maintains service Y. Add nodes and edges, and organize them into a queryable relationship structure.
A knowledge graph structure with entity nodes and relationship edges.
Based on the concept of "user growth strategy," retrieve semantically related nodes from the knowledge graph and return the most relevant linked entities with reasons.
A list of semantically similar nodes with relationship explanations.
I already have the nodes "customer feedback," "product defect," and "fix plan." Please add reasonable edges between them and output a graph structure suitable for agent reasoning.
Added relationships between nodes and a graph suitable for reasoning.
Provide persistent graph memory, semantic search, and traversal for AI agents.
Connect AI agents to secure RAG workflows across multiple vector databases.
Search, read, and analyze wiki content with graph and vector tools.
Build a project knowledge graph for code search, traversal, and Q&A.
Give AI agents semantic memory and web search for stronger retrieval and reasoning.
Turn codebases into structural graphs for efficient AI-assisted code exploration.