$ loading_
Build a local cognitive graph linking people, projects, and decisions.
Based on the available materials, NeuroDock Cognitive Graph appears to be a locally running graph-memory MCP tool with no declared secrets or remote endpoints, so overall risk is relatively low. The main cautions are its local code-execution capability and limited audit visibility due to missing README/license details.
The materials explicitly state that no keys or environment variables are required, and no API tokens, account credentials, or third-party authorizations are mentioned, so credential exposure and abuse risk appears low.
No remote endpoints or external hosts are declared; based on the description, it functions as a local graph-based memory tool, with no factual indication that user data is sent to external services.
The system checks explicitly mark this tool as executes-code, indicating standard MCP capability to start local processes or execute code on the host. This warrants least-privilege operation, but by itself does not justify a high-risk rating.
The description says it 'externalises memory,' so it is reasonable to infer that it stores or reads local graph data related to people, projects, and decisions. However, the materials do not specify file paths, storage scope, or whether other resources are modified, so local data boundaries should be reviewed.
Positive signals include an official registry source, an auditable open-source repository, and updates within the last year, all of which materially reduce risk. Cautions remain because the README is absent, the license is undeclared, and community adoption is very low (0 stars), reducing transparency and maturity; this supports a caution rather than risk rating.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "NeuroDock Cognitive Graph" MCP server from askskill: Run: claude mcp add 'io-github-tlennon-ie-neurodock-mcp-cognitive-graph' -- uvx neurodock-mcp-cognitive-graph
Please convert the following meeting notes into cognitive graph nodes and relations, including people, projects, decisions, dates, and rationale, and show who made which decision in which project: Project Apollo, March 12, Li Min proposed a two-week delay to complete the security audit, and Wang Zhe approved it.
A structured graph record showing the project, people involved, decision details, timing, and causal links.
Query the cognitive graph for the projects Li Min participated in, the key decisions Li Min proposed, and the outcomes of those decisions, then summarize them in chronological order.
A chronological participation summary with projects, decision records, and outcome overviews.
Design a continuously updatable memory graph for the team using the following materials: member list, active projects, decisions made, dependencies, and owners, and recommend suitable node types and edge types.
A maintainable graph model with node and edge design plus a clear structure for capturing information.
Connect a local GraphRAG knowledge base for private offline document retrieval.
Build and explore a neuroscience-inspired knowledge graph for search and reasoning.
Build graph-based memory and semantic search for LLM applications.
Give AI agents semantic memory with hybrid search and knowledge graph support.
Connect a Neo4j knowledge graph to AI assistants for search and read-only queries.
Give AI agents long-term memory, knowledge graphs, recall, and health insights.