$ loading_
Enable context-aware memory retrieval with authority weighting and conflict detection.
The materials describe an open-source, local memory MCP server with no declared secrets or remote endpoints, and no clear high-risk red flags are evident. The main concerns are its inherent local execution capability as an MCP service and the limited documentation, adoption, and maintenance signals, so least-privilege testing is recommended.
The material explicitly states that no keys or environment variables are required, and no API keys, OAuth tokens, or other sensitive credentials are mentioned; based on the available information, credential exposure or abuse risk appears low.
The material explicitly states there are no remote endpoint hosts, and the description does not claim any external service connectivity or third-party data transfer; based on the stated facts, no network egress path is evident.
The objective checks include executes-code, indicating it has the normal capability of running code/processes locally as an MCP tool. This is inherent to this class of tool, and no evidence is provided of system permissions exceeding its stated purpose, but it should still be isolated as a local execution component.
Its function is described as a 'memory MCP server' for 'intelligent memory retrieval', so some local memory/persistence read-write behavior is reasonably expected; however, the material does not specify file paths, database locations, or access boundaries. There is no clear evidence of overbroad access, but the data scope is insufficiently documented.
Positive signals include being open source under the MIT License, which allows source review, and a linked GitHub repository from a third-party registry. However, adoption is shown as 0 stars, maintenance status is unknown, and the README is absent, which weakens maturity and verifiability signals; this warrants caution at the supply-chain level but not a high-risk rating by itself.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-memory-graph" yet — see the docs or source repo.
Store the following user preferences, project background, and past decisions in the memory graph, then retrieve the most relevant memories in future conversations based on context. If conflicting information appears, flag the conflict and rank items by source authority.
Structured memory write results, plus future retrievals ranked by relevance and source authority.
Ingest facts from meeting notes, user feedback, and product documents into the memory system, detect contradictions, preserve typed relationships, and output the most trustworthy current conclusion plus a conflict list.
A fact graph with typed edges, conflict detection results, and recommended conclusions filtered by authority weighting.
Connect a memory graph to my AI agent so it automatically retrieves memories related to the current goal, people, and past actions before task execution, then returns a context summary ready for reasoning.
A task-focused context summary including relevant entities, relationships, history, and priority notes.
Persistent knowledge-graph memory for MCP with semantic search and version tracking.
Provides persistent graph memory for LLMs with auto-linking and layered recall.
Provide persistent graph memory, semantic search, and traversal for AI agents.
Give AI knowledge-graph memory with cloud persistence and semantic search.
Build a project knowledge graph for code search, traversal, and Q&A.
Provide shared cross-session memory storage, retrieval, and governance for MCP AI tools.