$ loading_
Store and recall cross-conversation details with persistent knowledge-graph-based memory.
This Memory MCP tool appears to be an official open-source project with very strong community adoption, and it does not declare any required secrets or remote endpoints, so the overall risk is low. The main considerations are that it executes locally as an MCP tool and that its persistent-memory feature implies storage of conversation-related data.
The materials explicitly state that no keys or environment variables are required. No API keys, tokens, or other sensitive credentials are mentioned, so there is no evident credential exposure or abuse risk from the available information.
The materials state that there are no remote endpoint hosts, and they do not describe any cloud sync, external API usage, or telemetry. Based on the available facts, there is no indication that user data is sent to remote services.
The system checks include 'executes-code', indicating that this MCP service runs code/processes locally. This is a normal capability for this kind of tool; the current materials do not show requests for unusual system privileges, but it should still be deployed with least privilege as a local executable component.
The description says it provides 'knowledge-graph-based persistent memory across conversations', which reasonably implies storing and retrieving conversation-related memory data. The materials do not specify storage location, data scope, or access to other local files, so there is no clear evidence of overbroad access, but it should be assumed to have at least local read/write access to its own memory store.
The source is platform-curated and points to an open-source implementation under the official modelcontextprotocol repository. It also has very strong community adoption (86.7k stars) and auditable source code. These are strong risk-reducing factors. The license and maintenance status are not clearly stated, which is an information gap, but not enough on its own to raise this to high risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Memory" MCP server from askskill: Run: claude mcp add 'memory' -- npx -y @modelcontextprotocol/server-memory
Fetch web pages and convert them to Markdown for AI reading and analysis.
Demonstrate MCP tools, resources, and prompts for comprehensive protocol capability testing.
Check current time and convert time zones for cross-region coordination and scheduling.
Let AI read, search, and manage local Git repositories and commit history.
Helps AI break down complex problems step by step and reflect on its reasoning.
Securely read and write local files, manage directories, and quickly search needed content.
Persist long-term AI memory with semantic retrieval and knowledge graph context.
Provides local persistent memory for coding agents with low-cost context retrieval.
Give your AI cross-tool memory with reliable context recall and uncertainty awareness.
Provide persistent memory for AI agents across sessions and tasks.
Give AI agents persistent memory and semantic recall across platforms and workflows.
Give AI agents persistent memory across sessions with automatic context retrieval.