Memory and knowledge · MCP server
MCP agent memory: MCP server, setup and security
MCP agent memory is an open-source MCP server that lets an AI agent read and update persistent memory with automatic background consolidation processes. Its repository has 6 stars and its last commit is from October 23, 2026 and it is licensed under MIT.
| Adoption (stars) | 8/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 15/30 |
What MCP agent memory does
According to its repository: “Filesystem-based persistent agent memory: agents read, write and search memory while a background daemon handles consolidation and extraction.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. MCP agent memory is listed under Memory and knowledge, a category of 250 servers in the directory, where it ranks #225 by stars.
Topics declared by the repository: agent-memory, ai-agents, bedrock, kiro, kiro-cli, kiro-ide.
Installing and connecting MCP agent memory
No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript. Listed systems: macOS.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to MCP agent memory. That does not replace reading the code.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on April 26, 2026, the tverney/mcp-agent-memory repository has 6 stars and 1 forks, with 0 open issues. It has more stars than 17% of the servers in the directory. It received changes this month.
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
MCP agent memory is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Permissive licence (MIT)
Limitations
- Few visible users
- Install from source
Alternatives
- Context763.6K ★
- Basic memory4.3K ★
- Hindsight53.4K ★
- Cognee32.7K ★
- Skill Seekers15.2K ★
- Honcho7.8K ★
Learn more
Frequently asked questions
How do I install MCP agent memory?
No package is declared in the MCP registry: clone the tverney/mcp-agent-memory repository, follow its README, then declare the start command in your client's MCP configuration.
Is MCP agent memory free?
The code is published under the MIT licence and can be used free of charge.
Is MCP agent memory safe?
No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.
Is it an official server?
Nothing says so: it is a project published by tverney on GitHub. Check who maintains it before giving it access.
What are the alternatives to MCP agent memory?
In the same category: Context7, Basic memory, Hindsight, and Cognee. Context7 and Basic memory score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score