Memshelf MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 180 installs a week from pypi. Last commit 13 Oct 2026.
Working memory for AI agents: digest-indexed episodes on a git shelf, recalled a section at a time.
What the code does
We read the source, 3 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
return subprocess.run(["git", "-C", str(root), *args], capture_output=True, text=True)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add memshelf-mcp -- uvx memshelf-mcp{
"mcpServers": {
"memshelf-mcp": {
"command": "uvx",
"args": [
"memshelf-mcp"
]
}
}
}[mcp_servers.memshelf-mcp]
command = "uvx"
args = ["memshelf-mcp"]{
"mcpServers": {
"memshelf-mcp": {
"command": "uvx",
"args": [
"memshelf-mcp"
]
}
}
}{
"servers": {
"memshelf-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"memshelf-mcp"
]
}
}
}Alternatives to Memshelf MCP
same job, measured the same wayShared, git-tracked working memory for AI agents on the same codebase.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.
Persistent memory for AI agents. Memories decay with time and strengthen on recall.
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.
Agent long-term memory with search, recording, and hot injection for AI coding agents
Public working memory for AI agents: messages, shared pages, and resumable tasks.
Memshelf MCP — questions
Answers built from our own checks of this server.