Context Keeper runs on your own machine — the client starts it, so there is no endpoint to ping. 249 installs a week from pypi. Last commit 6 Aug 2026.
Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.
We read the source, 22 h ago · rules 3dff92dd89df
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.
p = subprocess.run(
abs_scope = os.path.join(root, scope_norm.replace("/", os.sep))
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 context-keeper -- uvx context-keeper-mcp
{
"mcpServers": {
"context-keeper": {
"args": [
"context-keeper-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.context-keeper]
command = "uvx"
args = ["context-keeper-mcp"]
{
"mcpServers": {
"context-keeper": {
"args": [
"context-keeper-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"context-keeper": {
"args": [
"context-keeper-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
CONTEXT_KEEPER_PROJECT (Absolute path to the project directory. If omitted, uses cwd only when it already contains a .context/ directory; otherwise tools require explicit project_dir.).
The author declared them in the registry entry; get the values from the project itself.
Project memory across sessions for AI agents. A queryable decision log in the repo.
Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.
Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.
Persistent memory + decision tracking for Claude across sessions. Local SQLite, no cloud.
One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.
Memory for coding conventions and standing instructions that persists across sessions.
Share context, detect conflicts, and message across parallel Claude Code sessions
An MCP server that provides persistent memory and context management across sessions
Answers built from our own checks of this server.