Other · Local MCP server
Context Keeper
Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.jarmstrong158/context-keeper- Version
- 0.19.0
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-08-06
- Updated
- 2026-08-06
- Publisher
- jarmstrong158 (GitHub) · 8 servers with pages here
- Repository
- github.com/jarmstrong158/context-keeper
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | context-keeper-mcp | 0.19.0 | stdio |
How to connect Context Keeper
Context Keeper runs locally from a Python package published to PyPI: context-keeper-mcp version 0.19.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx context-keeper-mcp. It reads the environment variable CONTEXT_KEEPER_PROJECT; set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"context-keeper": {
"command": "uvx",
"args": [
"context-keeper-mcp"
],
"env": {
"CONTEXT_KEEPER_PROJECT": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from jarmstrong158 (GitHub)
| Server | Runs |
|---|---|
| agentsyncMulti-agent coordination MCP: claim work, survey peers, resolve conflicts via a git branch as CAS. | Local · stdio |
| agentsync (remote)Cloudflare Worker remote transport for agentsync. MCP 2026-07-28, dual-era, stateless. | Remote · HTTP |
| CambiumKnowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org. | Local · stdio |
| cambium (remote)Cloudflare Worker for read-only recall of cambium knowledge. MCP 2026-07-28, dual-era. | Remote · HTTP |
| ConductorLocal task scheduler and worker manager with MCP integration for Claude Desktop. | Local · stdio |
| Context Keeper (remote)Cloudflare Worker remote backend for context-keeper (D1). MCP 2026-07-28, dual-era. | Remote · HTTP |
| Skillmatch MCPJob search and ranking pipeline via MCP for Claude Desktop. | Local · stdio |
More other servers
| Server | Runs |
|---|---|
| ContexelShared AI memory. ChatGPT, Claude, Cursor and any MCP app read and write the same memory. | Remote · HTTP |
| ContextLocal-first documentation for AI agents. Offline, instant, private doc retrieval. | Local · stdio |
| Context BookStop re-explaining yourself to Agents. Give it the right context, right when needed. | Remote · HTTP |
| Context FabricContext sync layer for AI agents. Ensures continuity and eliminates memory drift automatically. | Local · stdio |
| Context MemPersistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools. | Local · stdio |
| Context PodPersistent context for AI agents built fromlearned vectors with certainty scores. | Remote · SSE |
| Context ProxyMCP proxy that lazy-loads tool schemas to cut context token overhead by 6-7x. | Local · stdio |