How to choose
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the memgit MCP server?
Git for AI memory — version-controlled, searchable context that persists across sessions
How to install memgit
Copy-paste configuration for popular MCP clients.
transport: stdio
Config generated by PluginBench — verify against the source before use.~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
"mcpServers": {
"memgit": {
"command": "npx",
"args": [
"-y",
"memgit-mcp"
]
}
}
}Related MCP servers
ME

MemoFS MCP Server
Active
Persistent memory and virtual filesystem MCP server for AI agents.
5
View repository →TypeScript
MIT
ME

MetaMesh-UGA
Active
Serverless edge control plane to discover, route and monetize 14,982+ MCP tools.
0
View repository →JavaScript
Run App Store Connect from your IDE: pricing, listings, screenshots, releases, AI visibility.
MI

minitok
Active
Verified coding workflows with planning, verification, bounded retries, evidence, and evolution.
1
View repository →JavaScript
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
ME
Scrape, crawl and search the web for AI agents via MCP.