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 io.github.wjabanjj/aifp-mcp MCP server?
Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.
How to install io.github.wjabanjj/aifp-mcp
Copy-paste configuration for popular MCP clients.
COGNITION_LLM_API_KEYsecretOptional LLM API key for automatic memory recognition (COGNITION_LLM_API_KEY or ANTHROPIC_API_KEY)
{
"mcpServers": {
"aifp-mcp": {
"command": "npx",
"args": [
"-y",
"aifp-mcp"
],
"env": {
"COGNITION_LLM_API_KEY": "<YOUR_COGNITION_LLM_API_KEY>"
}
}
}
}Related MCP servers

Track which AI agent wrote which lines in a shared Git checkout; each commits only its own lines.

Ontology Atlas
Understand your codebase as AI agents change it—keep ontology as Markdown in your repo.

io.github.woladi/macos-vision-mcp
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.

Desktop Commander
Execute terminal commands, manage files, and control processes with AI—all from Claude Desktop or your favorite MCP client.
Search AI capabilities across AWS Marketplace and the Official MCP Registry.

io.github.wjgoarxiv/vmd-hydrate-mcp
Drive VMD for GROMACS/LAMMPS analysis + clathrate-hydrate cage science (needs a local VMD)