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 CGIS Code Graph MCP server?
Code graph for AI agents: impact analysis and call tracing for Python and TypeScript.
How to install CGIS Code Graph
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": {
"codegraph-brain": {
"command": "uvx",
"args": [
"codegraph-brain"
]
}
}
}Related MCP servers
PE

p-e relay
Active
Read-only access to an append-only corpus of provenance-bearing coordination records.
0
View repository →TypeScript
MIT
CO

Code Relay
Active
Branch-scoped runbooks, remote checkpoints, and auditable verification receipts.
0
View repository →Go
MIT
IO

io.github.zazencodes/random-number-mcp
Maintained
Pseudorandom and cryptographically secure random number generation utilities for AI agents.
50
View repository →Python
MIT
LO

Local GPU Imagegen
Active
MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads.
1
View repository →Python
MIT

