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 GitHub MCP server?
Connect AI assistants to GitHub - manage repos, issues, PRs, workflows, and git operations.
How to install GitHub
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"omnigit-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/aifity/omnigit-mcp:0.6.0",
"-p",
"127.0.0.1:8085:8085",
"-e",
"GITHUB_OAUTH_CALLBACK_PORT=8085",
"-e",
"GITHUB_PERSONAL_ACCESS_TOKEN={token}"
]
}
}
}Related MCP servers

Control and query Rigol DHO824 oscilloscope for waveform capture and measurements
MCP server for roadmap.sh: roadmaps, best practices, interview questions, projects & progress
Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.
View repository →
Toolars
Local-first dev utilities: hash, base64, JWT, UUID, cron, URL codec. No network or telemetry.
Deterministic pre-trade risk checks for autonomous AI trading agents.

Hosted MCP for Pagent: review Bayesian A/B tests, capture hypotheses, manage websites via OAuth.
View repository →
