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 Repose MCP server?
Uptime monitoring that doesn't cry wolf: manage monitors, read incidents, record deploys.
How to install Repose
Copy-paste configuration for popular MCP clients.
Authorizationrequiredsecret"Bearer rsk_…" — create a token in Repose under Settings → API tokens. A read token gets the read-only tools; a read-write token (Team plan and up) adds create, update, acknowledge and record_deploy.
{
"mcpServers": {
"repose": {
"url": "https://repose.sh/api/mcp"
}
}
}Related MCP servers
Plan, track, and learn from software projects — three MCP tools for the AI agent lifecycle.
View repository →
LLM Sandbox
Securely run LLM-generated code in isolated containers across 7 languages and 3 backends.

MCP server that uses TypeScript AST to find which tests are affected by a code change
MCP server + Playwright reporter that builds a flakiness knowledge graph from test run history
Remote MCP server that returns sentiment analysis results from SentinelScan API.

VNISH Global Operator
Read-only VNISH firmware metadata, Ninja guidance and input-based mining economics calculations.
