Mergify MCP server for AI agents
Let Claude, ChatGPT or your own agent read Mergify: 2 typed functions through one MCP server. No Mergify API key needed.
- Site
- mergify.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Mergify
An MCP server for Mergify alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/mergifyEvery site
One MCP server for Mergify and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
queueStatusThe live state of a repo's Mergify merge queue.Arguments
Name Type Required args{ owner: string; repo: string }Yes Returns
mergifyQueueStatusinterface mergifyBatch { id: string; name: string; statusCode: string; batchFilledSlots: number | null; maxBatchSlots: number | null; retries: number; maxRetries: number; startedAt: string | null; estimatedMergeAt: string | null; estimatedCiFinishAt: string | null; ciFinishedAt: string | null; queueRuleName: string; checksPassed: number; checksTotal: number; pullRequestNumbers: number[]; } interface mergifyQueuedPull { number: number; title: string; url: string; author: string | null; queuedAt: string; priorityRuleName: string | null; estimatedMergeAt: string | null; } interface mergifyQueueStatus { batches: mergifyBatch[]; waitingPullRequests: mergifyQueuedPull[]; paused: boolean; pauseReason: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mergify/queueStatusCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mergify.queueStatus({ owner: "Mergifyio", repo: "mergify-engine" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mergify.queueStatus({"owner": "Mergifyio", "repo": "mergify-engine"}))curl -X POST https://api.bowmark.ai/v1/sites/mergify/queueStatus \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"owner":"Mergifyio","repo":"mergify-engine"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mergify.queueStatus({ owner: "Mergifyio", repo: "mergify-engine" });validateConfigValidate a Mergify configuration file (.mergify.yml) before pushing it.Arguments
Name Type Required args{ yaml: string }Yes Returns
mergifyConfigValidationinterface mergifyConfigError { path: string; message: string; keyword: string; } type mergifyConfigValidation = | { valid: true } | { valid: false; errors: mergifyConfigError[] };HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mergify/validateConfigCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mergify.validateConfig({ yaml: "queue_rules:\n - name: default\n" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mergify.validateConfig({"yaml": "queue_rules:\n - name: default\n"}))curl -X POST https://api.bowmark.ai/v1/sites/mergify/validateConfig \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"yaml":"queue_rules:\n - name: default\n"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mergify.validateConfig({ yaml: "queue_rules:\n - name: default\n" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/mergify/<function> - OpenAPI
/v1/sites/mergify/openapi.json