Claude
- Open runners.io in the Claude directory ↗
- Click Connect
- Sign in to your account

Cloud, data & infrastructure·Live in ![]()
Runners.io runs GitHub Actions jobs on managed runners.
This connector lets your AI read your organisation's CI data as you, so you can ask why a build failed without pasting a log into the chat.
What your AI can do:
Diagnose a failed job in one call: the verdict, the failing steps and tests, memory use, and the log around the last errors.
List recent jobs, filtered by repository, branch, runner label or status.
Read part of a job's log (the tail, a line range, or the lines around a phrase) and the failing tests from its test reports.
Show this month's metered minutes and spend per runner size.
Check Actions cache hit rates and entries, per repository.
List your repositories, the runner sizes and their prices, and search the runners.io docs.
Turn your workflow files into a patch that moves their jobs onto runners.io. It changes nothing: you apply the patch yourself.
Built to be safe:
Sign-in uses OAuth. Each connection covers one organisation and sees only what your role sees in the dashboard.
14 of the 16 tools only read. The two that change anything, cancelling a job and deleting a cache entry, are off by default: they need an owner or admin to approve write access, the organisation to switch them on, and a confirmation on every call.
Text that comes from repositories, such as logs, commit messages and branch names, is marked untrusted, so your AI treats it as data and never as instructions.
Requires a runners.io account with GitHub connected. Setup guide: https://www.runners.io/docs/observability/mcp-server
https://mcp.runners.io/mcphttps://mcp.runners.io/mcpmcp.runners.ioget_cache_statsget_docget_jobget_job_logsget_job_testsget_spendlist_cache_entrieslist_jobslist_repositorieslist_runner_tierssearch_docswhoamidiagnose_jobplan_migrationcancel_jobdelete_cache_entryNot found; the server needs sign-in so there may be skills that our scan couldn't access
Runners. io runs GitHub Actions jobs on managed runners. This connector lets your AI read your organisation's CI data as you, so you can ask why a build failed without pasting a log into the chat. It is listed under Cloud, data & infrastructure.
Open its listing in the app's connector directory and connect. Sign in to your account in the browser window that opens. It uses OAuth, so the AI never sees your password. Step-by-step setup for each app is on this page.
The runners.io MCP server URL is https://mcp.runners.io/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.
Yes. runners.io is published or run by runners.io, so it is the official MCP server. See other official connectors.
It is listed in 1 store: Claude. Apps where it is not listed can usually still add it as a custom connector.
It is ranked 11,611 of 11,897 in the Claude directory. A rank is the store's own order, not a usage count. How we track ranks.
It has 16 tools: 12 read data, 2 change data and 2 can delete or overwrite data. See every tool and its inputs.
Yes. 2 tools can change data and 2 tools can delete or overwrite it. Most AI apps ask before they run these. The store marks these as destructive:
None that we found. Not found; the server needs sign-in so there may be skills that our scan couldn't access.
No. Its answers come back as text in the chat. Connectors with interactive UI.
This page updates every day. To ask about runners.io from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.