DevOps for AI
Provides tools for working with GitHub repositories: reading files and repository trees, making safe multi-file commits and targeted edits, rolling back commits, inspecting commit history and branch comparisons, checking CI workflow status/logs/artifacts, managing releases, and calling arbitrary GitHub REST endpoints.
Provides tools for managing Railway projects and services: inspecting projects, deployments, logs and service status, viewing and setting variables, redeploying or restarting services, running raw GraphQL queries, and performing confirmed deletions of services or projects.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
DevOps for AI
A personal MCP server that lets an AI assistant (Claude) work with your GitHub and Railway accounts: read code, make safe multi-file commits, check CI, roll back, deploy and verify.
This is a personal project. I built it for my own workflow and I'm sharing it as-is. It is not a product, it is not audited, and it is not affiliated with or endorsed by Anthropic, OpenAI, GitHub or Railway. Self-host it, read the code, and use it at your own risk.
It is one small FastAPI app that is both a website (sign in, add accounts, create connector links) and an MCP server (Streamable HTTP). You paste a connector link into Claude (Settings, Connectors, Add custom connector) and the assistant gets ~55 tools.
What it does
Multiple accounts. Any number of GitHub and Railway accounts, each with a label. The assistant picks one with an
accountargument; calls to different accounts run in parallel.Per-link permissions. Every connector link has its own rights per account: none / read-only / read-write. Links can be revoked, edited and deleted.
Per-link tool sets. Each link also chooses which groups of tools the assistant can even see (GitHub read, GitHub write, Actions, Railway read/write, advanced, deletions, checks). Fewer tools means fewer tokens and fewer wrong tool choices. Hidden tools are also blocked at call time.
Safe file operations (Git Data API, one commit for any number of files, fast-forward only, never force):
batch_commit(text and binary files, deletions,dry_runshows diffs without writing)apply_edits(targeted old-to-new edits; any conflict means nothing is written; optionalexpected_shacheck)rollback_commit(reverts a commit with a new commit; refuses if files changed afterwards)upload_binary,batch_read_files,repository_tree,download_repository,compare_branches,commit_history_diff
CI and releases.
workflow_status(failed jobs plus log tail in one call), runs, jobs, logs, artifacts, releases,release_from_artifact(build artifact to a release with a permanent link, done server-side).Railway. Projects, deployments, logs, variables (names only by default), set variable, redeploy, restart,
railway_service_status, raw GraphQL.Post-deploy checks.
run_post_deploy_testscalls your site or API from the server (status, body text, JSON fields, latency). Private and internal addresses are blocked (SSRF protection).Confirmed deletions. Deleting a Railway service or project, or a GitHub branch, is a two-step operation: the first call returns a plan and a one-time code, the second call with the code executes it.
Tool annotations (
readOnlyHint,destructiveHint,openWorldHint) on every tool.A generic
github_apitool covers any other GitHub REST endpoint.
Related MCP server: Railway MCP Server
How it works
Claude --MCP over HTTPS--> /c/<secret>/mcp (this app) --> GitHub API / Railway GraphQL
|
+-- website: Google sign-in, accounts, links, permissionsAccount tokens are stored encrypted (Fernet) in Postgres. Connector links are stored only as a SHA-256 hash, so a link is shown once.
Core is
app.py. Extra tool modules (gitx.py,ops.py,safe.py,profiles.py) are loaded bymain.pyone by one; if one fails to import, the rest of the connector still works.
Quick start (Railway)
Fork or clone this repo and deploy it on Railway (Deploy from GitHub repo). The
Procfilerunsuvicorn main:application.Add a PostgreSQL database and reference its
DATABASE_URLin the app service.Generate a public domain and set
BASE_URLto it (no trailing slash).Create a Google OAuth client (redirect URI
https://YOUR_DOMAIN/auth/google/callback) and a GitHub OAuth app (callbackhttps://YOUR_DOMAIN/auth/github/callback).Set the environment variables below, open the site, sign in, add accounts, create a link, and paste it into Claude.
Variable | Meaning |
|
|
| long random string (session signing) |
| Fernet key: |
| Postgres URL |
| Google OAuth client |
| GitHub OAuth app |
| optional, comma-separated emails allowed to sign in. Set this unless you want anyone to be able to register |
GitHub accounts can be added through OAuth or with a personal access token (scope repo). Railway needs an account or workspace token (Account Settings, Tokens). The mcp package is pinned below version 2 on purpose.
Security model (read this)
A connector link is a credential. Anyone who has it can use the accounts and rights you enabled for it. Do not share it; revoke it if it leaks.
This app holds your GitHub and Railway tokens. Host it yourself, restrict sign-in with
ALLOWED_EMAILS, and prefer tokens with minimal scopes.Permissions are enforced on the server per link and per account; read-only links cannot write even if a tool is called by name.
There is no OAuth for the MCP connection itself (the secret link is the auth). That is fine for a personal tool, and it is why this is not suitable for a public connector directory as-is.
github_apiandrailway_graphqlcan do anything the underlying token allows; hide the "advanced" group on links where that is too much.Confirmation codes protect against accidental one-shot deletions, not against a malicious client that chains both calls.
Status and limitations
Used daily by the author on a few accounts. Core read and write tools, multi-account, per-link permissions, tool sets, batch commits, edits and rollback were exercised against the real GitHub API.
Release/artifact tools, post-deploy checks and the deletion tools are covered by tests against mocked services; they have had less real-world use, so expect rough edges.
No automated test suite is included in this repo yet.
Large binaries (APK/ZIP) are never passed through the chat: the server hands out temporary or permanent links instead.
Issues and pull requests are welcome, but this is a hobby project, so replies may be slow.
License
MIT, see LICENSE.
Русский
DevOps для ИИ: личный MCP-сервер, через который Claude работает с твоими GitHub и Railway. Читает код, делает безопасные коммиты сразу многих файлов, смотрит сборки и логи, откатывает изменения, проверяет сайт после деплоя.
Это личный проект. Я сделал его для себя и выкладываю как есть: без аудита и без гарантий, к Anthropic, OpenAI, GitHub и Railway он отношения не имеет. Разворачивай у себя, читай код и пользуйся на свой риск.
Что умеет
Любое число аккаунтов GitHub и Railway, у каждого своя метка.
Права у каждой ссылки свои: по каждому аккаунту нет доступа, только чтение или чтение и запись. А ещё для каждой ссылки выбирается набор инструментов, которые видит Claude (меньше инструментов: меньше токенов и путаницы).
Массовые коммиты одним запросом, точечные правки с проверкой конфликтов (при конфликте не пишется ничего), предпросмотр изменений, безопасный откат новым коммитом.
Статус сборок и логи упавших джобов одним вызовом, релизы из артефактов сборки, состояние сервисов Railway, проверка сайта после деплоя.
Удаление сервисов, проектов и веток только в два шага: сначала план и одноразовый код, потом выполнение.
Запуск: разверни на Railway (подключи Postgres, задай переменные из таблицы выше, создай OAuth-приложения Google и GitHub), войди на сайт, добавь аккаунты, создай ссылку и вставь её в Claude (Settings, Connectors, Add custom connector).
Безопасность: ссылка коннектора это пароль, никому её не давай. Токены аккаунтов хранятся зашифрованными, ссылки только в виде хеша. Обязательно задай ALLOWED_EMAILS, иначе зарегистрироваться сможет любой.
Статус: хобби-проект. Основное проверено на реальном GitHub; релизы, проверки после деплоя и удаления проверены только на имитации, возможны шероховатости.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Operate GitHub from your AI assistant: repos, PRs, issues, Actions. Previews and read-only mode.
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Deploy apps from GitHub, read build/runtime logs, and manage your app's users from your AI agent.
Put AI-built apps online from GitHub: deploy, check status, read logs and set env vars.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables management of Railway.app infrastructure through natural language, including deploying services from GitHub repos or Docker images, managing environment variables, monitoring deployments, and configuring networking and volumes.36MIT
- AlicenseAqualityDmaintenanceEnables management of Railway.app infrastructure through natural language, including deploying services, managing environment variables, monitoring deployments, and handling databases and volumes.36MIT
- AlicenseAqualityDmaintenanceConnects AI assistants to GitHub repositories, pull requests, issues, commits, and code search while enabling repository visibility controls, CI/CD monitoring, sandboxed local filesystem access, and code quality/security analysis.131MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to run structured preflight checks and identity-scoped Git operations, committing, pushing and opening GitHub PRs with the correct Git name, email, SSH key and signature for each repository. Persistent changes require exact proposals, human approval by default and recoverable, idempotent apply.77 PyPIMIT