ghcli-mcp-connector
ghcli-mcp-connector is an MCP server that lets agents run any GitHub CLI (gh) commandβrepos, issues, PRs, releases, workflows, gists, and moreβas a single static Go binary with a read-only-by-default safety gate on state-changing operations.
README
<div align="center">
π ghcli-mcp-connector
Talk to the GitHub CLI (gh) from an MCP-speaking agent.
</div>
A single static Go binary that speaks the Model Context Protocol
and lets an agent run GitHub CLI commands: any gh <command> <subcommand>
invocation β repo, issue, pr, release, gist, workflow, run,
secret, variable, project, ruleset, codespace, extension, api,
and more β with a read-only-by-default safety gate on anything that
changes state on GitHub.
No Python, no uv, no runtime dependency to install β just a binary and
an .mcp.json. It shells out to the gh binary already installed and
authenticated on the host (gh auth login, stored in the OS keychain, or
GH_TOKEN/GITHUB_TOKEN) instead of reimplementing a GitHub API client,
so it gets the full breadth of the CLI for free rather than a hand-curated
subset of endpoints.
Note: this is a sibling of github-mcp-connector, not a replacement. That one talks to the GitHub REST API directly via
google/go-githubwith a curated set of 18 tools. This one shells out to theghCLI itself β same trade-off asaws-mcp-connectorvs. a hand-written AWS SDK client: broader coverage (gh extensions, gh's own filters/formatting, workflow/run/codespace/project/ruleset management) through a singleghcli_execescape hatch, instead of a curated surface.
β¨ Why this exists
An agent that only has a narrow, hand-picked set of GitHub tools hits a wall the moment you need something outside that set. This connector instead wraps the
ghCLI itself, so an agent can rungh pr list,gh issue create,gh workflow run,gh api repos/owner/repo/issuesβ anything the CLI can do β without waiting on a new tool to be written for it. State-changing commands are blocked by default and require both a server-level opt-in and a per-callconfirm=true, so exploring/ reading is safe out of the box.
π§° Tools
| Tool | What it does | Write? |
|---|---|---|
ghcli_exec |
Run any gh <command> <subcommand> ... command. Read-only by default β commands that change GitHub state need GHCLI_MCP_ALLOW_WRITE=true on the server and confirm=true on the call. |
β (gated) |
ghcli_help |
Show gh <command> [subcommand] --help text β always safe, use it to check exact syntax before calling ghcli_exec. |
|
ghcli_whoami |
Show the GitHub identity (login, name, profile URL) the configured auth resolves to. |
Every tool accepts an optional response_format: markdown (default,
readable for a chat UI) or json (for programmatic use).
This server has no working-directory git repo, so repo-scoped commands
need an explicit -R/--repo owner/repo rather than relying on gh's
cwd-based repo detection.
π Quickstart
Fastest path: grab a prebuilt bundle from the latest release β
download ghcli-mcp-connector-plugin-<version>-<os>-<arch>.zip, unzip it,
and point Cowork/Claude at the plugin/ folder inside (see step 4 of
SETUP.md). No Go toolchain required.
From source:
# 1. Build
cd go-server
go mod tidy
go build -o ghcli-connector-server .
cp ghcli-connector-server ../plugin/servers/go/
# 2. Set up auth β needs the gh CLI itself installed and logged in
# (gh auth login) β see SETUP.md
gh auth status # should succeed before running the server
# 3. Run
./go-server/ghcli-connector-server # serves MCP over stdio
Or make build β see the Makefile for every shortcut
(test, vet, fmt, lint, tidy).
Full walkthrough β including wiring this up as a Claude/Cowork plugin β is in SETUP.md.
π Configuration
Everything is environment variables, passed through by the plugin's
.mcp.json:
| Variable | Purpose | Default |
|---|---|---|
GH_TOKEN / GITHUB_TOKEN |
gh CLI's own token env vars. Leave unset to use whatever gh auth login already configured. |
unset (keychain auth) |
GH_HOST |
Target a GitHub Enterprise hostname instead of github.com. | unset (github.com) |
GHCLI_MCP_ALLOW_WRITE |
"true" to permit state-changing commands at all (still needs confirm=true per call). |
false (read-only) |
GHCLI_MCP_ALLOWED_REPOS |
Comma-separated allowlist of owner/repo values, e.g. "me/proj,me/other". Only enforced when a call passes an explicit -R/--repo flag. |
unset (unrestricted) |
GHCLI_MCP_CLI_PATH |
Path to the gh binary. |
gh resolved via PATH |
π§ͺ Quality bar
This isn't a toy script β it's got the same checks you'd expect from a production Go service:
- β
Unit tests for every input-validation path (
go test ./...) - β
go vet+gofmtclean - β golangci-lint (govet, staticcheck, errcheck, gosec, and more)
- β govulncheck β no known vulnerabilities in the dependency graph
- β CodeQL static security analysis on every push
- β End-to-end verified against real GitHub during development β not mocks
- β Dependabot keeps Go modules and Actions current
All of it runs in CI on every push and PR.
π·οΈ Releases & versioning
Versions follow semver and are cut automatically by
release-please from
Conventional Commits on main:
fix: ...β patch (v0.1.0βv0.1.1)feat: ...β minor (v0.1.1βv0.2.0)feat!: .../BREAKING CHANGE:footer β major (v0.2.0βv1.0.0)
Every merged PR updates a standing "chore(main): release vX.Y.Z" PR with an auto-generated CHANGELOG.md. Merging that PR:
- tags the release and publishes it on GitHub
- builds and attaches zipped, ready-to-install plugin bundles for linux/darwin/windows Γ amd64/arm64
- regenerates
server.jsonfrom those exact assets (fresh version + SHA-256 hashes) and publishes it to the official MCP Registry viamcp-publisher, authenticated with GitHub OIDC β no stored secrets
See .github/workflows/release-please.yml
and .github/workflows/publish-mcp-registry.yml
(also runnable by hand for an existing tag via workflow_dispatch).
π Layout
ghcli-mcp-connector/
βββ README.md β you are here
βββ SETUP.md β step-by-step setup guide
βββ CONTRIBUTING.md β how to contribute
βββ CODE_OF_CONDUCT.md
βββ SECURITY.md β vulnerability reporting
βββ CODEOWNERS
βββ LICENSE β MIT
βββ Makefile β build / test / lint shortcuts
βββ .golangci.yml β lint rules
βββ release-please-config.json β semver/changelog automation config
βββ .release-please-manifest.json
βββ server.json β MCP Registry manifest (regenerated fresh per release by CI)
βββ scripts/
β βββ render-server-json.sh β rebuilds server.json from a release's zip assets
βββ .github/
β βββ workflows/
β β βββ ci.yml β build, vet, test, lint, govulncheck
β β βββ codeql.yml β security scanning
β β βββ pr-title.yml β Conventional Commits PR title check
β β βββ release-please.yml β version PRs, tagging, GitHub releases
β β βββ publish-mcp-registry.yml β publishes server.json to the MCP Registry
β β βββ rebuild-release-assets.yml β manual re-attach fallback
β βββ ISSUE_TEMPLATE/
β βββ PULL_REQUEST_TEMPLATE.md
β βββ dependabot.yml
βββ go-server/ β the MCP server source
β βββ main.go
β βββ main_test.go
β βββ go.mod / go.sum
β βββ README.md
βββ plugin/ β installable Cowork/Claude plugin
βββ .claude-plugin/plugin.json
βββ .mcp.json β holds credentials locally β never commit real ones
βββ skills/ghcli-mcp/SKILL.md β teaches Claude when/how to use the tools
βββ servers/go/ β compiled binary goes here
π€ Contributing
PRs and issues are very welcome β see CONTRIBUTING.md for the full guide (setup, coding conventions, how to add a new tool) and the Code of Conduct.
main is protected: every change, including the maintainer's, lands via
pull request with CI green. PR titles must follow
Conventional Commits β that's what
drives the automatic versioning above.
Found a security issue? Please follow SECURITY.md instead of opening a public issue.
π License
MIT Β© FerhatDundar
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.