Instructions for using an MCP server that manages Git repositories and GitHub, the code-hosting service for collaboration and review.

Checking repositories, committing and syncing code, handling branches and conflicts, managing pull requests and issues, reviewing alerts, and administering GitHub settings.

It organizes repository, branch, pull request, issue, workflow, and administration tasks with safety rules for operations that change data.

mcp-github — Skill by scopweb

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/scopweb/mcp-go-github/mcp-github

Any agent

npx skills add scopweb/mcp-go-github --skill mcp-github

Clone the repo

git clone --depth 1 https://github.com/scopweb/mcp-go-github

Made for: Claude Code, Codex.

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,550 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00152	$0.04550
Opus 5	$0.00076	$0.02275
Sonnet 5	$0.00030	$0.00910
Haiku 4.5	$0.00015	$0.00455

Measured yesterday against content hash 08fdb1e95f46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-github scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/mcp-github/SKILL.md · 534 lines

How it starts

The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP GitHub Skill

Use the mcp-go-github MCP server to interact with GitHub repositories, Git workflows, pull requests, issues, dashboards, and administrative operations — all through Claude Desktop via MCP protocol.

This skill provides 86 tools organized in categories: Git operations, GitHub API, dashboard, hybrid file ops, Git-free file ops, response/repair, and full admin controls with a 4-tier safety system.

When to Use

USE this skill when:

Managing local Git repositories (status, commit, push, pull, branch, merge, rebase)
Resolving merge conflicts safely with backup support
Creating or reviewing pull requests and issues via MCP
Viewing your GitHub dashboard (notifications, assigned issues, PRs to review)
Managing repository settings, webhooks, collaborators, or branch protection
Creating or updating files with hybrid Git-first/API-fallback strategy
Dismissing security alerts (Dependabot, Code Scanning, Secret Scanning)
Re-running failed GitHub Actions workflows
Performing administrative operations with safety controls

When NOT to Use

DON'T use this skill when:

Using gh CLI directly in terminal -> use the github skill instead
Working with non-GitHub platforms (GitLab, Bitbucket) -> different tools required
Doing local-only file editing without Git context -> use file tools directly
Complex web UI interactions (GitHub settings pages) -> use browser
Bulk scripting across many repos -> use gh api with scripting

Setup

1. Build the Server

# Clone and build
git clone https://github.com/scopweb/mcp-go-github.git
cd mcp-go-github
go build -o mcp-go-github ./cmd/github-mcp-server/

2. Generate GitHub Token

Go to GitHub Settings > Personal Access Tokens
Click "Generate new token (classic)"
Select scopes:
- repo (required) - Full control of private repositories
- delete_repo (optional) - For repository deletion
- workflow (optional) - For re-running GitHub Actions
- security_events (optional) - For security alert dismissal
- admin:repo_hook (optional) - Enhanced webhook management
- admin:org (optional) - Team management in organizations

Read the full file on GitHub · 534 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 534 lines · 152 tokens per session scan A 08fdb1e95f46

Subscribe to this mod's changes

mcp-github is a skill published in the GitHub repository scopweb/mcp-go-github (0 stars, last pushed 15d ago), licensed MIT. It adds 152 tokens to every session and 4,550 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics Code review Git and workflow claude-desktop github-mcp-server go

control-flow

Analyze and design control flows and data structures. Produces compact ASCII tree diagrams showing triggers, call chains, payload shapes, state mutations, and re-render effects. Use when user asks to diagram, trace, visualize, or design a flow or data structure.

slopus/happy · 54 tokens

liveagent-code-review

Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation. Use when the user asks for code review, invokes the Code Review action from Git Review, or explicitly mentions this skill.

Stack-Cairn/LiveAgent · 54 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

deploy

Trigger the claude-desktop-extra Build & Release GitHub Actions pipeline (build-and-release.yml). With no argument the skill inspects the changes since the last release and decides forcerebuild itself; "/deploy force" / "/deploy no-force" override.

patrickjaja/claude-desktop-extra · 54 tokens

lc-curate-context

Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…

cyberchitta/llm-context.py · 90 tokens

drt-analyze

Analyze DRT cluster health for a given time range. Reconstructs the operations timeline, checks CockroachDB metrics (availability, latency, storage, changefeeds, jobs, goroutines, admission control, LSM, KV prober) and logs for anomalies, correlates findings with disruptive operations to distinguish expected…

cockroachdb/cockroach · 149 tokens