mackenzie-github-mcp-server

An MCP (Model Context Protocol) server that exposes a set of GitHub operations (users, issues, pull requests, repositories, code search, and some code scanning alerts) to AI agents by wrapping GitHub APIs behind MCP tools. It can be run via Docker or built from source (Go binary) and authenticates to GitHub using a Personal Access Token passed via environment variable.

Evaluated Apr 04, 2026 (16d ago)

Repo ↗ DevTools mcp github go devtools api automation issues pull-requests repositories code-search

⚙ Agent Friendliness

/ 100

Can an agent use this?

🔒 Security

/ 100

Is it safe for agents?

⚡ Reliability

/ 100

Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality

Documentation

Error Messages

Auth Simplicity

Rate Limits

🔒 Security

TLS Enforcement

Auth Strength

Scope Granularity

Dep. Hygiene

Secret Handling

Uses a PAT provided via environment variable; this is typical but increases blast radius if overly permissive. The README does not document least-privilege scopes per tool, nor how secrets are handled internally (logging, redaction). Transport security (HTTPS to GitHub) is likely by the underlying GitHub client but is not explicitly stated. Project is MIT-licensed; dependency hygiene and vulnerability posture are not verifiable from the provided content.

⚡ Reliability

Uptime/SLA

Version Stability

Breaking Changes

Error Recovery

Best When

You want an MCP-native integration for agent tooling in VS Code or Claude Desktop and you’re comfortable authenticating via a GitHub PAT and operating the container/binary.

Avoid When

You need a public, vendor-hosted service with guaranteed SLAs, or you need fine-grained webhook/event delivery (this appears to be request/response tooling only).

Use Cases

• Automating GitHub workflows and repository interactions (issues, PRs, comments, branches, files).
• Building AI-powered developer tools that read and update GitHub resources.
• Searching GitHub for issues/pull requests, repositories, users, and code; optionally retrieving code scanning alerts.

Not For

• Running without GitHub credentials for any privileged actions (most operations require a token).
• Highly regulated environments that disallow use of personal access tokens without additional governance/controls.
• Use as a general-purpose GitHub API proxy when you need a stable HTTP/SDK contract rather than MCP tool semantics.

Interface

REST API

GraphQL

gRPC

MCP Server

Yes

SDK

Webhooks

Authentication

Methods: GitHub Personal Access Token (PAT) via GITHUB_PERSONAL_ACCESS_TOKEN / GITHUB_MCP inputs

OAuth: No Scopes: No

Authentication is via a PAT provided to the server container/binary. README instructs to enable the permissions you feel comfortable granting, but does not document required scopes per tool.

Pricing

Free tier: No

Requires CC: No

No service pricing described; usage depends on where you host/run the MCP server (Docker image or self-hosted binary) and GitHub API usage/limits.

Agent Metadata

Pagination

uses page/perPage style parameters for list/search tools (e.g., list_issues, list_pull_requests, search_*).

Idempotent

False

Retry Guidance

Not documented

Known Gotchas

⚠ Write operations may be non-idempotent (creating issues/comments/merges/files). Agents should avoid blind retries without deduplication logic.
⚠ Authentication is based on a PAT; mis-scoped tokens will cause authorization failures, but the required scopes per tool are not documented here.
⚠ Rate limiting behavior is not described in the provided README (agents may need to handle GitHub rate limits defensively).
⚠ The repository metadata indicates the project is archived; tooling may lag behind GitHub API changes.

Alternatives

GitHub REST API v3 or GraphQL API directly (with your own client code). Official GitHub SDKs (e.g., Octokit) for REST/GraphQL integration. Other MCP GitHub connectors (community projects) if they provide clearer contracts and stronger operational guarantees. Running GitHub Actions/workflows instead of agent-mediated write operations (for some automations).

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mackenzie-github-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-04-04.