github-mcp-server
Provides a Model Context Protocol (MCP) server that exposes GitHub-related tools (e.g., listing/searching and creating issues/PRs, pending reviews, and issue priority analysis). Tools are described as stateless and require authentication with permission checks.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
README states tools require authentication and are protected by permission checks, and expects a token via environment variable. However, it does not document whether transport uses HTTPS-only (for the MCP server), how tokens are stored/handled internally (logging/redaction), or whether tools enforce fine-grained scopes per operation.
⚡ Reliability
Best When
You want an agent-friendly, tool-based integration to GitHub issue/PR workflows via MCP, using a token-based auth model and controlled permissions.
Avoid When
You need a fully documented REST/OpenAPI interface, webhooks, or strong published guarantees about retries/idempotency and error formats beyond what is stated in the README.
Use Cases
- • Enable LLM agents to list/search GitHub issues and pull requests
- • Automate issue triage workflows (including priority analysis)
- • Create issues from agent workflows with permissioned access
- • Fetch PRs pending review for operational workflows
Not For
- • Arbitrary GitHub data scraping without authenticated permissions
- • High-risk write operations without reviewing tool semantics and idempotency
- • Use cases requiring real-time webhook push events from this MCP server
Interface
Authentication
README indicates authentication via a GitHub token and permission checks, but does not document OAuth flow details or fine-grained scopes for MCP tools.
Pricing
No pricing information provided (appears to be a self-hosted open-source-style repo).
Agent Metadata
Known Gotchas
- ⚠ Write operations (e.g., create_issue) may require careful handling to avoid duplicates, but idempotency behavior is not documented in the README.
- ⚠ Pagination/limit behavior for list/search tools is not documented in the README.
- ⚠ Error formats and retry guidance are not documented in the README; agents may need to infer retry behavior from runtime errors.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for github-mcp-server.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
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
Scores are editorial opinions as of 2026-04-04.