Git Commit Generator
MCP server implementation by Theoklitos Bampouris that generates conventional commit messages from staged git changes using AI analysis. The implementation provides two core tools: generate_commit_message which analyzes git diffs, file status, and change summaries to create structured prompts for LLMs to produce properly formatted conventional commits with optional user-specified type and scope parameters, and check_git_status which reports staged, unstaged, and untracked files with repository validation. Built with FastMCP and supporting both stdio and SSE transports, the server includes comprehensive git repository validation, detailed diff analysis with file change summaries, and strict output formatting rules that guide AI assistants to produce commit messages following conventional commit standards, making it valuable for developers who want consistent, well-structured commit messages generated automatically from their staged changes.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- version-control
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Git Commit Generator from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.