Connect AI assistants to GitHub - manage repos, issues, PRs, workflows, and git operations.
MCPpedia last refreshed this data
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-aifity-omnigit-mcp": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
The Omnigit GitHub & Local Git MCP Server connects AI tools directly to GitHub's platform. This gives AI agents, assistants, and chatbots the ability to read repositories and code files, manage issues and PRs, analyze code, and automate workflows. All through natural language interactions.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml
Dynamic problem-solving through sequential thought chains
Persistent memory using a knowledge graph
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
Compact, efficient, and extensible long-term memory for LLM agents.
MCP Security Weekly
Get CVE alerts and security updates for io.github.aifity/omnigit-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
The Omnigit GitHub & Local Git MCP Server connects AI tools directly to GitHub's platform. This gives AI agents, assistants, and chatbots the ability to read repositories and code files, manage issues and PRs, analyze code, and automate workflows. All through natural language interactions.
Built for developers who want to connect their AI tools to GitHub context and capabilities, from simple natural language queries to complex multi-step agent workflows.
This is a fork of github/github-mcp-server with the following additions and improvements.
For the maintained backport checklist, see Fork Differences From Upstream.
get_review_comments now returns a CommentID field (which is the databaseId from GraphQL) alongside the GraphQL NodeID and DatabaseID for every comment node. This CommentID is the numeric ID that should be used when calling add_reply_to_pull_request_comment or pull_request_comment_write. Previously, only the opaque base64 GraphQL node ID was returned, forcing the model to decode it or scrape the numeric ID from comment URLs. The commentId / comment_id parameter descriptions in those tools now explicitly say to use the CommentID field.
issue_comment_write)A new issue_comment_write tool lets AI agents update or delete existing issue comments. Previously only add_issue_comment (create) was available.
pull_request_comment_write)A new pull_request_comment_write tool lets AI agents update or delete existing pull request review comments.
filter_patterns)Issue bodies, PR bodies, and local git commit messages are filtered before being sent to GitHub. By default, Co-Authored-By: trailers and generic AI-generated PR footers are stripped. The filter list is fully configurable via filter_patterns in omnigit-mcp-config.json. See i18n / Overriding Descriptions for details.
local_git)A full set of git_* tools for operating on local repositories without going through the GitHub API: git_add, git_apply_patch_file, git_apply_patch_string, git_checkout, git_commit, git_create_branch, git_diff, git_diff_staged, git_diff_unstaged, git_init, git_list_repositories, git_log, git_pull, git_push, git_reset, git_show, and git_status.