Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    GitHub-Issues Manager

    1

    Production-grade MCP server for safe, automated GitHub issue management and triage.

    Free

    1 useSecurity scanned
    GitHub-Issues Manager

    GitHub-Issues Manager

    Example session with this skill installed

    I've finished the login validation bug fix. Close issue #42 as completed and add the 'high-priority' label to it so the QA team sees it.

    • Read your context and instructions
    • Compiled the github-issues manager

    I have updated issue #42. I added the 'high-priority' label and then closed the issue with the reason 'completed'.

    GitHub Issue Update: #42

    PropertyValue
    Issue Number42
    Current Stateclosed
    State Reasoncompleted
    Added Labelhigh-priority
    Current Labelsbug, high-priority
    RepositoryEngine-User/issue-function

    Next steps

    • Verify the 'high-priority' label appears in the GitHub UI for your QA workflow.
    • Use list_open_issues to check if there are other related bugs that need closing.
    • Inform the @alice that the fix is ready for verification.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Manual GitHub issue management wastes developer cycles and disrupts flow. This skill provides an MCP server that gives AI agents safe, validated, and auditable access to your GitHub issue tracker directly from your IDE.

    What it does

    • Create issues with full support for titles, bodies, labels, and assignees.
    • List open issues using filters to find specific tasks without pull request noise.
    • Retrieve issue details including state and labels with automatic body truncation for context efficiency.
    • Close issues with specific state reasons like completed or not planned.
    • Manage labels through a secure allowlist system that validates or creates tags as needed.

    How it works

    1. Configure credentials by setting a GitHub Personal Access Token and repository target in a .env file.
    2. Launch the server via an MCP-compatible host like Claude Desktop, Cursor, or Claude Code.
    3. Execute commands using natural language to trigger tools like create_issue or list_open_issues.

    Frameworks & tools

    Built with Python 3.14 and the uv package manager. It uses the Model Context Protocol (MCP) to interface with IDEs and AI chat clients.

    Why this beats prompting it yourself

    Generic prompts lack the safety boundaries required for repository write access. This skill implements a defense-in-depth model with a read-only kill switch, label allowlisting, and idempotency checks to prevent duplicate operations.

    Use cases

    • Triage bug reports by instantly creating issues from chat transcripts and tagging them for review.
    • Cleanup stale tasks by listing old issues and closing them with appropriate reasons.
    • Sprint planning by fetching issue details and updating priorities based on team discussion.

    Known limitations

    Does not support pull request management, comments, or repository settings. Designed for standard GitHub repositories, not tested for GitHub Enterprise.

    No support for pull requests, comments, or webhooks. Requires Python 3.14. Not tested on GitHub Enterprise. Body content is truncated at 8000 characters.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Requires

    Python
    Git

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Listed24 days ago

    What's inside

    Frequently Asked Questions

    This skill allows your AI agent to create, list, and close GitHub issues while providing a safety layer that includes label allowlisting and a read-only kill switch to prevent accidental repository changes.

    The skill is designed for any environment that supports the Model Context Protocol (MCP), including Claude Desktop, Cursor, and Claude Code.

    No, this specific skill is purpose-built for issue triage and management; it does not currently support pull requests, comments, or general repository settings.

    You will receive the complete Python-based MCP server source code, a configuration template for environment variables, and comprehensive instructions for deployment via the `uv` package manager.

    Setup is straightforward: you simply provide a GitHub Personal Access Token and your target repository details in a `.env` file, then point your MCP host to the server's entry point.

    New in APIs & Backend