GitHub Issues and PRs with GitHub MCP and Continue

Use Continue and the GitHub MCP to list, summarize, and act on open issues and recently merged pull requests with natural language prompts.

What You'll Build

A GitHub workflow assistant that uses Continue with the GitHub MCP to:
  • List, filter, and summarize open issues
  • Review and summarize recently merged PRs
  • Post comments with AI-generated summaries or checklists
  • Automate routine GitHub maintenance with headless CLI runs

Prerequisites

Before starting, ensure you have:
  • Continue account with Hub access
  • Node.js 22+ installed locally
  • A GitHub account and a repository to work with
  • A GitHub token with the appropriate scopes:
    • For read-only: repo:read
    • To comment on issues/PRs: public_repo for public repos or repo for private repos
For all options, first:
1

Install Continue CLI

curl -fsSL https://raw.githubusercontent.com/continuedev/continue/main/extensions/cli/scripts/install.sh | bash
2

Configure GitHub Token

Add your GITHUB_TOKEN to your Continue Mission Control agent's environment variables.
To use agents in headless mode, you need a Continue API key. For write actions (e.g., posting comments), your token must include the relevant GitHub scopes.

GitHub MCP Workflow Options

🚀 Fastest Path to Success

Use the GitHub MCP from Continue Mission Control for one-click setup, or add it via CLI.
After ensuring you meet the Prerequisites above, you have two paths to get started:
1

Install GitHub MCP via Continue Mission Control

Visit the GitHub Project Manager Agent on Continue Mission Control and click Install to add it to your agent.
The listing provides a pre-configured MCP block; add your GITHUB_TOKEN in Hub.
2

Launch the Agent

From your repo root:
cn --agent continuedev/github-project-manager-agent
Now try: "List my open issues labeled bug and summarize priorities."
You can also attach an MCP to a one-off session: cn --mcp anthropic/github-mcp.

Issue Workflows

Use natural language to explore, triage, and act on open issues. The agent calls GitHub MCP tools under the hood.
Where to run these workflows:
  • IDE Extensions: Use Continue in VS Code, JetBrains, or other supported IDEs
  • Terminal (TUI mode): Run cn to enter interactive mode, then type your prompts
  • CLI (headless mode): Use cn -p "your prompt" --auto for automation
To run any of the example prompts below in headless mode, use cn -p "prompt"

Triage and Summaries

Summarize Open Issues

Get a prioritized overview of current open issues.
Prompt:
List the 20 most recently updated open issues in this repo.
Cluster by label and severity. Summarize top priorities.

Owner/Label Filters

Narrow by label or assignee.
Prompt:
Show open issues labeled bug or security, assigned to @me.
Summarize blockers and suggest next steps.

Taking Action

Comment on an Issue

Post an AI-generated status update or checklist.
Prompt:
Find the issue with the most engagement (comments, reactions) in the last 30 days.
Come up with a triage plan and draft a comment with:
- current hypothesis
- next 2 steps
- owner and ETA
Then post the comment.
Requires a token with permission to comment (public_repo or repo). The agent will confirm before posting unless --auto is used.

Find Stale Issues

Identify issues that need attention.
Prompt:
Find open issues with no activity in the last 30 days.
Suggest action (close, needs-repro, or prioritize) and draft comments.

Merged PR Workflows

Analyze recently merged PRs for change awareness, release notes, and quality signals.

Recently Merged Overview

Merged PR Digest

Summarize merged PRs over a time window.
Prompt:
List PRs merged in the last 7 days.
Group by area (label or path). Summarize impact and notable changes.

Release Notes

Generate Release Notes

Turn merged PRs into crisp release notes.
Prompt:
Generate release notes for PRs merged since tag v1.2.0.
Use keep-a-changelog sections and include PR numbers/authors.

Deep Dives

Summarize a PR

Get a human-readable summary of a recently merged PR with active discussion.
Prompt:
Find the last merged PR with a significant amount of comments.
Summarize the conversation, including goal, key changes,
risk areas, and any follow-ups.

Automate with GitHub Actions

Run headless commands on a schedule or in PRs to keep teams informed.

Add GitHub Secrets

Repository Settings → Secrets and variables → Actions:

Example Workflow

Create .github/workflows/github-mcp-reports.yml:
name: GitHub MCP Reports

on:
  schedule:
    - cron: "0 13 * * 1"  # Mondays 13:00 UTC
  workflow_dispatch:
  pull_request:
    types: [opened, synchronize]

jobs:
  report:
    runs-on: ubuntu-latest
    env:
      CONTINUE_API_KEY: ${{ secrets.CONTINUE_API_KEY }}
      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: "18"
      - name: Install Continue CLI
        run: npm i -g @continuedev/cli

      - name: Weekly Issue Triage Summary
        if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
        run: |
          cn --agent continuedev/github-project-manager-agent \
             -p "List open issues updated in the last 14 days. Group by label and priority. Propose top 5 actions and include issue links." \
             --auto > issue_summary.txt

      - name: Post PR Context Comment
        if: github.event_name == 'pull_request'
        env:
          PR_NUMBER: ${{ github.event.pull_request.number }}
        run: |
          REPORT=$(        cn --agent continuedev/github-project-manager-agent \
            -p "Summarize the context for PR #${PR_NUMBER}: related open issues, risk areas, and test suggestions. Keep under 200 words." \
            --auto)
          gh pr comment ${PR_NUMBER} --body "$REPORT"
Use continuedev/github-project-manager-agent consistently throughout your automation as the recommended agent configuration.

Troubleshooting

  • Missing or invalid token: Ensure GITHUB_TOKEN is set and has the required scopes. Try a minimal test: “List 3 open issues in this repo”.
  • Permissions errors on comment: Your token must include public_repo (public) or repo (private) to write comments.
  • Rate limiting: Reduce frequency or filter queries; consider using a PAT distinct from the default Actions token when running in CI.
  • MCP connection timeout: If using custom YAML, increase connectionTimeout or verify the command/args from Mission Control listing.

What You've Built

After completing this guide, you have a complete AI-powered GitHub workflow system that:
  • ✅ Uses natural language — Simple prompts for complex GitHub operations
  • ✅ Automates issue triage — AI analyzes and summarizes open issues
  • ✅ Generates release notes — Automatic PR digests and changelogs
  • ✅ Runs continuously — Automated reports via GitHub Actions

Continuous AI

Your GitHub workflow now operates at Level 2 Continuous AI - AI handles routine issue triage and PR summaries with human oversight through review and approval.

Next Steps

  1. Explore your issues - Try the issue triage prompts on your repository
  2. Generate release notes - Use the merged PR prompts to create changelogs
  3. Set up automation - Add the GitHub Actions workflow to your repo
  4. Customize prompts - Tailor the prompts to your team's workflow
  5. Monitor progress - Track issue resolution metrics over time

Additional Resources

GitHub MCP (Anthropic)

Anthropic GitHub MCP on Continue Mission Control

MCP in Continue

How MCP works with Continue agents

GitHub Project Manager Agent

Pre-configured agent on Continue Mission Control

GitHub MCP Server

Official GitHub MCP server README