io.github.sjh9714/mergewarden MCP Server
io.github.sjh9714/mergewarden
Check whether a coding agent's changes stayed inside the scope it was given.
What is the io.github.sjh9714/mergewarden MCP server?
MergeWarden is an MCP server that analyzes pull requests to surface missing context before code review. It checks for missing issue links, thin descriptions, skipped templates, oversized changes, workflow permission risks, agent instruction changes, untrusted prompt inputs, and install scripts—without requiring login or AI analysis.
MergeWarden helps maintainers triage pull requests by identifying deterministic facts that deserve attention before code review. It surfaces missing issue links, thin descriptions, template violations, oversized changes, and security boundaries like workflow permissions and agent instruction modifications. Use it to streamline review queues and catch scope violations in coding agent changes.
How to install io.github.sjh9714/mergewarden
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
PR triage analysis— Analyze pull requests to identify missing issue links, thin descriptions, unused templates, and oversized changesSecurity boundary checks— Check workflow permissions, agent instructions, untrusted prompt inputs, and install scripts in pull requestsRepository queue review— Generate a deterministic queue of pull requests ordered by facts a maintainer would check before reading codeDetailed PR risk scan— Run comprehensive security and scope checks on individual pull requests via URL or owner/repository#number
Use cases
- Triage pull requests to identify which ones need context before code review
- Detect when a coding agent's changes exceed the scope defined in its instructions
- Verify that pull requests include proper issue links and descriptions before review
- Identify security risks like workflow permission changes or agent instruction modifications
- Automate PR risk checks in GitHub Actions workflows with automatic commenting
io.github.sjh9714/mergewarden MCP server FAQ
MergeWarden is a tool that analyzes pull requests to surface missing context and scope violations before code review. It checks for missing issue links, thin descriptions, oversized changes, and security boundaries like workflow permissions and agent instruction changes.
Yes, MergeWarden is open-source (MIT license) and free to use. The web app has no login requirement and no telemetry.
Install via npm with `mergewarden-mcp` and configure it in your MCP client. The MCP server provides tools to analyze pull requests and check scope compliance for coding agents.
The web app requires no login. For a larger authenticated queue, you can use the CLI with a GitHub token: `GH_TOKEN=... npx mergewarden@0.10.4 triage owner/repository`.
MergeWarden checks workflow permissions, agent instructions (AGENTS.md, CLAUDE.md, .mcp.json), untrusted prompt inputs in workflows, and install-time lifecycle scripts in package manifests.
No. MergeWarden uses only deterministic rules and public GitHub metadata. It never calls a language model and does not execute pull request code.
README (reference)
Source of truth, from the repository.
MergeWarden
See which pull requests need context before code review.
Paste a public GitHub repository. MergeWarden surfaces missing issue links, thin descriptions, skipped templates, and oversized changes. No login. No AI.
This is an experimental tool. Review-time savings and repeat maintainer use have not been demonstrated. Product expansion is on hold; see the roadmap and evidence limits.
Review a public repository
The getting started guide explains queue states, detailed PR results, and the Action install path.
Paste owner/repository or a full GitHub repository URL. The browser reads the
latest thirty open pull request summaries, removes trusted repository roles,
base repository branches, and known maintenance automation, then loads details
for at most ten external pull requests.
Rows are ordered by deterministic facts a maintainer would otherwise check before reading code.
| Fact | What it means |
|---|---|
| No linked issue | The body has no issue number, issue URL, or closing keyword |
| Thin description | The body has fewer than 80 characters of prose |
| Template unused | The repository has a visible PR template structure that the body did not keep |
| Oversized | The change exceeds 50 files or 1,500 changed lines |
First contribution is shown as context and never used as a score. MergeWarden does not call a contribution spam, low quality, or AI generated. It never closes, labels, scores, or comments on a pull request.
The queue uses public metadata and the base branch pull request template. It does not fetch changed file contents, execute code, use a backend, or store the target.
For a larger authenticated queue, use the CLI.
GH_TOKEN=... npx --yes mergewarden@0.10.4 triage owner/repository
Run the detailed PR risk scan
The same page accepts a full pull request URL or owner/repository#number.
Every queue row links to this detailed scan.
The detailed scan checks four security boundaries.
| Check | What deserves review |
|---|---|
| Workflow permissions | A workflow gains write access, uses a dangerous trigger, or depends on a moving Action reference |
| Agent instructions | A PR changes AGENTS.md, CLAUDE.md, .mcp.json, or another file that steers coding agents |
| Untrusted prompt inputs | Pull request text reaches an agent prompt in a workflow |
| Install scripts | A package manifest adds or changes install-time lifecycle code |
The configuration reference lists every deterministic rule and severity.
Run the same scan from a terminal without cloning the target repository.
npx --yes mergewarden@0.10.4 scan https://github.com/owner/repository/pull/123
Add the Action
The Action automates the detailed PR risk check. It does not order the review queue.
Create .github/workflows/mergewarden.yml.
name: MergeWarden PR Risk Check
on:
pull_request:
permissions:
contents: read
pull-requests: write
jobs:
mergewarden:
runs-on: ubuntu-latest
steps:
- uses: sjh9714/mergewarden@v0.10.4
with:
comment: auto
comment: auto stays quiet when there is nothing actionable and updates one
comment when a finding needs attention. Existing Action defaults are unchanged.
For an immutable install, pin the release commit.
MergeWarden does not publish or recommend a mutable v0 tag.
- uses: sjh9714/mergewarden@d63b4fc8c09c540375f039ecd30d2fce56abf31f
Safety boundaries
- The web app talks directly to the public GitHub API and has no telemetry.
- The queue reads metadata and templates at each PR's exact base commit. The detailed scan reads only the files required by deterministic rules.
- No checkout. MergeWarden does not execute pull-request code in the web app or Action.
- Policy comes from the exact base commit, never the untrusted PR head.
- Analysis never calls a language model.
- Incomplete evidence is reported as incomplete and never presented as a pass.
- Browser sample limits are explicit: reaching 30 summaries or leaving external PRs beyond the ten-detail limit does not produce a complete queue.
Read the security model and evidence model for the full trust boundary.
Evidence and advanced interfaces
Does triage help? records the existing queue measurement and its main limit. It measured whether rows discriminate, not whether maintainers save time. The current web queue remains a product experiment until maintainers confirm that value.
The documentation index includes configuration, Action and CLI references, coding-tool integrations, reproducible studies, and the MCP server.
Contributing
pnpm install --frozen-lockfile
pnpm build
pnpm test
pnpm typecheck
pnpm lint
pnpm format:check
Every new rule needs a passing fixture, a failing fixture, and a report snapshot. See the contribution guide.
License
Related MCP servers

RoutineKit
Capture tool workflows, save typed tools, and replay with human approval. Includes an MCP Apps UI.

io.github.sjk4425/ncloud
MCP server for managing Naver Cloud Platform (Ncloud) infrastructure

MCP server for managing Naver Cloud Platform Government (Ncloud 공공존) infrastructure

Reversecore MCP
AI-powered reverse engineering, malware analysis, and security auditing via 120 integrated tools
AI agent-to-agent SLA agreements on Base with insurance, reputation, and x402 payments.
Free, private skill discovery for AI agents — find vetted practices without sharing your work.
