Skip to main content
Glama
paolino

mcp-merge-guard

by paolino
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

mcp-merge-guard

MCP server that guards PR merge decisions by validating CI, approvals, conflicts, and branch freshness.

Features

  • check-merge-ready - Query-only status check that validates all guards

  • guard-merge - Atomic validate-then-merge that refuses if guards fail

    • Default merge method is merge (preserves signed branch commits)

    • Rebase is refused unless allowSignatureStripping: true is passed

    • Optional localRepoPath support updates the local base branch after merge without relying on the clone's remote protocol

Related MCP server: mcp-pr-reviewer

Guards

Guard

Description

ci-status

All CI checks passed, none pending or failed

approval

PR is approved (or no review required)

conflicts

No merge conflicts

up-to-date

Branch is current with base (optional, off by default)

merge-method-policy

Rebase refused unless allowSignatureStripping is set

Installation

Requires gh CLI installed and authenticated.

With Nix (recommended)

Add to your Claude Code settings (~/.claude/settings.json):

{
  "mcpServers": {
    "merge-guard": {
      "command": "nix",
      "args": ["run", "github:paolino/mcp-merge-guard"]
    }
  }
}

Or use /settings in Claude Code to add the MCP server through the UI.

From source

git clone https://github.com/paolino/mcp-merge-guard
cd mcp-merge-guard
npm install && npm run build

Add to ~/.claude/settings.json (use absolute path):

{
  "mcpServers": {
    "merge-guard": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-merge-guard/dist/index.js"]
    }
  }
}

Restart Claude Code after adding the configuration.

Usage

Once configured, use the tools in Claude Code:

Check if PR #42 in owner/repo is ready to merge
Merge PR #42 in owner/repo if all guards pass

Documentation

Full documentation at paolino.github.io/mcp-merge-guard

Development

just install   # Install dependencies
just build     # Build TypeScript
just test      # Run tests
just CI        # Full CI pipeline

License

MIT

Available Tools

1 tool
guard-mergeA

Validate guards and merge PR only if all pass (atomic operation)

ParametersJSON Schema
NameRequiredDescriptionDefault
repoYesRepository name
ownerYesRepository owner (user or organization)
prNumberYesPull request number
mergeMethodNoMerge method to use (default: rebase)rebase
localRepoPathNoLocal repo path whose base branch should be updated after merge. Fetches the merged base branch over GitHub HTTPS and fast-forwards the local base branch.
requireUpToDateNoRequire branch to be up to date with base (default: false)

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the atomic validation-then-merge behavior and the guard constraint. However, with no annotations, it does not cover potential side effects, auth requirements, or failure handling beyond the implied no-merge if guards fail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that is front-loaded with the key actions and condition. No superfluous words; every part is necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is too brief for a tool with 6 parameters and no output schema. It does not explain what 'guards' are, how validation works, or what the output looks like (e.g., success/failure). More context is needed for an agent to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds no additional parameter meaning beyond what the schema provides; it does not clarify how guards are specified or what 'validate' entails.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool validates guards and merges a PR only if all pass, with 'atomic operation' highlighting indivisibility. The verb 'validate' and 'merge' combined with the condition clearly define the tool's purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for validating and merging PRs but does not specify when to use this tool vs alternatives. No exclusions or when-not-to-use guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion between tools. The single tool has a clearly distinct purpose.

Naming Consistency5/5

The single tool name 'guard-merge' follows a consistent verb_noun pattern, making it clear and predictable.

Tool Count3/5

The server has only one tool, which is on the low end of appropriate scope. While focused, it feels thin for typical server expectations.

Completeness2/5

The server only offers an atomic guard-and-merge operation, lacking separate validation or configuration tools. This creates significant gaps for an agent that might need to validate guards without merging.

Maintenance

ActivitySlowing
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/paolino/mcp-merge-guard'

If you have feedback or need assistance with the MCP directory API, please join our Discord server