Skip to main content
Glama
SiwarKhalfaoui

github-changelog-mcp

by SiwarKhalfaoui
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

github-changelog-mcp

An MCP server that turns raw GitHub commit history into a categorized, human-readable changelog — directly inside Claude (or any MCP-compatible client).

You: "Generate a changelog for expressjs/express between v4.18.0 and v4.19.0"

Claude: [calls generate_changelog tool]

## expressjs/express: v4.18.0 → v4.19.0

### Features
- add support for X-Forwarded-Host header (`a1b2c3d`) — @wesleytodd

### Bug Fixes
- prevent ReDoS in query parser (`b2c3d4e`) — @cdoublev

### Chores
- bump path-to-regexp to 0.1.10 (`c3d4e5f`) — @dependabot

No paid APIs. No API keys required to get started (an optional free GitHub token just raises the rate limit).

Why this exists

Writing release notes by hand is tedious and usually done by skimming git log and manually sorting commits into categories. This tool automates that: it fetches the commit diff between two refs via GitHub's public REST API, classifies each commit (Conventional Commits prefix first, keyword heuristics as a fallback), filters out merge-commit noise, and renders clean grouped Markdown — as a tool Claude can call directly in conversation.

Related MCP server: gitrama-mcp

Tools

Tool

Description

list_tags

List recent tags for a public repo (use this to find valid ref names)

compare_refs

Raw commit diff between two refs, uncategorized

generate_changelog

The main tool — categorized Markdown changelog between two refs, with optional contributor summary

Setup

git clone https://github.com/SiwarKhalfaoui/github-changelog-mcp.git
cd github-changelog-mcp
npm install
npm run build

Optional — raise the GitHub API rate limit from 60/hr to 5,000/hr:

cp .env.example .env
# add a free token from https://github.com/settings/tokens (no scopes needed)

Connect it to Claude Desktop

Add this to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "github-changelog": {
      "command": "node",
      "args": ["/absolute/path/to/github-changelog-mcp/build/index.js"],
      "env": {
        "GITHUB_TOKEN": "optional-token-here"
      }
    }
  }
}

Restart Claude Desktop. You should see a 🔨 tools icon confirming the server connected — then just ask Claude to generate a changelog for any public repo.

Development

npm run dev              # run directly with tsx, no build step
npm run test:changelog   # run the categorization logic test suite

Architecture notes

  • src/github.ts — thin GitHub REST API wrapper. No SDK dependency, just fetch + a shared header builder. Handles rate-limit errors explicitly and surfaces an actionable message (which token to add, when the limit resets) rather than a raw HTTP error.

  • src/changelog.ts — the actual logic: Conventional Commits parsing with a keyword-based fallback for repos that don't use that convention, merge commit filtering, and Markdown rendering.

  • src/index.ts — MCP server wiring (tool registration, schemas via zod, stdio transport).

Kept intentionally dependency-light — GitHub's REST API and MCP's official SDK are the only two runtime dependencies. No frameworks, no ORMs, no unnecessary abstraction for a tool this size.

Possible extensions

  • Group changelog entries by scope (feat(auth): ... → group under "Auth") in addition to type

  • Compare against unreleased commits (to_ref = default branch) and suggest the next semver bump based on commit types present

  • Cache compareRefs responses per (owner, repo, base, head) to reduce API calls on repeated queries in the same session

License

MIT

Available Tools

3 tools
compare_refsCompare two refsA

Show the raw commit diff between two Git refs (tags, branches, or SHAs) in a public GitHub repository, without categorization.

ParametersJSON Schema
NameRequiredDescriptionDefault
baseYesBase ref, e.g. a tag name like 'v1.2.0'
headYesHead ref, e.g. 'main' or a newer tag
repoYes
ownerYes

TDQS

A4/5.0
Behavior3/5

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

Describes the output as raw commit diff without categorization. Does not disclose rate limits, authentication needs (though 'public repository' implies no auth), or behavior with large diffs. Adequate for a simple read operation given no annotations.

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?

Single sentence, no redundant words, front-loaded with key action and scope. Every word adds value.

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

Completeness4/5

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

Given no output schema and simple parameter set, the description covers the tool's purpose, scope, and key constraint (public repo, no categorization). Could optionally mention output format (e.g., diff text) but sufficient for selection.

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 descriptions for 'base' and 'head' are present (50% coverage), with examples like 'v1.2.0' and 'main'. The tool description mentions 'two Git refs' but does not clarify 'owner' and 'repo' beyond 'public GitHub repository'. Partially compensates for missing schema descriptions.

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?

Clearly states verb 'Show', resource 'raw commit diff', and scope 'between two Git refs in a public GitHub repository'. Explicitly notes 'without categorization', distinguishing it from sibling 'generate_changelog' which likely categorizes.

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

Usage Guidelines4/5

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

Provides context that the diff is raw and uncategorized, implicitly guiding agents to use this tool when they need a pure diff and alternative tools like 'generate_changelog' for categorized output. Lacks explicit when-not-to-use or named alternatives.

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

generate_changelogGenerate a categorized changelogA

Generate a clean, categorized Markdown changelog (Features / Bug Fixes / Docs / etc.) between two refs in a public GitHub repository. Uses Conventional Commits parsing where available and falls back to keyword heuristics otherwise. This is the main tool — use list_tags first if you don't know valid ref names.

ParametersJSON Schema
NameRequiredDescriptionDefault
repoYesRepository name, e.g. 'react'
ownerYesRepository owner, e.g. 'facebook'
to_refYesEnding ref (newer), e.g. 'main' or the latest tag
from_refYesStarting ref (older), e.g. a previous release tag
include_contributorsNoAppend a contributor commit-count summary (default false)

TDQS

A4.7/5.0
Behavior4/5

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

Discloses the internal algorithm (Conventional Commits parsing with fallback to keyword heuristics), which is beyond the basic purpose. However, it does not explicitly state that the operation is read-only, mention error handling, or note rate limits. The lack of annotations increases the burden, but the description covers essential behavioral traits well.

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?

Three sentences, no filler. First sentence front-loads the core purpose, second adds algorithm details, third gives usage guidance. Every sentence is essential and well-organized.

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

Completeness5/5

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

Given the tool's complexity (5 parameters, no output schema, no annotations), the description sufficiently covers purpose, algorithm, usage sequence, and output format. It provides enough context for an agent to invoke the tool correctly without additional information.

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

Parameters4/5

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

With 100% schema coverage, the schema already describes each parameter. The description adds value by explaining that from_ref and to_ref are 'refs', recommends using list_tags to find valid ref names, and ties parameters to the repository context (public GitHub repo). This extra context raises it above the baseline of 3.

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?

Clearly states the verb 'Generate', the resource 'categorized Markdown changelog', and the context 'between two refs in a public GitHub repository'. Differentiates from sibling 'list_tags' by positioning itself as the main tool and recommending list_tags for discovering valid ref names.

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

Usage Guidelines5/5

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

Explicitly states when to use this tool ('main tool') and when to use a sibling ('use list_tags first if you don't know valid ref names'). Provides clear prerequisite guidance, which helps the agent decide the correct sequence.

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

list_tagsList repository tagsA

List the most recent Git tags/releases for a public GitHub repository. Use this first to find valid ref names for generate_changelog.

ParametersJSON Schema
NameRequiredDescriptionDefault
repoYesRepository name, e.g. 'react'
limitNoMax tags to return (default 20)
ownerYesRepository owner, e.g. 'facebook'

TDQS

A3.8/5.0
Behavior4/5

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

No annotations are provided, but the description discloses read-only intent ('list'), scope ('public GitHub repository'), and recency ('most recent'). It does not cover rate limits or error scenarios, but is adequate for a simple list tool.

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?

Two efficient sentences: the first states the core purpose, the second provides a practical use case. No unnecessary words.

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

Completeness4/5

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

For a tool with 3 fully described parameters and no output schema, the description is fairly complete: it specifies scope (public), recency (most recent), and a downstream tool tie-in. Could mention return format or default ordering.

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 coverage is 100% with each parameter described. The description adds 'most recent' context and a usage purpose, but does not clarify how limit interacts with the 'most recent' ordering or the format of returned ref names.

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

Purpose4/5

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

Description clearly states 'list the most recent Git tags/releases for a public GitHub repository', a specific verb and resource. It also hints at differentiation by noting it should be used first for generate_changelog, though not explicitly distinguishing from compare_refs.

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 provides an implicit usage cue: 'Use this first to find valid ref names for generate_changelog'. However, it lacks explicit when-to-use or when-not-to-use guidance, and does not mention alternatives like compare_refs.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 3 tool updatesv1.0.0
    • First observedcompare_refs
    • First observedgenerate_changelog
    • First observedlist_tags
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.3/5.0
Disambiguation5/5

Each tool has a distinct purpose: listing tags for reference, generating a categorized changelog, and showing a raw diff. There is no overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern (list_tags, compare_refs, generate_changelog), making them predictable and easy to remember.

Tool Count5/5

Three tools is perfectly scoped for a changelog-focused server. Each tool serves a necessary step without bloat or deficiency.

Completeness5/5

The tool set covers the full workflow: listing available refs, generating a changelog, and providing a raw diff for verification. No obvious gaps for the declared purpose.

Maintenance

ActivityStale
ResponsivenessNo issues

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/SiwarKhalfaoui/github-changelog-mcp'

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