release-intel
An MCP server that generates release intelligence from GitHub repository data, correlating commits, pull requests, issues, and contributors between two git refs to produce structured context for release notes, changelogs, and summaries.
README
release-intel-mcp
An MCP server that generates release intelligence from GitHub repository data. It correlates commits, pull requests, issues, and contributors between any two git refs and returns structured context ready for AI synthesis into release notes, changelogs, and release summaries.
Tools
get_changes_between_refs
Get all commits between two git refs enriched with associated PR metadata, author information, and linked issues.
| Field | Type | Description |
|---|---|---|
owner |
string | GitHub repository owner or organization |
repo |
string | GitHub repository name |
base |
string | Base ref (older tag, branch, or SHA) |
head |
string | Head ref (newer tag, branch, or SHA) |
get_pull_requests_in_range
Get all merged PRs between two refs, automatically categorized by label into: breaking, feature, fix, docs, chore, dependencies, other.
Input fields are identical to get_changes_between_refs.
get_release_summary
Generate a structured release context object combining commit data, PR metadata, linked issues, contributor list, and aggregate statistics.
| Field | Type | Description |
|---|---|---|
owner |
string | GitHub repository owner |
repo |
string | GitHub repository name |
from_tag |
string | Previous release tag (base) |
to_tag |
string | New release tag or HEAD |
Setup
All options require a GitHub personal access token with repo read access.
Generate one at: https://github.com/settings/tokens
Option A: stdio (local process)
The standard approach: the MCP client spawns the server as a local subprocess.
Claude Desktop
Config file: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"release-intel": {
"command": "npx",
"args": ["-y", "@barissozudogru/release-intel-mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token"
}
}
}
}
Claude Code
claude mcp add release-intel -e GITHUB_TOKEN=ghp_your_token -- npx -y @barissozudogru/release-intel-mcp
Cursor
Config file: ~/.cursor/mcp.json
{
"mcpServers": {
"release-intel": {
"command": "npx",
"args": ["-y", "@barissozudogru/release-intel-mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token"
}
}
}
}
Windsurf
Config file: ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"release-intel": {
"command": "npx",
"args": ["-y", "@barissozudogru/release-intel-mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token"
}
}
}
}
VS Code + Copilot
Config file: .vscode/mcp.json
{
"servers": {
"release-intel": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@barissozudogru/release-intel-mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token"
}
}
}
}
Cline
Config file: ~/.cline/mcp_settings.json (or via the Cline extension settings UI)
{
"mcpServers": {
"release-intel": {
"command": "npx",
"args": ["-y", "@barissozudogru/release-intel-mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token"
}
}
}
}
Continue.dev
Config file: ~/.continue/config.yaml
mcpServers:
- name: release-intel
command: npx
args:
- -y
- "@barissozudogru/release-intel-mcp"
env:
GITHUB_TOKEN: ghp_your_token
Zed
Config file: ~/.config/zed/settings.json
{
"context_servers": {
"release-intel": {
"command": {
"path": "npx",
"args": ["-y", "@barissozudogru/release-intel-mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token"
}
}
}
}
}
JetBrains (AI Assistant plugin)
{
"mcpServers": {
"release-intel": {
"command": "npx",
"args": ["-y", "@barissozudogru/release-intel-mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token"
}
}
}
}
Option B: HTTP (remote / stateless)
Run the server as an HTTP endpoint. Useful for remote clients, shared team deployments, or clients that prefer URL-based connections.
GITHUB_TOKEN=ghp_your_token npx @barissozudogru/release-intel-mcp --http
By default this starts on port 3000. Set PORT to change it.
Cursor (HTTP)
{
"mcpServers": {
"release-intel": {
"url": "http://localhost:3000/mcp"
}
}
}
VS Code + Copilot (HTTP)
{
"servers": {
"release-intel": {
"type": "http",
"url": "http://localhost:3000/mcp"
}
}
}
Windsurf (HTTP)
{
"mcpServers": {
"release-intel": {
"serverUrl": "http://localhost:3000/mcp"
}
}
}
Continue.dev (HTTP)
mcpServers:
- name: release-intel
type: streamable-http
url: http://localhost:3000/mcp
A health check endpoint is available at GET /health.
Option C: Docker
docker build -t release-intel-mcp .
docker run -p 3000:3000 -e GITHUB_TOKEN=ghp_your_token release-intel-mcp
The container starts in HTTP mode by default. The MCP endpoint is at http://localhost:3000/mcp.
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
GITHUB_TOKEN |
Yes | - | GitHub personal access token (repo scope) |
TRANSPORT |
No | stdio | Set to http to enable HTTP mode |
PORT |
No | 3000 | HTTP port (HTTP mode only) |
Local Development
git clone https://github.com/barissozudogru/release-intel-mcp.git
cd release-intel-mcp
npm install
npm run build
GITHUB_TOKEN=ghp_... node dist/index.js
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。