Diversion MCP Server
Connects Claude to Diversion version control API enabling repository management, branch operations, commit tracking, and code reviews through natural language. Supports workspace monitoring, file history, and collaborator access with flexible API key authentication.
README
Diversion MCP Server
MCP server untuk connect Claude dengan Diversion version control API.
Tools Available
| Tool | Description |
|---|---|
test_auth |
Test API token |
list_repos |
List semua repos |
get_repo |
Get details sesebuah repo |
list_branches |
List branches dalam repo |
create_branch |
Buat branch baru |
get_branch |
Get details sesebuah branch |
list_commits |
List commits |
get_commit |
Get details sesebuah commit |
list_workspaces |
List workspaces |
workspace_status |
Check workspace status (modified files) |
get_file_tree |
Get file tree sesebuah repo |
get_file_history |
Get commit history untuk file tertentu |
list_reviews |
List reviews/PRs |
list_collaborators |
List collaborators |
Deploy ke Railway (Paling Mudah)
1. Push ke GitHub dulu
git init
git add .
git commit -m "init diversion mcp server"
gh repo create diversion-mcp --public --push
2. Deploy kat Railway
- Pergi https://railway.app
- New Project → Deploy from GitHub repo
- Pilih repo
diversion-mcp - Add environment variable:
DIVERSION_API_KEY= (API key kau, optional — boleh pass per-request)
- Railway auto-detect Node.js dan build sendiri
- Copy URL yang Railway bagi (format:
https://xxx.railway.app)
3. Tambah dalam Claude
- Pergi Settings → Connectors → Add custom connector
- URL:
https://xxx.railway.app/mcp - Dalam Advanced Settings, letak Authorization header:
- Key:
Authorization - Value:
Bearer <DIVERSION_API_KEY_KAU>
- Key:
- Save ✅
Deploy ke Render (Free Tier Available)
- Push ke GitHub
- Pergi https://render.com → New Web Service
- Connect GitHub repo
- Settings:
- Build Command:
npm install && npm run build - Start Command:
npm start - Environment:
DIVERSION_API_KEY=<token_kau>
- Build Command:
- Copy URL → tambah
/mcp→ letak dalam Claude connectors
Run Locally (Testing)
npm install
npm run dev
Server akan run kat http://localhost:3000/mcp
Untuk test, gunakan MCP Inspector atau curl:
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <DIVERSION_API_KEY>" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
Authentication
Server support dua cara auth:
- Per-request — Pass
Authorization: Bearer <token>dalam setiap request (recommended, lebih secure) - Environment variable — Set
DIVERSION_API_KEYdan server akan guna tu kalau header tak ada
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.