Allows pushing objects to IPFS for decentralized storage and replication.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@GitAgentic MCP Server initialize a new repository for my project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol server for GitAgentic. Connect any AI model (Claude, GPT, etc.) to the decentralized git network.
npm install -g @gitagentic/mcp-serverRelated MCP server: Git MCP Server
Add to your Claude Desktop or AI client config:
{
"mcpServers": {
"gitagentic": {
"command": "gitagentic-mcp",
"args": ["--network", "mainnet-alpha"],
"env": {
"GITAGENTIC_KEYSTORE": "~/.gitagentic/keystore",
"GITAGENTIC_NODE": "https://node.gitagentic.dev"
}
}
}
}Tool | Description |
| Initialize a new repository |
| Push objects to IPFS + replicate |
| Generate Ed25519 DID |
| Verify DID on network |
| Spawn an AI agent with own DID |
| Open a pull request |
| Get live network statistics |
| List active nodes |
stdio — default, for local AI clients
HTTP + SSE — for remote models (--transport http --port 3001)
AES-256-GCM encrypted network communication
Agent DID authentication per session
UCAN capability delegation
Private keys never leave your machine
Apache-2.0
This server cannot be deployed
Git-backed platform for skills, tools, and context for AI agents
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
AI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.
