Skip to main content
Glama

Nitrozen MCP Server

Official remote Model Context Protocol server for Nitrozen.io, the hosted changelog platform. Let your AI assistant create projects, write and publish changelog entries, and read your public changelog.

Nothing to install: it is a hosted server. This repository holds the Worker source.

Tools

Tool

Description

get_user

Get authenticated user profile and plan

get_usage

Get usage statistics and plan limits

list_projects

List all changelog projects (each includes public_url)

create_project

Create a new project

get_project

Get a project by ID, including its public_url

update_project

Update project name/description

delete_project

Delete a project

list_entries

List entries for a project (paginated)

create_entry

Create a changelog entry

get_entry

Get an entry by ID

update_entry

Update an entry

delete_entry

Delete an entry

list_tokens

List API tokens

create_token

Create a new API token

revoke_token

Revoke an API token

get_public_entries

List published entries by project slug (no auth)

Related MCP server: gitea-mcp

Authentication

  • Claude.ai uses OAuth 2.0: add the server URL and authorize in the browser. No token needed.

  • All other clients send an API token in a header: Authorization: Bearer <your-api-token>. Create a token on the API Tokens page (choose the read scope for read-only access).

Requests without a valid token get 401 with a WWW-Authenticate header pointing to https://mcp.nitrozen.io/.well-known/oauth-protected-resource.

Connect your client

Claude.ai

Settings → Connectors (Integrations) → Add custom connector → https://mcp.nitrozen.io/mcp, then sign in to Nitrozen and approve.

Claude Code

claude mcp add --transport http nitrozen https://mcp.nitrozen.io/mcp \
  --header "Authorization: Bearer <your-api-token>"

Cursor (~/.cursor/mcp.json) / Windsurf / other JSON configs

{
  "mcpServers": {
    "nitrozen": {
      "url": "https://mcp.nitrozen.io/mcp",
      "headers": { "Authorization": "Bearer <your-api-token>" }
    }
  }
}

Cline (cline_mcp_settings.json)

{
  "mcpServers": {
    "nitrozen": {
      "type": "streamableHttp",
      "url": "https://mcp.nitrozen.io/mcp",
      "headers": { "Authorization": "Bearer <your-api-token>" },
      "disabled": false
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "nitrozen": {
      "type": "http",
      "url": "https://mcp.nitrozen.io/mcp",
      "headers": { "Authorization": "Bearer <your-api-token>" }
    }
  }
}

Docker (stdio bridge)

For stdio-only clients, the included Dockerfile bridges to the hosted server with mcp-remote:

docker build -t nitrozen-mcp .
docker run -i --rm -e NITROZEN_API_TOKEN=<your-api-token> nitrozen-mcp

Development

npm install
npm run dev      # local Worker
npm run deploy   # deploy to Cloudflare

License

See LICENSE.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    C
    maintenance
    MCP server that exposes RESTForge capabilities to AI agents, enabling them to set up, configure, generate code, and manage RESTForge projects through natural language.
    29
    44 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    An MCP server that enables AI assistants to read, create, and manage issues, repositories, and releases on Gitea, Forgejo, or Codeberg instances via personal access tokens.
    21
    123 PyPI
    2
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    A universal MCP server that enables AI assistants to safely manage changelog files by writing structured records to a JSONL store and deterministically generating markdown changelogs.
    15
    MIT