home / mcp / theneo mcp server
Model Context Protocol server for Theneo SDK - The automation backbone for API documentation in the AI era.
Configuration
View docs{
"mcpServers": {
"atombreak-theneo-mcp": {
"url": "https://api.theneo.io",
"headers": {
"THENEO_API_KEY": "YOUR_API_KEY",
"THENEO_PROFILE": "default",
"THENEO_BASE_API_URL": "https://api.theneo.io",
"THENEO_BASE_APP_URL": "https://app.theneo.io"
}
}
}
}You are equipped with a Model Context Protocol (MCP) server that exposes Theneoβs API documentation platform to AI assistants. This server lets you create, update, and publish API docs automatically, enabling AI-driven workflows, CI/CD automation, and developer productivity tools with natural language commands.
Interact with the MCP server using an MCP-compatible AI assistant. You can reference workspaces and projects by name, not IDs, and perform end-to-end documentation tasks such as listing workspaces, creating projects from OpenAPI specs, importing updates, generating AI descriptions, previewing editors, and publishing documentation. You can combine natural language prompts with explicit tool calls to control flow and timing, for example by creating a project, waiting for AI generation to finish, then exporting or publishing.
Prerequisites: Node.js (for building and running the MCP server locally) and a modern shell. You will install a local MCP CLI, or run the server via Docker. Follow the concrete steps below to get started.
# Global installation (recommended for quick start)
npm install -g theneo-mcp
# Verify installation
theneo-mcp --versionDocker provides a ready-to-run option that accepts an API key for authentication. You can pull the latest image and run it with your key in the environment.
# Pull and run with API key
docker pull theneo/theneo-mcp:latest
docker run -it --rm \
-e THENEO_API_KEY=your_api_key \
theneo/theneo-mcp:latestIf you are developing locally, you can clone the project, install dependencies, and build before running the server. The typical flow is to install dependencies, build, and then start the MCP server.
git clone https://github.com/atombreak/theneo-mcp.git
cd theneo-mcp
npm install
npm run build
# Start during development (example)
npx theneo-mcp server
```
Note: You may run the server with an API key as an environment variable when you start it in development or production environments. Replace your_api_key with your actual key.Configure authentication and environment settings to control how the MCP server operates and how it connects to Theneo services.
# OS keychain (recommended for local dev)
theneo-mcp creds save --profile default --apiKey YOUR_API_KEY
# Environment variable (alternative)
export THENEO_API_KEY=YOUR_API_KEYUse the MCP client through your AI assistant to manage projects, workspaces, versions, AI generation, previews, and exports. You can list workspaces, create projects from OpenAPI specs, import updates, publish versions, and export documentation. Tools can be driven by natural language prompts or explicit tool calls.
List all workspaces accessible to your account. Provides a view of the workspaces you can interact with.
List all projects in a workspace or across workspaces. You can filter by workspace by ID, key, or name.
Create a new API documentation project from an OpenAPI/Swagger file, URL, or raw spec, with optional AI description generation and publishing.
Import or update API documentation into an existing project from a file, URL, or raw spec, with merge or overwrite options.
Publish a project to make it live, optionally specifying a version to publish.
Get the editor preview URL for a project to review the docs in the editor.
Wait for AI-generated descriptions to complete for a project.
Check the progress and status of AI description generation for a project.
Permanently delete a project and all its associated data.
List all versions of a specific project.
Create a new version of a project, possibly copying from a previous version.
Delete a specific project version.
Add an email subscriber to receive updates for a specific project version.
Export a project's documentation, optionally as OpenAPI, with various options.
List all Postman collections available with a given Postman API key.