Speckle MCP server for AI agents

This MCP server acts as a bridge between Speckle's API and client applications, providing tools to interact with Speckle projects, models, and objects. It allows you to search projects, retrieve model versions, and query object properties from within interfaces that support the Model Context Protocol.

Installation

Prerequisites

Python 3.13 or higher
Speckle account with a personal access token
uv for dependency management and virtual environments

Setup

Clone the repository:

git clone https://github.com/bimgeek/speckle-mcp.git
cd speckle-mcp

Verify your Python version:

python --version  # Should show Python 3.13.x

Install dependencies using uv:
```
uv pip install -r requirements.txt
```

Configuration

Environment Variables

The server requires the following environment variables:

SPECKLE_TOKEN: Your Speckle personal access token (required)
SPECKLE_SERVER: The Speckle server URL (defaults to https://app.speckle.systems)

MCP Configuration

To use this server with Claude, update your MCP configuration file, typically located at:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add or update the "speckle" entry in the mcpServers section:

{
  "mcpServers": {
    "speckle": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/speckle-mcp",
        "run",
        "speckle_server.py"
      ],
      "env": {
        "SPECKLE_TOKEN": "YOUR_SPECKLE_API_TOKEN_HERE",
        "SPECKLE_SERVER": "https://app.speckle.systems"
      }
    }
  }
}

Be sure to replace /path/to/speckle-mcp with the actual path to the directory containing the speckle_mcp package.

Using Available Tools

Projects

List Projects

Lists all accessible Speckle projects.

Parameters:

limit (optional): Maximum number of projects to retrieve (default: 20)

Get Project Details

Retrieves detailed information about a specific project.

Parameters:

project_id: The ID of the Speckle project to retrieve
limit (optional): Maximum number of models to retrieve (default: 20)

Search Projects

Searches for projects by name or description.

Parameters:

query: The search term to look for in project names and descriptions

Models

Get Model Versions

Lists all versions for a specific model.

Parameters:

project_id: The ID of the Speckle project
model_id: The ID of the model to retrieve versions for
limit (optional): Maximum number of versions to retrieve (default: 20)

Objects

Get Version Objects

Retrieves objects from a specific version.

Parameters:

project_id: The ID of the Speckle project
version_id: The ID of the version to retrieve objects from
include_children (optional): Whether to include children objects (default: false)

Query Object Properties

Queries specific properties from objects in a version.

Parameters:

project_id: The ID of the Speckle project
version_id: The ID of the version to retrieve objects from
property_path: The dot-notation path to the property (e.g., "elements.0.name")

Troubleshooting

If you encounter issues:

Verify your Speckle token is valid and has the necessary permissions
Check the server logs for detailed error messages
Ensure the environment variables are correctly set in the MCP configuration

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "speckle" '{"command":"uv","args":["--directory","/path/to/speckle-mcp","run","speckle_server.py"],"env":{"SPECKLE_TOKEN":"YOUR_SPECKLE_API_TOKEN_HERE","SPECKLE_SERVER":"https://app.speckle.systems"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "speckle": {
            "command": "uv",
            "args": [
                "--directory",
                "/path/to/speckle-mcp",
                "run",
                "speckle_server.py"
            ],
            "env": {
                "SPECKLE_TOKEN": "YOUR_SPECKLE_API_TOKEN_HERE",
                "SPECKLE_SERVER": "https://app.speckle.systems"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "speckle": {
            "command": "uv",
            "args": [
                "--directory",
                "/path/to/speckle-mcp",
                "run",
                "speckle_server.py"
            ],
            "env": {
                "SPECKLE_TOKEN": "YOUR_SPECKLE_API_TOKEN_HERE",
                "SPECKLE_SERVER": "https://app.speckle.systems"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect