Interact with Speckle, the collaborative data hub that connects with your AEC tools.
A Model Context Protocol (MCP) server for interacting with Speckle, the collaborative data hub that connects with your AEC tools.
This MCP server acts as a bridge between Speckle's API and client applications and exposes a set of tools that allow users to:
Clone this repository:
git clone https://github.com/bimgeek/speckle-mcp.git
cd speckle-mcp
Ensure you have Python 3.13 installed:
python --version # Should show Python 3.13.x
Install dependencies using uv:
uv pip install -r requirements.txt
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)To use this server with Claude, you need to update your MCP configuration file. The configuration file is typically located at:
~/Library/Application Support/Claude/claude_desktop_config.json
%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"
}
}
}
}
Replace /path/to/speckle-mcp
with the actual path to the directory containing the speckle_mcp
package.
list_projects
: Lists all accessible Speckle projects
limit
(optional): Maximum number of projects to retrieve (default: 20)get_project_details
: Retrieves detailed information about a specific project
project_id
: The ID of the Speckle project to retrievelimit
(optional): Maximum number of models to retrieve (default: 20)search_projects
: Searches for projects by name or description
query
: The search term to look for in project names and descriptionsget_model_versions
: Lists all versions for a specific model
project_id
: The ID of the Speckle projectmodel_id
: The ID of the model to retrieve versions forlimit
(optional): Maximum number of versions to retrieve (default: 20)get_version_objects
: Retrieves objects from a specific version
project_id
: The ID of the Speckle projectversion_id
: The ID of the version to retrieve objects frominclude_children
(optional): Whether to include children objects in the response (default: false)query_object_properties
: Queries specific properties from objects in a version
project_id
: The ID of the Speckle projectversion_id
: The ID of the version to retrieve objects fromproperty_path
: The dot-notation path to the property (e.g., "elements.0.name")This project is licensed under the MIT License - see the LICENSE file for details.
Create, manage, and explore your content and content model using natural language in any MCP-compatible AI tool.
Access global weather forecasts and historical data through the Open-Meteo API.
An MCP server for the Lodgify vacation rental API.
An MCP server deployed on Cloudflare Workers, featuring OAuth login and data storage via Cloudflare KV.
A read-only MCP server for Azure Data Catalog, powered by CData's JDBC driver.
Provides comprehensive analytics for Solana wallets, including real-time portfolio insights and detailed DeFi activity tracking.
Analyzes images using the GPT-4o-mini model via the OpenAI API.
A server for Snowflake providing tools for its Cortex AI features, including Search, Analyst, and Complete.
Integrates with Alibaba Cloud APIs to manage resources like ECS, Cloud Monitor, and OOS.
Official Hostinger API MCP server for services managment.