Click on "Install 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., "@OpenContext find datasets about air quality in Boston"
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.
# 1. Configure (create config, enable one data source)
cp config-example.yaml config.yaml
# Edit config.yaml - set enabled: true for one plugin
# 2. Test locally
pip install aiohttp
python3 scripts/local_server.py
# 3. Deploy
./scripts/deploy.shConnect via Claude Connectors (same steps on both Claude.ai and Claude Desktop):
Go to Settings → Connectors (or Customize → Connectors on claude.ai)
Click Add custom connector
Enter a name (e.g. "Boston OpenData") and your API Gateway URL
Get the URL: cd terraform/aws && terraform output -raw api_gateway_url
See Getting Started for full setup.
Related MCP server: ontario-data-mcp
Doc | Description |
Setup and usage | |
System design and plugins | |
AWS, Terraform, monitoring | |
Local testing (Terminal, Claude, MCP Inspector) | |
Parcel/assessment MCP server (this repo's plugin) |
Boston OpenData (CKAN): examples/boston-opendata/config.yaml
Custom plugin: examples/custom-plugin/
Pre-commit hooks (optional):
pip install pre-commit
pre-commit installHooks: Ruff, yamllint, gofmt. Run manually: pre-commit run --all-files.
MIT — see LICENSE.
Author: Srihari Raman, City of Boston Department of Innovation and Technology
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
This MCP server provides seamless access to Malaysia's government open data, including datasets, w…
MCP server giving Claude AI access to 22+ NYC public-record databases for real estate due diligence
MCP server for Brazilian Federal Senate open data (legislative, administrative, e-Cidadania).
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/codeforanchorage/anchorage-parcels-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server