Who it is forA maintainer or contributor who has found a geospatial MCP server that is not yet in the list.
The problemThe README tables are generated, so a new server only appears after the entry is added and the script is run.
The outcomeThe new server appears in the correct category table with its language, deployment, type, access, and health status.
What you need first
- Git to clone the repo
- Python 3 to run the generation and health scripts
- Claude Code if you want to use the skill
- A web browser to read the catalog README
Steps
- Add an entry for the new server to servers.yaml, following the existing entries and the rules in CONTRIBUTING.md.
python3 -m venv .venv && ./.venv/bin/pip install -r requirements.txt./.venv/bin/python scripts/generate_readme.py- Open README.md and confirm the new server appears in the right category table and the counts are updated.
Prompt for your agent
In the sparkgeo/geo-mcp-servers repo, add an entry for <server name> to servers.yaml, regenerate the README tables, and report which category table the new row appears in. Verify that the total server count in README.md increased by one.
Caveat. The README says the tables are generated from servers.yaml, so edits made directly to README.md will be overwritten on the next regeneration.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for sparkgeo/geo-mcp-servers and "Add a new geo MCP server to the tracked catalog"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer