Naturepedia Canonical Discovery
RemoteAbout Naturepedia Canonical Discovery
Naturepedia Canonical Discovery is a stateless, read-only MCP server for discovering canonical resources from the Naturepedia live catalog. It is intended for clients that need to inspect publisher and authority details, search catalog entries, or resolve identifiers.
Key features
- 01Retrieve publisher, authority, access, and licensing details
- 02Search the live catalog
- 03Resolve catalog IDs, identifiers, slugs, or URLs
- 04Read canonical pages and machine-readable resources
Use cases
- 01Finding canonical Naturepedia pages
- 02Looking up machine-readable catalog resources
- 03Resolving a known identifier or URL
- 04Checking publisher and rights metadata
MCP support
It exposes three read-only tools through a Streamable HTTP MCP endpoint: `about_naturepedia`, `search_naturepedia`, and `resolve_naturepedia_resource`. The tools read the live Naturepedia AI catalog.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.robbiegeorgephotography.com/mcpclaude mcp add --transport http com-robbiegeorgephotography-naturepedia https://mcp.robbiegeorgephotography.com/mcp{"mcpServers":{"com-robbiegeorgephotography-naturepedia":{"type":"http","url":"https://mcp.robbiegeorgephotography.com/mcp"}}}Open in Cursor{"servers":{"com-robbiegeorgephotography-naturepedia":{"type":"http","url":"https://mcp.robbiegeorgephotography.com/mcp"}}}Open in VS Code{"mcpServers":{"com-robbiegeorgephotography-naturepedia":{"type":"http","url":"https://mcp.robbiegeorgephotography.com/mcp"}}}{"mcpServers":{"com-robbiegeorgephotography-naturepedia":{"serverUrl":"https://mcp.robbiegeorgephotography.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
3This tool takes no parameters.
Details
From the project READMENaturepedia MCP Server
Stateless, read-only Model Context Protocol server for Naturepedia, Robbie's Razor, and GC-MRD-v2.0 discovery.
Architecture
This project deploys as a separate Cloudflare Worker. It does not replace or modify cold-bird-7036. The MCP tools read the live Naturepedia AI catalog at:
https://www.robbiegeorgephotography.com/.well-known/ai-catalog.json
Initial tools
about_naturepedia— returns the publisher, authority, access model, and licensing boundary.search_naturepedia— searches the live catalog for canonical pages and machine-readable resources.resolve_naturepedia_resource— resolves an exact catalog ID, identifier, slug, or URL.
Routes
https://mcp.robbiegeorgephotography.com/health— ordinary HTTP health response.https://mcp.robbiegeorgephotography.com/mcp— production Streamable HTTP MCP endpoint.
Publisher and Registry metadata
- Registry identity:
com.robbiegeorgephotography/naturepedia - Publisher: Robbie George Photography
- Creator: Robbie George
- Publisher ID:
urn:ai:robbiegeorgephotography:publisher - Authority:
GC-MRD-v2.0 - Registry descriptor:
server.json
server.json is published in the official MCP Registry under com.robbiegeorgephotography/naturepedia. The active Registry record describes the public remote endpoint and includes publisher-provided service, discovery, authority, and rights metadata.
Official Registry record:
https://registry.modelcontextprotocol.io/v0/servers?search=com.robbiegeorgephotography%2Fnaturepedia
Development
npm install
npm run typecheck
npm run validate:registry
npm run dev
Deployment
Connect this repository to Cloudflare Workers Builds and set the root directory to mcp-server.
- Build command:
npm run typecheck - Deploy command:
npm run deploy - Production Worker name:
naturepedia-mcp - Production custom domain:
mcp.robbiegeorgephotography.com
The first release intentionally contains no paid MCP tools. Existing x402 endpoints remain canonical. Paid MCP tools should be added only after the cold-bird payload builder can be invoked without triggering a second settlement.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.