mcp · Global

rag-mcp

Package to build mcp server which can apply retrieval augmented generation ( RAG ) principles to tool selection. Instead of flooding the LLM with all MCP descriptions, we will maintain an external vector index of all available MCP metadata

Visit source ↗GitHub repository ↗

Claim this listing

Represent rag-mcp? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: semantic retrieval over an external vector index of MCP metadata · top-k candidate MCP retrieval for a query

Useful for

Use cases llm-inferred: Selecting the right MCP server from a large catalogue of water, civils and environmental data tools without loading every tool description into the prompt · Keeping an assistant's prompt small when a consultancy's MCP registry grows past about 10 tools · Routing a query to one dataset server (e.g. gauge or rainfall data) before invocation
Audience llm-inferred: AI/LLM application developers · MCP server developers · platform engineers building tool-routing for assistants

Limitations

Constraints llm-inferred: Docs describe a retrieval approach for tool selection, not a data source; no datasets, coverage or update details are stated · No install instructions, API reference, transport or output formats are given in the docs · No licence or authentication is stated in the metadata or docs · Performance figures (token reduction, accuracy gains) are cited from a research paper and a trading-bot example, not measured for this package · Entry categories (flood, gis) and region (Global) are not reflected in the docs

Licence: Unknown — check provider terms
Authentication: Unknown — review source docs
GitHub stars: 6
Last commit: 28/07/2025
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Auto-extracted, unverified fields: tools, auth. Check upstream documentation.

Provenance & evidence

Tools/install/auth auto-extracted from README; quality score heuristic (stars, recency, tool count, licence).

Metadata observed 15/10/2026 · research sweep: github-search