mcp-local-rag
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rag_search_ddgsA | Search the web and return the most relevant pages as text. Default choice for lookups. Uses ddgs "auto" metasearch, which queries several engines (DuckDuckGo, Brave, Wikipedia, ...) and skips any that are blocked. Results are re-ranked locally by semantic similarity to the query before the top pages are fetched. |
| rag_search_googleA | Search Google and return the most relevant pages as text, re-ranked locally by semantic similarity. Google often blocks scrapers. When it returns nothing, this retries with ddgs "auto" metasearch and sends a warning saying so. |
| searchA | Search the web and return only the passages that answer the query, not whole pages: usually about a tenth of the text of rag_search_ddgs. Use this first. Tiers, cheapest first:
|
| deep_researchA | Research a topic across several search terms and engines. Each term is searched on each backend, results are re-ranked locally by relevance, duplicates are removed, and the best pages are fetched as text. Backends: auto, brave, duckduckgo, google, grokipedia, mojeek, startpage, wikipedia, yahoo.
|
| deep_research_googleA | Deep research using only Google: each term is searched, re-ranked locally, de-duplicated and the best pages fetched as text. Google often blocks scrapers. If it returns nothing, the terms are retried with ddgs "auto" metasearch and a warning is sent. |
| deep_research_ddgsA | Deep research using ddgs "auto" metasearch, which queries several engines per term and skips blocked ones. Results are re-ranked locally, de-duplicated and the best pages fetched as text. Same as deep_research with its default backend. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| research | Research a topic with deep_research and write a cited summary. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| mcpsurfr-search/SKILL.md | Search the web and research topics with the mcpsurfr MCP server, which needs no API keys and ranks results locally. Use it when you need current information, documentation, news, or several sources on a topic. Start with the `search` tool, which returns only the relevant passages. |
| mcpsurfr-search/_manifest | File listing for mcpsurfr-search |
TDQS
Scored across 6 tools
There is substantial overlap: rag_search_ddgs and deep_research_ddgs differ mainly by single-term vs multi-term querying, and rag_search_google mirrors deep_research_google. The bare `search` tool also competes with rag_search_ddgs, though its passage-level output and 'use this first' guidance help differentiate it.
Most tools use a consistent snake_case, prefixed pattern (rag_search_* and deep_research_*). The bare `search` name and the parallel backend suffixes (`_ddgs`, `_google`) create minor inconsistency, but the overall naming remains readable and predictable.
Six tools is well-scoped for a web-search/RAG server. Each tool maps to a search mode (smart passage search, page search, deep multi-term research) with backend variants.
The surface covers single-query page search, passage search, and multi-term deep research across multiple engines. A direct fetch/extract-URL tool or explicit index-management operation is absent, but core research workflows are covered.