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": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rag_search_ddgsA | Search the web for a given query using DuckDuckGo. Returns context to the LLM with RAG-like similarity scoring to prioritize the most relevant results. This tool fetches web search results, scores them by semantic similarity to the query using text embeddings, and returns the top-ranked content as markdown text. |
| rag_search_googleB | Search on Google for a given query using ddgs. Give back context to the LLM with a RAG-like similarity sort. |
| deep_researchA | Perform deep research across multiple search terms using specified search backends. This tool aggregates results from multiple searches across chosen engines, scores them by relevance, and returns the most relevant content with duplicates removed. Perfect for comprehensive research on a topic. Available backends: bing, brave, duckduckgo, google, grokipedia, mojeek, yandex, yahoo, wikipedia USAGE GUIDANCE FOR LLM:
|
| deep_research_googleA | Perform deep research across multiple search terms using ONLY Google. Aggregates results from multiple Google searches, scores them by relevance, and returns the most relevant content with duplicates removed. |
| deep_research_ddgsA | Perform deep research across multiple search terms using ONLY DuckDuckGo. Aggregates results from multiple DuckDuckGo searches, scores them by relevance, and returns the most relevant content with duplicates removed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
The generic deep_research tool already supports DuckDuckGo and Google as backends, making the dedicated deep_research_ddgs and deep_research_google tools redundant. Similarly, rag_search_ddgs and rag_search_google overlap with each other and partially with deep_research. This overlap can cause an agent to choose the wrong tool.
Tool names follow a consistent verb_noun pattern (deep_research, rag_search) with backend suffixes (_ddgs, _google). The generic deep_research lacks a suffix, which is a minor inconsistency, but overall the pattern is predictable.
With 5 tools, the count is reasonable for a search-and-research server. However, the shortcuts for specific backends could be eliminated by making the generic tools accept a backend parameter, so the count is slightly higher than necessary.
The deep_research tool supports many backends, but rag_search only supports DuckDuckGo and Google. Missing rag_search for other backends (e.g., Bing, Brave) is a notable gap. Additionally, there is no plain search tool without RAG scoring, which may be needed for some use cases.