MCP RAG
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_MODEL | No | Model name | gpt-4o-mini |
| OPENAI_API_KEY | Yes | API key for OpenAI or Doubao | |
| OPENAI_API_BASE | No | API base URL | https://api.openai.com/v1 |
| OPENAI_TEMPERATURE | No | Temperature for model | 0 |
| OPENAI_EMBEDDING_MODEL | No | Embedding model name | text-embedding-3-large |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_ragB | 用户想查询已有资料或者需要知识库时调用 |
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 1 tool
Only one tool exists, so there is no risk of ambiguity between tools. The tool's purpose is clear enough for an agent to identify when to use it.
The single tool name 'ask_rag' follows a clear verb_noun convention, which is consistent even with only one tool.
A RAG server typically requires tools for managing the knowledge base (add, delete, list) in addition to querying. Having only one tool is too few for the apparent scope of a RAG server.
The server only supports querying an existing knowledge base, with no way to ingest, update, or manage documents. This leaves significant gaps in the RAG workflow.