MCP RAG Agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_REGION | No | AWS region for Bedrock, e.g., us-east-1. | |
| AWS_ACCESS_KEY_ID | No | AWS access key ID for Bedrock authentication. | |
| OLLAMA_CHAT_MODEL | No | Ollama chat model name, e.g., llama3.1. | |
| BEDROCK_CHAT_MODEL | No | Bedrock chat model ID, e.g., anthropic.claude-3-5-sonnet-20240620-v1:0. | |
| CLIENT_LLM_PROVIDER | No | LLM provider to use for chat generation. Options: ollama, bedrock. | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret access key for Bedrock authentication. | |
| OLLAMA_EMBEDDING_MODEL | No | Ollama embedding model name, e.g., nomic-embed-text. | |
| RAG_EMBEDDING_PROVIDER | No | Embedding provider for retrieval. Options: ollama, bedrock. | |
| BEDROCK_EMBEDDING_MODEL | No | Bedrock embedding model ID, e.g., amazon.titan-embed-text-v2:0. |
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 |
|---|---|
| retrieve_documentsC | Retrieve relevant knowledge chunks. |
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
With only one tool, there is no possibility of confusion between tools.
The single tool name 'retrieve_documents' follows a clear verb_noun pattern and is descriptive, but there is no set of tools to evaluate consistency.
A RAG agent typically requires multiple tools (e.g., retrieval and generation). A single tool is too few for the stated purpose.
The tool set covers only retrieval, missing essential capabilities like generation or query processing for a RAG agent.