bioevidence-mcp
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 |
|---|---|
| healthA | Return stable service health metadata. |
| search_biomedical_evidenceC | Retrieve, score, group, and optionally summarize biomedical evidence. |
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 2 tools
The health and search tools serve completely different purposes—one for service health, the other for querying evidence—so there is no ambiguity.
One tool uses a short noun ('health'), while the other uses a verb_noun pattern with underscores ('search_biomedical_evidence'), showing inconsistent naming conventions.
With only two tools and one being a simple health check, the server feels underdeveloped for the domain of biomedical evidence retrieval, suggesting more tools are needed.
The search tool provides a broad query capability, but lacks supporting tools for retrieving specific evidence items, managing sources, or performing other typical operations in the domain.