mcp-openfda
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_drug_labelsB | Search FDA drug labels using OpenFDA API. Returns drug labeling information including indications, contraindications, warnings, and adverse reactions. |
| get_drug_adverse_reactionsB | Get adverse reactions information for a specific drug from FDA labels |
| get_drug_warningsC | Get warnings and precautions for a specific drug from FDA labels |
| ae_pipeline_ragC | Advanced RAG pipeline for drug safety analysis. Fetches, extracts, chunks, retrieves and summarizes FDA drug label data in one call to prevent LLM response truncation. |
| get_drug_indicationsA | Get indications and usage information for a specific drug from FDA labels |
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
Most tools have clear, distinct purposes: get_drug_adverse_reactions, get_drug_warnings, and get_drug_indications target specific label sections, while search_drug_labels provides broad search. However, search_drug_labels overlaps with the section-specific tools, and ae_pipeline_rag also covers drug label data, creating minor ambiguity.
Three tools follow a consistent get_drug_<section> pattern (get_drug_adverse_reactions, get_drug_warnings, get_drug_indications), but search_drug_labels and ae_pipeline_rag deviate from this pattern. The convention is mostly consistent, with two outliers.
Five tools is well-scoped for a focused FDA drug label API server. Each tool serves a clear purpose without unnecessary bloat, making the count appropriate.
The set covers common drug label sections (indications, warnings, adverse reactions) and provides search and RAG capabilities, but omits other important sections like contraindications, dosage, or interactions. There's no direct tool for retrieving the full label, which is a notable gap.