This server provides AI assistants with tools to search FDA public datasets for drug and medical device information via the openFDA API.
Drug Tools:
search_drug_adverse_events: Search FDA Adverse Event Reporting System (FAERS) data.
search_drug_labels: Search drug product labeling (SPL) information.
search_drug_ndc: Query the National Drug Code (NDC) directory.
search_drug_recalls: Find drug recall enforcement reports.
search_drug_approvals: Search the Drugs@FDA database for approved products.
search_drug_shortages: Query current drug shortage reports.
Device Tools:
search_device_510k: Search FDA 510(k) premarket clearance data.
search_device_classifications: Search FDA medical device classifications.
search_device_adverse_events: Search medical device adverse event (MDR) reports.
search_device_recalls: Search medical device recall enforcement reports.
Common Features:
Pagination via limit and skip parameters (up to 1,000 results per request).
Frequency counting with the count parameter for field-level aggregation.
Advanced querying using openFDA syntax (exact matches, date ranges, AND/OR logic).
Works without an API key (1,000 req/hr) or with a free FDA API key for higher limits (120,000 req/hr).
Designed for MCP-compatible AI assistants, providing clean JSON responses with metadata summaries over stdio.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@OpenFDA MCP Server What adverse events are reported for Ozempic?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Python Model Context Protocol (MCP) server that gives AI assistants access to the U.S. Food and Drug Administration's public datasets through the openFDA API. Query drug adverse events, product labeling, recalls, approvals, shortages, NDC directory data, and medical device regulatory information — all from your AI assistant.
Demo placeholder: a GIF or screenshot of the server answering a real query in Claude Desktop / the MCP Inspector belongs here. Not generated yet — this environment has no way to drive Claude Desktop or capture a screen. Add one under
docs/assets/and swap this callout forwhen available.
10 search tools covering drugs and medical devices
Async HTTP client built on httpx for fast, concurrent requests
Pagination and counting — skip/limit and field-level frequency counts out of the box
Optional API key — works without one (1k req/hr); set FDA_API_KEY for 120k req/hr
Clean JSON responses with metadata summaries for the LLM
Related MCP server: OpenFDA MCP Server
Tool | Description |
| Search FDA Adverse Event Reporting System (FAERS) data |
| Search drug product labeling (SPL) information |
| Query the National Drug Code (NDC) directory |
| Find drug recall enforcement reports |
| Search the Drugs@FDA database for approved products |
| Query current drug shortage reports |
Tool | Description |
| Search FDA 510(k) premarket clearance data |
| Search FDA medical device classifications |
| Search medical device adverse event (MDR) reports |
| Search medical device recall enforcement reports |
pixi (recommended) or Python 3.11+
git clone https://github.com/colbyw5/openfda-mcp-server.git
cd openfda-mcp-server
pixi installpip install -e .All tools work without an API key, but you'll be limited to 1,000 requests per hour. For higher limits:
Get a free API key at open.fda.gov/apis/authentication
Copy the example env file and add your key:
cp .env.example .env
# edit .env and paste your keyThe server loads .env automatically on startup via python-dotenv. Alternatively, set the environment variable directly:
export FDA_API_KEY="your-key-here"pixi run serve
# or
openfda-mcp-serverThe server communicates over stdio, designed for use with MCP-compatible AI assistants.
{
"mcpServers": {
"openfda": {
"command": "pixi",
"args": ["run", "serve"],
"cwd": "/path/to/openfda-mcp-server",
"env": {
"FDA_API_KEY": "your-key"
}
}
}
}Claude Desktop launches MCP servers as a GUI process, which doesn't inherit your shell's PATH or working directory. Use an absolute path to the pixi binary and --manifest-path instead of cwd:
{
"mcpServers": {
"openfda": {
"command": "/opt/homebrew/bin/pixi",
"args": [
"run",
"--manifest-path",
"/path/to/openfda-mcp-server/pixi.toml",
"serve"
],
"env": {
"FDA_API_KEY": "your-key"
}
}
}
}Find your pixi binary path with which pixi if it's not at /opt/homebrew/bin/pixi (e.g. /usr/local/bin/pixi on Intel Macs, or ~/.pixi/bin/pixi).
Once connected, your AI assistant can answer questions like:
"What adverse events have been reported for Ozempic?"
"Show me Class I drug recalls from the past year"
"Look up the NDC codes for metformin"
"What 510(k) clearances has Medtronic received for cardiac devices?"
"Are there any current drug shortages for antibiotics?"
All tools accept a search parameter using openFDA query syntax:
# Exact match
patient.drug.openfda.brand_name:"aspirin"
# Date range
receivedate:[20240101+TO+20241231]
# AND / OR
openfda.brand_name:"lipitor"+AND+serious:1
# Count a field (returns frequency data instead of records)
count=patient.reaction.reactionmeddrapt.exactYour MCP client (Claude Desktop, Claude Code, etc.) talks to this server over stdio using the MCP protocol. The FastMCP server (server.py) dispatches each tool call to a handler in tools.py, which uses an async httpx client (client.py) to query the openFDA REST API and formats the JSON response for the LLM.
MCP client ⇄ (stdio) ⇄ FastMCP server ⇄ async httpx client ⇄ openFDA REST APIFAERS and other openFDA datasets are spontaneous reports, not incidence rates. There is no denominator (total exposed population), so you cannot compute risk or incidence from report counts alone — only relative frequency within the dataset. Keep in mind:
Report volume reflects reporting behavior, not risk. Counts are inflated by prescription volume, time on market, and media/litigation attention, independent of any actual safety signal.
A single report can list multiple reactions. Reaction counts don't sum to the number of reports, and one severe report can contribute many reaction terms.
Duplicate reports exist in FAERS (the same case reported by both a patient and a provider, for example) and are not fully deduplicated by the API.
Raw frequency is not signal detection. Real pharmacovigilance signal detection uses disproportionality measures — Proportional Reporting Ratio (PRR) or Reporting Odds Ratio (ROR) — comparing a drug/event pair against a comparator, not raw counts. See examples/prr_example.py for a worked calculation.
The data is CC0 public domain — no attribution is legally required — but every tool response includes openFDA's disclaimer, which is worth reading: do not rely on this data to make medical care decisions; assume all results are unvalidated. See openFDA's terms of service for full details.
examples/prr_example.py computes a Proportional Reporting Ratio (PRR) for an adverse reaction between two drugs, using live FAERS report counts:
pixi run python examples/prr_example.py --drug ozempic --comparator victoza --reaction nauseaIt prints the underlying report counts, the PRR, a plain-language interpretation, and the caveats that apply to it (see Data caveats & limitations above — this is an unadjusted, single-comparator calculation, not a validated signal-detection result).
pixi run test # run tests
pixi run lint # lint with ruff
pixi run fmt # format with ruff
pixi run typecheck # type check with pyrightopenfda-mcp-server/
├── pixi.toml # environment and task config
├── pyproject.toml # package metadata
└── src/openfda_mcp_server/
├── client.py # async httpx client for openFDA API
├── server.py # FastMCP server entry point
└── tools.py # MCP tool definitions and handlersSearch FDA 510(k) premarket clearance data for medical devices.
Args: search: openFDA query (e.g. 'applicant:"medtronic"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description implies read-only search but does not disclose rate limits, authentication needs, or data update frequency. 'Search' suggests safe operation, but lacks explicit behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise with a front-loaded purpose and parameter explanations. Six lines total, each informative. Could be slightly more streamlined but no unnecessary content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists, so return value explanation not required. Parameter details are adequate for use. However, missing context on API limits or error handling, but given tool complexity, it is reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but description adds meaning to each parameter: e.g., search is an 'openFDA query' with example, limit has range (1-1000), skip is pagination offset, count is 'Field to count'. Adds value beyond schema types and defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Search' and resource 'FDA 510(k) premarket clearance data'. Distinguishes from sibling tools that target other drug/device data types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description specifies the data source (510k) and provides an example query, implying usage for that specific data type. However, it does not explicitly contrast with sibling tools like search_device_classifications or search_device_adverse_events.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search FDA medical device adverse event (MDR) reports.
Args: search: openFDA query (e.g. 'device.brand_name:"insulin pump"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It explains parameters and provides an example query, which adds some behavioral context beyond the schema. However, it does not disclose whether the tool is read-only, any rate limits, or auth requirements—leaving gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded: a clear purpose sentence followed by a bulleted Args list. Every sentence adds value, and there is no redundancy or wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (search with 4 optional params) and the presence of an output schema, the description is fairly complete. It covers the purpose, param details, and example. A minor omission: no explanation of pagination beyond skip/limit, but this is adequately implied.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. The Args section adds meaningful explanations: 'search: openFDA query (e.g. ...)', 'limit: Max results (1-1000)', 'skip: Offset for pagination', 'count: Field to count'. These go beyond the schema's titles and types, providing clear semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Search') and resource ('FDA medical device adverse event (MDR) reports'). It distinguishes from sibling tools by focusing on medical device adverse events, not drugs or other device categories.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context (searching adverse events) but does not provide explicit guidance on when to use vs. alternatives, such as 'Use this for MDR reports; for drug adverse events, use search_drug_adverse_events.' No exclusions or when-not-to-use are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search FDA medical device classifications.
Args: search: openFDA query (e.g. 'medical_specialty_description:"cardiovascular"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided and description only states 'Search' without revealing behavioral traits like idempotency, rate limits, or potential side effects. Since annotations are absent, the description carries the full burden but fails to add behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise: one-line header then bulleted parameters. No fluff. Front-loaded with purpose. Could be slightly improved by including defaults or a brief usage example inline.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for basic use but missing usage context (e.g., which sibling to choose), error handling info, or prerequisites. Output schema exists so return values are covered elsewhere, but the agent would benefit from more guidance on query formatting.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, but the description's Args section explains each parameter (search, limit, skip, count) with clear semantics and examples, adding significant meaning beyond the raw schema types.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Search FDA medical device classifications' – a specific verb and resource. Distinguishes from sibling tools like search_drug_ndc or search_device_510k by specifying 'device classifications'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides an example query but no explicit advice on when to use this tool vs. siblings (e.g., drug search tools or other device searches). Usage is implied but not guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search FDA medical device recall enforcement reports.
Args: search: openFDA query (e.g. 'classification:"Class I"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries burden. Discloses pagination (limit, skip) and counting capability, but does not explicitly state it is read-only or mention any potential side effects, rate limits, or authentication needs. The 'search' parameter hints at FDA API query syntax but does not specify behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise: one-line purpose followed by parameter explanations. No unnecessary text. Front-loaded with purpose, then parameter details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists, so return value documentation is covered externally. Description adequately documents input parameters. Could optionally mention that it is read-only or reference the FDA recall report source, but not strictly necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% according to context, meaning the schema only provides titles and defaults. The description adds essential meaning: explains that 'search' is an openFDA query, 'limit' caps at 1000, 'skip' is for pagination, and 'count' is for field counting. This greatly enhances usability beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Search FDA medical device recall enforcement reports', providing a specific verb and resource. It clearly distinguishes from sibling tools like 'search_drug_recalls' and other device searches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Does not mention sibling tools or provide context for when this search is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search FDA Adverse Event Reporting System (FAERS) data.
Args: search: openFDA query (e.g. 'patient.drug.openfda.brand_name:"aspirin"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count (returns frequency counts instead of records).
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description adequately discloses key behaviors: the 'count' parameter returns frequency counts instead of records, and parameters like limit (1-1000) and skip (offset) imply pagination. However, it does not mention rate limits, authentication, or data freshness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear lead sentence followed by a concise parameter list. Each sentence adds value without redundancy, making it easy to scan for an AI agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema, the description reasonably omits return details. It covers all parameters, includes an example query, and notes the 'count' behavioral switch. Minor missing info on required fields or advanced query syntax, but overall adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description provides clear, explanatory text for each parameter: an example query for 'search', range for 'limit', purpose of 'skip', and the special frequency behavior of 'count'. This adds critical meaning beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches FDA Adverse Event Reporting System (FAERS) data, which is a specific verb-resource pair that distinguishes it from sibling tools like search_drug_ndc or search_drug_labels.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance is provided on when to use this tool versus its siblings (e.g., adverse events vs. drug labels). The description lacks 'when-not-to-use' or alternative suggestions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Drugs@FDA database for approved drug products.
Args: search: openFDA query (e.g. 'openfda.brand_name:"keytruda"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states that it searches a database; it does not mention read-only nature, rate limits, authentication needs, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief with a clear main sentence and a structured list for parameters. No unnecessary words, though the parameter list could be formatted more clearly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers basic purpose and parameter semantics, but given the existence of an output schema (not shown), it does not need to detail returns. However, it lacks information on authentication, rate limits, or constraints, which is acceptable for a simple search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description carries full burden. It adds an example openFDA query, a range for limit (1-1000), pagination explanation for skip, and the purpose of count. This goes beyond the schema's defaults and types.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search the Drugs@FDA database for approved drug products,' using a specific verb and resource. It distinguishes itself from siblings that target other FDA databases (NDC, adverse events, labels, etc.).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides parameter details but no explicit when-to-use or when-not-to-use guidance. While siblings cover different domains, the description does not point out when to choose this tool over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search drug product labeling (SPL) information.
Args: search: openFDA query (e.g. 'openfda.brand_name:"lipitor"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It explains parameter behavior (search query format, limit, skip, count) but does not disclose return format, pagination behavior, rate limits, or whether the tool is read-only/destructive. The output schema exists but is not referenced.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: one sentence for purpose plus a clear bulleted list for parameters. Every sentence adds value, and the structure is front-loaded with the main action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 4 parameters and an output schema, the description covers parameter usage well with examples. It omits response structure and error handling, but output schema exists. Given the sibling tools, some guidance on when to use this tool would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description fully compensates. Each parameter is explained with purpose and an example for 'search'. This adds essential meaning beyond the schema's type/default fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search drug product labeling (SPL) information', specifying the verb (search) and resource (drug labeling). It distinguishes from siblings like search_drug_ndc, search_drug_adverse_events, etc., because SPL is a unique domain within FDA data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus its siblings (e.g., when to search labeling vs NDC or adverse events). The description only explains parameters without context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the National Drug Code (NDC) directory.
Args: search: openFDA query (e.g. 'brand_name:"tylenol"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It implies a read-only search but does not explicitly state safety, side effects, or rate limits. The parameter explanations add some behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise, front-loading the purpose, then listing parameters. No redundant sentences. Could be slightly improved by grouping parameters differently, but it's efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search tool with an output schema, the description covers the key query parameters. It does not detail return values, but the output schema presumably handles that. Overall sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description explains all four parameters (search, limit, skip, count) with examples and defaults, adding significant meaning beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search the National Drug Code (NDC) directory.', which is a specific verb and resource. It distinguishes from sibling tools that search other drug-related databases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus siblings like search_drug_labels or search_drug_adverse_events. The description does not mention any context or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search drug recall enforcement reports.
Args: search: openFDA query (e.g. 'classification:"Class I"'). limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether the tool is read-only, destructive, or has rate limits. It only describes the parameters, leaving the agent uninformed about side effects or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a one-line purpose followed by bullet-pointed parameter explanations. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters with 0% schema coverage and no annotations, the description adequately covers parameter semantics but lacks usage guidelines and behavioral context. Output schema exists, so return values need not be described. Overall, it is minimally complete but has gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description carries full burden. It explains each parameter: search (openFDA query), limit (max results), skip (offset), count (field to count), adding meaning beyond the plain schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the function: 'Search drug recall enforcement reports.' This is a specific verb (Search) and resource (drug recall enforcement reports), distinguishing it from sibling tools like search_drug_ndc or search_drug_adverse_events.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It merely lists parameters without any context about use cases, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search current FDA drug shortage reports.
Args: search: openFDA query. limit: Max results (1-1000). skip: Offset for pagination. count: Field to count.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| count | No | ||
| limit | No | ||
| search | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden of transparency. It only states 'search' without disclosing read-only nature, rate limits, data freshness, or any side effects. The minimal description fails to inform the agent about important behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: one sentence for purpose and four lines for parameters. Information is front-loaded, and every sentence earns its place without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 4 parameters (0 required) and an output schema, the description covers the basics but lacks examples, query format, or field details for 'count'. The tool's purpose is clear, but the agent may need more context to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has no parameter descriptions (0% coverage), so the description adds basic meaning: 'search: openFDA query', 'limit: Max results (1-1000)', 'skip: Offset for pagination', 'count: Field to count'. While helpful, the description for 'count' is vague (which fields are valid?) and 'search' assumes knowledge of 'openFDA query' syntax.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Search current FDA drug shortage reports.' The verb 'search' and specific resource 'current FDA drug shortage reports' differentiate it from sibling tools like search_drug_ndc or search_drug_adverse_events.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no usage guidance, such as when to use this tool versus alternatives like search_drug_recalls or search_drug_approvals. There are no prerequisites, exclusions, or context hints for the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0search_device_510ksearch_device_adverse_eventssearch_device_classificationssearch_device_recallssearch_drug_adverse_eventssearch_drug_approvalssearch_drug_labelssearch_drug_ndcsearch_drug_recallssearch_drug_shortagesEach tool targets a distinct FDA dataset (e.g., NDC, adverse events, labels, recalls, approvals, shortages, 510(k), classifications) with no overlap in purpose. Descriptions clearly differentiate the endpoints.
All tools follow a consistent 'search_{domain}_{dataset}' pattern (e.g., search_drug_ndc, search_device_recalls), making it predictable and easy to navigate.
With 10 tools, the server covers the major FDA drug and device datasets without being too sparse or overwhelming. It is well-scoped for the intended domain.
The tool set covers key FDA drug endpoints (NDC, adverse events, labels, recalls, approvals, shortages) and device endpoints (510(k), classifications, adverse events, recalls). Few major gaps exist for the core OpenFDA query use cases.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Hosted MCP server exposing US hospital procedure cost data to AI assistants
OpenFDA MCP — wraps the openFDA API (free, no auth required)
FDA MCP — US Food and Drug Administration public API (free, no auth)
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/colbyw5/openfda-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
