Documentation

Connect the FDA record to your agent.

Connect once, start with a company-level manufacturing and compliance summary, then drill into inspections, warning letters, OII records, facilities, import risk, and product data as needed.

01Access

Authentication

Provision a key on /signup. Pass it in the Authorization header for HTTP clients, or as the apiKey query parameter for claude.ai connectors. Persist the session id returned by initialize for the life of the connection.

HTTP headers

Authorization: Bearer fda_...

# Persist the session id returned by initialize:
Mcp-Session-Id: <session_id>

02First call

Start here

Evaluating a company for manufacturing, compliance, diligence, or account research? Start with fda_manufacturing_risk_summary, then follow the trail.

Start with fda_manufacturing_risk_summary when you need a fast company-level view.
Use fda_facility_dossier when you already know the FEI and want the local compliance story fast.
Use fda_company_compliance_timeline when you want one dated event stream across inspections, warning letters, import risk, and recalls.
Use inspections, citations, warning letters, OII, import alerts, and debarments after the workflow tools when you need raw evidence.
Use product, label, approval, shortage, and recall tools after you know which business unit or facility you care about.

Prompt

“Give me a manufacturing risk summary for Pfizer.”

Prompt

“Summarize recent warning letters, inspections, and import alerts for Moderna.”

Prompt

“Show manufacturing risk summary plus recent OII records for Thermo Fisher.”

03Setup

Connect your client

RegDataLab speaks the Model Context Protocol over one HTTP endpoint. Start with claude.ai for a zero-install connection, or wire it into Claude Desktop, Claude Code, Cursor, ChatGPT, or your own pipeline. Replace YOUR_KEY with the key from /signup.

Connect in claude.ai (no install)

The fastest path — nothing to install, works in any modern browser.

01Open claude.ai → Settings → Connectors → Add custom connector
02Paste this URL as the connector endpoint, then save

Connector URL

https://www.regdatalab.com/mcp?apiKey=YOUR_KEY

Treat the URL like a password — it carries your key. Anyone who has it can spend your credits.

Claude Desktop

Uses the mcp-remote wrapper over stdio. Add this to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json

{
  "mcpServers": {
    "regdatalab": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://www.regdatalab.com/mcp",
        "--header", "Authorization: Bearer YOUR_KEY"
      ]
    }
  }
}

Claude Code

One command, native HTTP transport, no local wrapper required.

Terminal

claude mcp add regdatalab https://www.regdatalab.com/mcp \
  --transport http \
  --header "Authorization: Bearer YOUR_KEY" \
  --scope user

Cursor

Native HTTP transport. Add this to ~/.cursor/mcp.json.

~/.cursor/mcp.json

{
  "mcpServers": {
    "regdatalab": {
      "url": "https://www.regdatalab.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_KEY" }
    }
  }
}

ChatGPT / OpenAI

Pass RegDataLab as an MCP tool in the OpenAI Responses API.

Python

from openai import OpenAI
client = OpenAI()

resp = client.responses.create(
    model="gpt-4.1",
    tools=[{
        "type": "mcp",
        "server_label": "regdatalab",
        "server_url": "https://www.regdatalab.com/mcp",
        "headers": {
            "Authorization": "Bearer YOUR_KEY"
        }
    }],
    input="Look up Pfizer's FDA facilities",
)

Team sharing (.mcp.json)

Drop this in your project root for team-wide access, with the key resolved from an environment variable.

.mcp.json

{
  "mcpServers": {
    "regdatalab": {
      "type": "http",
      "url": "https://www.regdatalab.com/mcp",
      "headers": {
        "Authorization": "Bearer ${REGDATALAB_API_KEY}"
      }
    }
  }
}

Troubleshooting

Tools not showing after setup: Restart the client after editing its config, then confirm regdatalab appears in the connector or MCP server list.
Invalid API key: Confirm the Bearer token is the full key from /signup with no spaces or line breaks. For claude.ai connectors, the apiKey in the URL must match.
npx or mcp-remote not found: Install Node.js, then test the wrapper directly: npx -y mcp-remote https://www.regdatalab.com/mcp --header "Authorization: Bearer YOUR_KEY"
Session expired: Re-initialize by restarting the client. Most clients handle session renewal automatically.

04Practice

Search tips

Better matching

Use the most canonical company name you know first, then confirm aliases or subsidiaries before widening the search.
For large parents, drill down into a specific subsidiary, brand, FEI, or geography when broad name matching brings back noise.
Avoid firing many heavy tools in parallel until you know which company entity and question you actually want to pursue.
If a result looks off, compare it against facilities, aliases, and recent compliance evidence before trusting the match.

Credits & pacing

Credits are consumed per successful tool call, so broad parallel research can burn through a free key quickly.
When credits are exhausted the API returns HTTP 402 with a no_credits-style error instead of silently failing.
New keys start with 50 credits at signup; verify your email to unlock 300 credits a month, at 60 requests per minute.

05Audience

Who it helps

Positioned manufacturing-first, but the same data layer serves broader workflows once the core company and facility questions are answered.

Manufacturing and quality teamsResearchersJournalistsInvestorsSales teams

06Reference

Tool reference

48 MCP tools, organized by category. Start with the manufacturing summary for a fast company view, then reach for the drill-down tools when you need raw evidence.

01Start Here

fda_manufacturing_risk_summary Best first tool for a company-level manufacturing and compliance summary across inspections, warning letters, OII records, import risk, debarments, facilities, and recalls.

13Manufacturing & Compliance

`fda_inspections`	Search FDA inspections with NAI, VAI, and OAI outcomes by company, FEI, date, and geography.
`fda_citations`	Search inspection citations and CFR findings tied to facilities and companies.
`fda_compliance_actions`	Search warning letters, seizures, and injunctions from FDA compliance dashboards.
`fda_search_warning_letters`	Search FDA warning letters with text, excerpts, dates, and issuing office context.
`fda_search_oii_records`	Search OII reading-room records, including machine-readable inspection and compliance documents.
`fda_search_debarments`	Search FDA debarment records and integrity-related exclusions.
`fda_search_import_alerts`	Search import alerts, red-list and green-list placements, and linked firms.
`fda_search_opdp_untitled_letters`	Search OPDP untitled letters for pharma promotional and commercial compliance issues.
`fda_bpdr_summary`	Review BPDR annual summary data for biologics manufacturing and quality signal context.
`fda_device_supply_status`	Check device supply disruption and shortage signals for medtech manufacturing monitoring.
`fda_inspection_observation_summary`	Review annual inspection observation summary trends and common citation patterns.
`fda_import_refusals`	Search import refusal records by company, FEI, country, category, and date.
`fda_ires_enforcement`	Search iRES enforcement and recall records from FDA internet Recall Enterprise System data.

12Company & Facility Intelligence

`fda_lookup_company`	Quick company view across facilities, enforcement history, and alias resolution.
`fda_search_facilities`	Search FDA facilities by company, location, and operating context.
`fda_get_facility`	Open a detailed facility record by FEI, including linked enforcement context.
`fda_facility_products`	List products and classifications linked to a facility.
`fda_resolve_company`	Resolve a company to its normalized aliases and canonical record.
`fda_save_aliases`	Save alias mappings for a parent company when you need cleaner future matching.
`fda_suggest_subsidiaries`	Suggest likely subsidiaries and brand/entity relationships from FDA and EDGAR-style evidence.
`fda_company_full`	Pull a broader company profile across facilities, recalls, approvals, and drug/device coverage.
`fda_company_compliance_timeline`	One reverse-chronological event stream across inspections, warning letters, import risk, debarments, and recalls.
`fda_facility_dossier`	Full compliance dossier for one facility by FEI: inspections, citations, warning letters, recalls, and import risk in a single call.
`fda_search_family_facilities`	Map a company's entire manufacturing footprint across its resolved corporate family.
`fda_link_subsidiaries`	Link confirmed subsidiaries to a parent company so future lookups roll them up automatically.

12Products, Approvals & Labels

`fda_search_510k`	Search FDA 510(k) clearances by company, product code, and decision details.
`fda_search_pma`	Search FDA PMA approvals by company, product code, and decision window.
`fda_search_drugs`	Search Drugs@FDA applications, brand names, and submission status.
`fda_search_ndc`	Search the NDC directory by labeler, brand, or application number.
`fda_search_nsde`	Search National Standard Drug Element records by name, package NDC, and application number.
`fda_search_by_product`	Search across drug and device product-oriented datasets by product name.
`fda_device_class`	Look up device classification details by product code.
`fda_product_code_lookup`	Cross-reference a product code across classification, 510(k), and PMA data.
`fda_clinical_result_letters`	Search Complete Response Letters and related FDA transparency records.
`fda_drug_labels`	Search SPL drug labels, sections, manufacturers, and application references.
`fda_device_udi`	Search the FDA UDI dataset for device identifiers, companies, and product codes.
`fda_device_udi_lookup`	Look up GUDID-style UDI records directly.

10Recalls, Safety & Specialty

`fda_search_enforcement`	Search recall and enforcement actions across drug, device, and food records.
`fda_search_recall_text`	Search recall reason text and product descriptions across enforcement records.
`fda_recall_facility_trace`	Trace recalls back to likely facilities and manufacturing entities.
`fda_drug_shortages`	Search active and resolved FDA drug shortages.
`fda_device_recalls`	Search device recall records with firm, product code, and status filters.
`fda_consumer_events`	Search food and cosmetic adverse events.
`fda_vet_events`	Search veterinary adverse event records.
`fda_tobacco_problems`	Search tobacco product problem reports and health issues.
`fda_substance_lookup`	Look up FDA substance and UNII data by code or name.
`fda_search_aphis`	Search APHIS veterinary biologics establishments and related references.

07Limits

Rate limits

Rate limits are enforced per API key. Each key defaults to 60 requests per minute. When exceeded, the API returns HTTP 429 with the reset window in the response headers.

Response headers

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 42
X-RateLimit-Reset: 1708905600

08Failure

Errors

Errors use standard HTTP codes with JSON payloads.

`401 / 403`	Authentication failure — invalid or missing API key.
`402`	Credits exhausted — top up, upgrade, or wait for the monthly reset.
`429`	Rate limit exceeded — retry after the reset window.
`500`	Internal error — retry or contact support.

09Provenance

Data sources

RegDataLab ingests openFDA bulk downloads, DECRS facility data, FDA Dashboard compliance feeds, warning letters, OII reading-room records, import alerts, debarments, APHIS veterinary biologics data, and iRES enforcement reports. Each dataset is normalized with provenance metadata including source, ingested_at, and run_id.

{ "mcpServers": { "regdatalab": { "command": "npx", "args": [ "-y", "mcp-remote", "https://www.regdatalab.com/mcp", "--header", "Authorization: Bearer YOUR_KEY" ] } } }

from openai import OpenAI client = OpenAI() resp = client.responses.create( model="gpt-4.1", tools=[{ "type": "mcp", "server_label": "regdatalab", "server_url": "https://www.regdatalab.com/mcp", "headers": { "Authorization": "Bearer YOUR_KEY" } }], input="Look up Pfizer's FDA facilities", )