easydocforms-mcp
An MCP server for healthcare intake forms that lets AI agents import blank PDFs, create patient fill links, and retrieve completed PDFs while keeping PHI out of the model context.
README
easydocforms-mcp
An MCP server for healthcare intake forms: give an AI agent the ability to turn a blank PDF intake packet into a hosted, mobile-friendly fillable form, hand the patient a link, and retrieve the completed, pixel-exact PDF — without any PHI ever entering the agent's context.
Built on EasyDocForms, whose document-understanding pipeline (field detection, checkbox semantics, consent blocks, signature models) runs healthcare intake in production. This server wraps the Partner API via the easydocforms-go SDK.
The PHI boundary (read this first)
This server is designed so protected health information never passes through the model:
- Imports are blank forms only.
import_pdf_from_urlrequiresblank_form_attestation: trueand takes a URL, never document bytes. get_submissionreturns metadata and an answer count — never the patient's answers. Answers stay server-side, behind your API key.get_completed_pdf_linkreturns a ~10-minute signed URL the agent can hand to a human or an EMR without exposing your API key. Treat it like a fax.external_refmust never contain PHI — it's an opaque correlation id (your visit or order number).
Tools
| Tool | What it does |
|---|---|
import_pdf_from_url |
Import a blank PDF intake form (async; requires blank-form attestation) |
get_import_status |
Poll an import until its template is ready |
list_templates |
List the organization's active form templates |
create_fill_link |
Mint a hosted URL where a patient fills the form |
get_submission |
Submission metadata + answer count — never answers |
get_completed_pdf_link |
Short-lived signed download URL for the completed PDF |
Install
go install github.com/easydocforms/easydocforms-mcp/cmd/easydocforms-mcp@latest
You'll need an API key from the EasyDocForms app: Settings → Integrations → Partner API (shown exactly once).
Or run the Docker image (no Go toolchain needed):
docker run -i --rm -e EASYDOCFORMS_API_KEY=edfk_live_... ghcr.io/easydocforms/easydocforms-mcp:latest
Claude Code
claude mcp add easydocforms --env EASYDOCFORMS_API_KEY=edfk_live_... -- easydocforms-mcp
Claude Desktop (or any MCP client)
{
"mcpServers": {
"easydocforms": {
"command": "easydocforms-mcp",
"env": { "EASYDOCFORMS_API_KEY": "edfk_live_..." }
}
}
}
Environment
| Variable | Required | Purpose |
|---|---|---|
EASYDOCFORMS_API_KEY |
yes | edfk_live_* Partner API key |
EASYDOCFORMS_BASE_URL |
no | API base URL override |
Try it
With MCP Inspector:
EASYDOCFORMS_API_KEY=edfk_live_... npx @modelcontextprotocol/inspector easydocforms-mcp
A typical agent session: "Import the intake form at https://clinic.example.com/forms/new-patient.pdf (it's blank), then give me a fill link for visit 8675309." The agent imports, polls, mints a link with external_ref: "visit-8675309", and hands back a URL. After the patient submits, "Is the PDF for that visit ready?" → get_submission + get_completed_pdf_link.
Transport
stdio only, credentials from the environment — per the MCP spec's guidance for locally-run servers. A hosted remote variant (Streamable HTTP + OAuth 2.1) is planned as a second wave.
Development
go test ./... -race
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.