easydocforms-mcp
OfficialClick on "Deploy 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., "@easydocforms-mcpImport the blank intake PDF at https://clinic.example.com/intake.pdf and create a fill link."
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.
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).
Related MCP server: atlas_mcp
Tools
Tool | What it does |
| Import a blank PDF intake form (async; requires blank-form attestation) |
| Poll an import until its template is ready |
| List the organization's active form templates |
| Mint a hosted URL where a patient fills the form |
| Submission metadata + answer count — never answers |
| Short-lived signed download URL for the completed PDF |
Install
go install github.com/easydocforms/easydocforms-mcp/cmd/easydocforms-mcp@latestYou'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:latestClaude Code
claude mcp add easydocforms --env EASYDOCFORMS_API_KEY=edfk_live_... -- easydocforms-mcpClaude Desktop (or any MCP client)
{
"mcpServers": {
"easydocforms": {
"command": "easydocforms-mcp",
"env": { "EASYDOCFORMS_API_KEY": "edfk_live_..." }
}
}
}Environment
Variable | Required | Purpose |
| yes |
|
| no | API base URL override |
Try it
With MCP Inspector:
EASYDOCFORMS_API_KEY=edfk_live_... npx @modelcontextprotocol/inspector easydocforms-mcpA 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 ./... -raceLicense
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Hosted MCP server for Anvil — fill & generate PDFs and run Etch e-signature packets for AI agents.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA comprehensive Model Context Protocol (MCP) server for medical document processing with advanced AI capabilities, including OCR, medical NER, local embeddings, and vector search.221 npm1MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that brings AI-powered search and conversation to your FHIR clinical documents.1MIT
- FlicenseNot gradedqualityDmaintenanceA local MCP server that extracts text-layer content from PDF files, enabling AI agents to inspect, extract text, outlines, and page content.-
- AlicenseAqualityCmaintenanceMCP server and CLI for detecting, redacting, and auditing PHI in medical text before it is sent to AI agents, with tools for scan, redact, audit, and validate operations.4MIT