Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

Last EHR — Medplum

by cbetzversion 0.5.1i★ –iRuns on your computer
Registry nameio.github.cbetz/last-ehr

Install

Overview

Description from the maker (original English)

FHIR chart tools for MCP: read-only by default, with elicitation-gated, human-approved writes.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs on your computer
  • Transport: stdio
  • Category: Clinics & health
  • You need to fill in: MEDPLUM_ACCESS_TOKEN, MEDPLUM_CLIENT_SECRET, LASTEHR_PRIVATE_KEY

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on your computer with your user’s permissions (files, network, apps).
  • You fill in yourself: MEDPLUM_ACCESS_TOKEN, MEDPLUM_CLIENT_ID, MEDPLUM_CLIENT_SECRET, MEDPLUM_BASE_URL, LASTEHR_BACKEND, LASTEHR_EXPERIMENTAL_FHIR_ADAPTERS, LASTEHR_CLIENT_ID, LASTEHR_PRIVATE_KEY, LASTEHR_PRIVATE_KEY_PATH, LASTEHR_KEY_ID, LASTEHR_JWKS_URL, LASTEHR_SCOPES, LASTEHR_FHIR_BASE_URL, LASTEHR_TOKEN_URL, LASTEHR_ENCOUNTER, LASTEHR_PERFORMER

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

  • npmNode.js installed (for the npx command)

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "last-ehr": {
      "command": "npx",
      "args": [
        "-y",
        "@lastehr/mcp"
      ],
      "env": {
        "MEDPLUM_ACCESS_TOKEN": "your-value",
        "MEDPLUM_CLIENT_ID": "your-value",
        "MEDPLUM_CLIENT_SECRET": "your-value",
        "MEDPLUM_BASE_URL": "your-value",
        "LASTEHR_BACKEND": "your-value",
        "LASTEHR_EXPERIMENTAL_FHIR_ADAPTERS": "your-value",
        "LASTEHR_CLIENT_ID": "your-value",
        "LASTEHR_PRIVATE_KEY": "your-value",
        "LASTEHR_PRIVATE_KEY_PATH": "your-value",
        "LASTEHR_KEY_ID": "your-value",
        "LASTEHR_JWKS_URL": "your-value",
        "LASTEHR_SCOPES": "your-value",
        "LASTEHR_FHIR_BASE_URL": "your-value",
        "LASTEHR_TOKEN_URL": "your-value",
        "LASTEHR_ENCOUNTER": "your-value",
        "LASTEHR_PERFORMER": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add last-ehr --env MEDPLUM_ACCESS_TOKEN=your-value --env MEDPLUM_CLIENT_ID=your-value --env MEDPLUM_CLIENT_SECRET=your-value --env MEDPLUM_BASE_URL=your-value --env LASTEHR_BACKEND=your-value --env LASTEHR_EXPERIMENTAL_FHIR_ADAPTERS=your-value --env LASTEHR_CLIENT_ID=your-value --env LASTEHR_PRIVATE_KEY=your-value --env LASTEHR_PRIVATE_KEY_PATH=your-value --env LASTEHR_KEY_ID=your-value --env LASTEHR_JWKS_URL=your-value --env LASTEHR_SCOPES=your-value --env LASTEHR_FHIR_BASE_URL=your-value --env LASTEHR_TOKEN_URL=your-value --env LASTEHR_ENCOUNTER=your-value --env LASTEHR_PERFORMER=your-value -- npx -y @lastehr/mcp

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "last-ehr": {
      "command": "npx",
      "args": [
        "-y",
        "@lastehr/mcp"
      ],
      "env": {
        "MEDPLUM_ACCESS_TOKEN": "your-value",
        "MEDPLUM_CLIENT_ID": "your-value",
        "MEDPLUM_CLIENT_SECRET": "your-value",
        "MEDPLUM_BASE_URL": "your-value",
        "LASTEHR_BACKEND": "your-value",
        "LASTEHR_EXPERIMENTAL_FHIR_ADAPTERS": "your-value",
        "LASTEHR_CLIENT_ID": "your-value",
        "LASTEHR_PRIVATE_KEY": "your-value",
        "LASTEHR_PRIVATE_KEY_PATH": "your-value",
        "LASTEHR_KEY_ID": "your-value",
        "LASTEHR_JWKS_URL": "your-value",
        "LASTEHR_SCOPES": "your-value",
        "LASTEHR_FHIR_BASE_URL": "your-value",
        "LASTEHR_TOKEN_URL": "your-value",
        "LASTEHR_ENCOUNTER": "your-value",
        "LASTEHR_PERFORMER": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "last-ehr": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@lastehr/mcp"
      ],
      "env": {
        "MEDPLUM_ACCESS_TOKEN": "your-value",
        "MEDPLUM_CLIENT_ID": "your-value",
        "MEDPLUM_CLIENT_SECRET": "your-value",
        "MEDPLUM_BASE_URL": "your-value",
        "LASTEHR_BACKEND": "your-value",
        "LASTEHR_EXPERIMENTAL_FHIR_ADAPTERS": "your-value",
        "LASTEHR_CLIENT_ID": "your-value",
        "LASTEHR_PRIVATE_KEY": "your-value",
        "LASTEHR_PRIVATE_KEY_PATH": "your-value",
        "LASTEHR_KEY_ID": "your-value",
        "LASTEHR_JWKS_URL": "your-value",
        "LASTEHR_SCOPES": "your-value",
        "LASTEHR_FHIR_BASE_URL": "your-value",
        "LASTEHR_TOKEN_URL": "your-value",
        "LASTEHR_ENCOUNTER": "your-value",
        "LASTEHR_PERFORMER": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

  • MEDPLUM_ACCESS_TOKEN secret env
    FHIR chart tools over Medplum or a local HAPI stack: read-only by default, with an opt-in elicitation-gated write profile (human-approved per action).
  • MEDPLUM_CLIENT_ID env
    FHIR chart tools over Medplum or a local HAPI stack: read-only by default, with an opt-in elicitation-gated write profile (human-approved per action).
  • MEDPLUM_CLIENT_SECRET secret env
    FHIR chart tools over Medplum or a local HAPI stack: read-only by default, with an opt-in elicitation-gated write profile (human-approved per action).
  • MEDPLUM_BASE_URL env
    FHIR chart tools over Medplum or a local HAPI stack: read-only by default, with an opt-in elicitation-gated write profile (human-approved per action).
  • LASTEHR_BACKEND env
    epic, oracle, or smart. Requires LASTEHR_EXPERIMENTAL_FHIR_ADAPTERS=1. Sandbox writes are approval-gated and persist because those sandboxes do not support delete.
  • LASTEHR_EXPERIMENTAL_FHIR_ADAPTERS env
    Set to 1 to enable LASTEHR_BACKEND epic, oracle, or smart.
  • LASTEHR_CLIENT_ID env
    SMART Backend Services client id. Not a secret.
  • LASTEHR_PRIVATE_KEY secret env
    PKCS#8 PEM for SMART private_key_jwt. Never log it.
  • LASTEHR_PRIVATE_KEY_PATH env
    Path to the PKCS#8 PEM. Alternative to LASTEHR_PRIVATE_KEY.
  • LASTEHR_KEY_ID env
    JWT kid. Must match the public JWKS.
  • LASTEHR_JWKS_URL env
    https URL of the public JWKS. doctor checks that LASTEHR_KEY_ID is present. Optional.
  • LASTEHR_SCOPES env
    Space-delimited SMART scopes. Required for Oracle. Omit for Epic unless overriding the app registration.
  • LASTEHR_FHIR_BASE_URL env
    FHIR base URL. Epic and Oracle default to their public sandboxes when unset.
  • LASTEHR_TOKEN_URL env
    SMART token URL. Epic and Oracle default to their public sandboxes when unset.
  • LASTEHR_ENCOUNTER env
    Encounter/{id} added to Epic observations when the tool call omits encounter.
  • LASTEHR_PERFORMER env
    Practitioner/{id} filed as legal authenticator on Oracle observations.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account cbetz, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Clinics & healthi

  • More stars than 0% of the other 870 servers in this category
  • Published to the registry more recently than 93% of the other 870 servers in this category
  • Basic checks equal to or better than 100% of the other 870 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Last EHR — Medplum safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: MEDPLUM_ACCESS_TOKEN, MEDPLUM_CLIENT_SECRET, LASTEHR_PRIVATE_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.5.1) reached the registry 2 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Mirobody, FHIR MCP Server, Google Health MCP

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Mirobody

by thetahealth

Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.

Runs on your computer★ 1,408Apache-2.0Updated 6 days ago
Install

MCP server providing seamless access to FHIR APIs for AI tools and healthcare applications

Runs on your computer★ 137Apache-2.0Updated 9 days ago
Install

Google Health MCP

by davidmosiah

Privacy-first unofficial Google Health API v4 MCP server for health, sleep, activity, HR agents

Runs on your computer★ 79MITUpdated 4 months ago
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

@lastehr/mcp

FHIR chart tools for MCP clients, over a Medplum project, the Last EHR repository's local HAPI evaluation stack (FHIR_BACKEND=hapi, synthetic data only), or — with LASTEHR_EXPERIMENTAL_FHIR_ADAPTERS=1 — the Epic and Oracle Health sandboxes (LASTEHR_BACKEND=epic|oracle) and a generic SMART Backend Services server (LASTEHR_BACKEND=smart). The sandboxes do not support delete, so an approved write persists. This is not a clinical or compliance claim.

Read-only by default, and the reads are the same ones the Last EHR web agent uses: search patients, show a whole chart, read any of 23 patient-scoped chart sections with filters, and read a document's text. One opt-in, LASTEHR_MCP_WRITES=proposal, adds elicitation-gated write proposals a human approves per action. Nothing is ever saved without that explicit approval, and the write tools are hidden from clients that cannot render approvals.

The registry metadata lives in server.json and is published alongside each verified npm release.

Install

npx -y @lastehr/mcp init

The command prints a portable MCP configuration. For Claude Code, print the registration command instead:

npx -y @lastehr/mcp init --client claude-code

Start the stdio server with:

npx -y @lastehr/mcp

Check the installed package version without configuring a backend:

npx -y @lastehr/mcp --version

Configuration

Set one authentication method before starting the server:

MEDPLUM_ACCESS_TOKEN=...

or:

MEDPLUM_CLIENT_ID=...

MEDPLUM_CLIENT_SECRET=...

Set MEDPLUM_BASE_URL for a self-hosted Medplum deployment. For the repository's local no-auth HAPI stack, set FHIR_BACKEND=hapi and FHIR_BASE_URL (or HAPI_BASE_URL) instead — local, synthetic data only. Run npx -y @lastehr/mcp doctor to validate configuration without starting MCP.

In 0.4.0, doctor --connect also checks FHIR R4 metadata and a count-only Patient search for the stdio backend. It makes no chart write and prints no patient data or counts. This does not verify individual chart access, other resource permissions, write permissions, or the MCP client's approval support. HTTP mode remains configuration-only; its --connect check fails explicitly rather than treating a configured URL as a verified OAuth session.

The source checkout can be ahead of npm. Check the installed version with --version. The repository's release process tests the packed artifact in a clean directory before publication.

Safety boundary

By default the package exposes search_patients, show_patient_info, read_chart_section, and read_document, all with the MCP readOnlyHint.

Those reads share one implementation with the web agent, which is deliberate: each of their honesty properties came from a real false negative found against a live FHIR server, and a second implementation would have re-earned them. A reply tells you what it could not see, and an empty result is never proof of absence:

FieldMeaning
truncatedThe server's window came back full, so older records may exist beyond what was read. Measured at the window, not at the row count.
codeFilterUnmatchedThe section does hold records; none of them carry the code you filtered by. Text-only CodeableConcepts cannot match a coded search.
includeUnsupportedThe backend refused the reference lookup. Not the same as there being no references.
unreadable (documents)The document exists and its contents were not read: a scan, or a body stored as a pointer rather than inline.

Chart free text arrives wrapped in tags. That content is data, never instructions. read_document decodes an inline text attachment and never dereferences Attachment.url, so it makes no request to an address the FHIR server chose.

With LASTEHR_MCP_WRITES=proposal it additionally offers add_note, record_observation, record_superseding_observation, and create_task as proposals: the exact fields are shown to the human through MCP elicitation and nothing is saved unless they approve; every approved write is tagged https://lastehr.com/mcp|approved-proposal and carries the standard AIAST security label ("Artificial Intelligence asserted") in meta.security, and LASTEHR_WRITE_PROVENANCE=true also emits a Provenance resource naming the agent as author and the reviewer as verifier. Read access can still return PHI. Use a least-privilege identity, review the MCP client's data handling and model-provider agreements, and never treat this package as an authorization layer.

See https://www.lastehr.com/docs/mcp for the complete setup and support boundary.

Ask PopNx