Healthcare
Metriport MCP connector
The Metriport connector lets Claude, ChatGPT, Cursor, and the Elaichi Agent register patients, request medical record summaries, run document queries, and manage facilities and cohorts in Metriport, each person signed in as themselves, every action logged.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Metriport to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Metriport once
-
Open Connections, choose Add connection, and pick Metriport.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Metriport API key. One person generates a token in Metriport and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect Metriport to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect Metriport to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect Metriport to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Metriport to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Metriport through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Intake
Register a new patient before their visit
Add a patient to Metriport with their demographics and the facility they are being seen at, so their outside records can start being gathered before they arrive.
-
Care coordination
Pull a medical record summary for a referral
Ask for a patient's consolidated medical record summary in Metriport and check whether it is ready, so the referring notes, medications, and history are in hand before the appointment.
-
Clinical operations
Check on a record query that is still running
Start a document query for a patient and ask how far along it is, instead of refreshing a dashboard while a clinician waits.
-
Health information management
Find the right patient and avoid duplicates
Match a person against existing Metriport patients, look them up by the ID from your own system, and fix demographics on the record without creating a second one.
-
Population health
Group patients into a cohort for outreach
Add a list of patients to a cohort in Metriport, see which cohorts a patient already belongs to, and keep treatment relationships current as a panel changes.
-
Practice administration
Keep facilities and rosters up to date
Add a new clinic location, update its details, and bulk create or update patients when a practice or a batch of new patients joins.
Try asking
- “Show Metriport patients added to cohorts this week.”
- “Get the medical record summary for patient 4821.”
- “Which facilities are set on our newest Metriport patients?”
AI tools
Metriport tools for your AI agents
61 tools are ready to call through Elaichi's MCP endpoint the moment you connect Metriport, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Metriport gets you
6 screens from the product, each doing one job for your Metriport account.
The agent
Ask about patients and read the answer.
Plain language questions return live Metriport patients, cohorts and facilities.
- patients
- cohorts
- facilities
- medical record summaries
Ask Elaichi to work across your apps.
Show Metriport patients added to cohorts this week.
Get the medical record summary for patient 4821.
Which facilities are set on our newest Metriport patients?
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor share one endpoint.
Every client reaches Metriport over OAuth, with no SDK and no shared key.
Copy the endpoint
Tool catalog
61 Metriport tools arrive ready to call.
Patient, cohort and facility methods are listed and callable without custom code.
- Create a Metriport patient
- Get single Metriport patient by ID
- Update a Metriport patient by ID
- List all Metriport patients
Toolboxes
Every team gets its own Metriport toolbox.
Curate one toolbox per team so each sees only relevant Metriport tools.
- Care coordination
- Clinical records
- Patient intake
- Population health
Shared connections
Teammates use Metriport accounts without credentials.
Each connection shows who connected it and which teams and members share it.
- Primary care
- Cardiology clinic
- Patient intake
- Population health
Audit log
Every Metriport call is written down.
When, who, what happened, type and resource, appended for each patient request.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule runs the whole patient digest.
Metriport records are fetched, grouped, drafted by an agent, approved, then posted back.
Metriport digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch patients
Metriport
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Metriport
Queued
Collections and dashboards
Metriport patient numbers land before anyone asks.
Four metrics, 14 days of records created and a team breakdown, computed on schedule.
Metriport health
Refreshed 4 minutes ago · every 15 minutes · from the patients collection
Patients
1,284 ↓ 12%
Cohorts
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Patients created
Last 14 days
By team
Share of activity
Primary care 34%
Cardiology clinic 27%
Patient intake 21%
Population health 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Metriport to Claude?
Connect Metriport in Elaichi first: pick Metriport from the catalog and paste in the API key from your Metriport dashboard, then in Claude go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. That is the whole setup, and there is no client ID or secret to generate. Sign in with your Elaichi account and Claude can start working with Metriport patients, facilities, and record queries.
Does Metriport work with ChatGPT and Cursor as well as Claude?
Yes. Once Metriport is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Metriport once and every client you use picks it up.
What can an AI agent actually do with my Metriport data?
An agent can register a patient in Metriport, match a person against existing patients, update demographics, and request a medical record summary or start a document query and tell you when it is ready. It can also add patients to cohorts, set which facility a patient is seen at, and keep facility details current. Because Metriport exposes a lot of actions, short concrete asks such as "get the record summary status for this patient" work better than long paragraphs.
Does connecting Metriport give the AI access to every patient?
No. Every request to Metriport runs with the access of the person who signed in to Elaichi, so an agent can only reach the patients, facilities, and records that person's Metriport access already allows. Elaichi can narrow that further by hiding actions or whole groups of actions, but it can never grant more than the person already has.
Can I stop an agent from deleting or changing things in Metriport?
Yes. Restrictions in Elaichi work per action, so you can allow reading Metriport patients and record summaries while blocking deleting patients or removing facilities. A blocked action is never shown to Claude, ChatGPT, or any other client, so no prompt, however worded, can reach it.
What happens to a Metriport connection when someone leaves?
Offboarding a person in Elaichi ends their access to Metriport through every client at once, with no keys to rotate on their way out. A shared Metriport connection keeps working for everyone else on the team. If you ever want to remove Metriport entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client at the same time.
Put Metriport in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.