Read Photon Health patients, prescriptions, orders, pharmacies and medications; screen interactions. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"photon-health": {
"url": "https://photon-health.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"photon-health": {
"type": "http",
"url": "https://photon-health.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
Patient data: Do not use this server with protected health information (PHI). We do not sign HIPAA Business Associate Agreements (BAAs). See Terms, Health data.
The login page asks for your Client ID, Client secret and Environment.
Find the key pair in the Photon app → Settings (app.photon.health for production, app.neutron.health for the Neutron sandbox). Sandbox keys only work with Sandbox, production keys only with Production. Your credentials are used only to call the Photon API on your behalf and to derive a private account id; they are never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Client ID, Client secret and Environment. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Photon Health connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
photonhealth_list_patients | read | List patients List the organization's patients (id, external id, name, date of birth, sex, contact, address), optionally filtered by name. Photon GraphQL: patients. |
photonhealth_get_patient | read | Get a patient Get one patient by Photon id, with allergies, medication history, preferred pharmacies, and their prescriptions and orders (ids + states). Photon GraphQL: patient. |
photonhealth_list_prescriptions | read | List prescriptions List the organization's prescriptions, filterable by patient, prescriber and state (ACTIVE, EXPIRED, DEPLETED, CANCELED). Each has the medication, quantity, refills/fills remaining, directions, diagnoses and fills. Photon GraphQL: prescriptions. |
photonhealth_get_prescription | read | Get a prescription Get one prescription by id: state, prescriber, patient, medication (with RxCUI/NDC codes), quantity, refills and fills remaining, days supply, directions, notes, diagnoses, dates and fills. Photon GraphQL: prescription. |
photonhealth_list_orders | read | List orders List pharmacy orders, filterable by patient and state (ROUTING, PENDING, PLACED, COMPLETED, CANCELED, ERROR). Each has the pharmacy, delivery address, fulfillment (type, state, carrier, tracking number) and fills. Photon GraphQL: orders. |
photonhealth_get_order | read | Get an order Get one order by id: state, patient, pharmacy, address, fulfillment status/tracking and its fills. Photon GraphQL: order. |
photonhealth_get_fill | read | Get a fill Get one fill (a single dispensing of a prescription within an order) by id: state (SCHEDULED, NEW, SENT, CANCELED), requested/filled times, medication, prescription and order. Photon GraphQL: fill. |
photonhealth_search_pharmacies | read | Search pharmacies Search pharmacies by name and/or near a location (latitude/longitude + radius in miles), by fulfillment type (PICK_UP = retail, MAIL_ORDER). Returns NPI, NCPDP, address, phone, fax. Photon GraphQL: pharmacies. |
photonhealth_get_pharmacy | read | Get a pharmacy Get one pharmacy by Photon id: name, NPI, NCPDP, address, phone, fax and fulfillment types. Photon GraphQL: pharmacy. |
photonhealth_search_medications | read | Search medications Search Photon's medication database by drug name (partial) or code (RxCUI, NDC or SKU). Returns DRUG-level concepts with RxCUI/NDC codes, schedule, controlled flag, strength and form; drill down with list_medication_products / list_medication_packages. Photon GraphQL: medications. |
photonhealth_list_medication_products | read | List medication products List the prescribable products (strength + form) of a DRUG-level medication from search_medications. Photon GraphQL: medicationProducts. |
photonhealth_list_medication_packages | read | List medication packages List the packages (package NDCs) of a PRODUCT-level medication from list_medication_products. Photon GraphQL: medicationPackages. |
photonhealth_get_medication_by_ndc | read | Look up a medication by NDC Find the medication matching a package NDC (11-digit National Drug Code). Photon GraphQL (clinical API): medicationFromNdc. |
photonhealth_search_medical_equipment | read | Search medical equipment Search prescribable medical equipment/supplies (e.g. glucose test strips) by name. Photon GraphQL: medicalEquipment. |
photonhealth_list_catalogs | read | List catalogs List the organization's treatment catalogs (the medications it prescribes) with their treatments and prescription templates. Photon GraphQL: catalogs. |
photonhealth_get_catalog | read | Get a catalog Get one treatment catalog by id with its treatments and prescription templates (quantity, refills, days supply, directions). Photon GraphQL: catalog. |
photonhealth_search_allergens | read | Search allergens Search Photon's allergen list by name (fuzzy), e.g. to map a patient's reported allergy to an allergen id/RxCUI. Photon GraphQL: allergens. |
photonhealth_list_dispense_units | read | List dispense units List the dispense units Photon accepts on a prescription (e.g. Each, Milliliter, Tablet). Photon GraphQL: dispenseUnits. |
photonhealth_get_organization | read | Get the organization Get the Photon organization these API keys belong to: id, name, type, NPI, address and contact details. Photon GraphQL (clinical API): organization. |
photonhealth_list_users | read | List users List the organization's users (prescribers and staff): id, name, email, NPI, credentials and roles — use an id as prescriber_id in list_prescriptions. Photon GraphQL (clinical API): users. |
photonhealth_screen_interactions | read | Screen for drug interactions Screen proposed medications for a patient against drug-drug and drug-allergy (and diagnosis) interactions, using the patient's allergies, medication history and existing prescriptions. READ-ONLY: nothing is written or prescribed. Returns alerts with type (DRUG, ALLERGEN, CONDITION), severity (MINOR, MODERATE, MAJOR), a description and the involved medications/allergens. Photon GraphQL (clinical API): prescriptionScreen. |
photonhealth_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
photonhealth_request_feature | Request a missing feature Tell usefulapi that the user needs something the Photon Health tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
photonhealth_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Photon Health (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $19/month or $190/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
photonhealth_cancel_subscription | Cancel the Pro subscription Cancel the caller's Photon Health Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run photonhealth_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper organization | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this Photon Health server only. Subscribe with photonhealth_upgrade (it returns a Stripe Checkout link). Cancel any time with photonhealth_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running photonhealth_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Photon Health. The server calls the Photon Health API with your own Photon Health access, so it sees only the data that your account can see.
No. Do not use this server with protected health information (PHI). We do not sign HIPAA Business Associate Agreements (BAAs). See Terms, Health data.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Client ID, Client secret and Environment. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Client ID, Client secret and Environment. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Photon Health API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Photon Health.
All 21 Photon Health tools are marked read-only.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this Photon Health server only. Cancel any time: Pro then runs to the end of the paid period. Run photonhealth_usage_status to see how many calls you used.
Ask the AI to run photonhealth_upgrade: it returns a Stripe Checkout link. To cancel, run photonhealth_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with photonhealth_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.