Read Spruce Health contacts, conversations, messages, phone lines and team members (read-only). 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": {
"spruce-health": {
"url": "https://spruce-health.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"spruce-health": {
"type": "http",
"url": "https://spruce-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 Spruce API token.
An organization admin creates the token in the Spruce web app → Settings → API Access. API access needs the Communicator plan and must first be enabled by Spruce Support. Your token is used only to call the Spruce API on your behalf; it is 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 Spruce API token. 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 Spruce Health connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
sprucehealth_get_organization | read | Get the organization Your Spruce organization (id and name). The id is the owner/member id used by other objects. Good first call. GET /organization. |
sprucehealth_list_members | read | List organization members All members of the organization: teammates (name, email, admin, suspended), teams and the organization itself. Paged with hasMore/paginationToken; totalCount included. GET /organization/members. |
sprucehealth_get_member | read | Get an organization member One organization member (teammate, team or the organization) by id. GET /organization/members/{memberId}. |
sprucehealth_list_team_members | read | List a team's members The members of one team (team ids come from sprucehealth_list_members, type 'team'). Paged. GET /teams/{teamId}/members. |
sprucehealth_list_contacts | read | List contacts Contacts of the organization (patients, professionals, clinics): name, date of birth, phones, emails, tags, custom fields, integration links. Paged with hasMore/paginationToken; totalCount included. Use sprucehealth_search_contacts to find someone. GET /contacts. |
sprucehealth_search_contacts | read | Search contacts Find contacts by free text and/or filters (category, tags, name, phone, email, invite state, created time). Filters combine with AND; values inside one filter match ANY (tags can use all/none). Paged; totalCount with totalCountRelation (eq = exact, gte = lower bound). A read: POST /contacts/search changes nothing. |
sprucehealth_get_contact | read | Get a contact One contact by Spruce contact id (entity_…): demographics, phones, emails, tags, custom and organization fields, integration links. GET /contacts/{contactId}. |
sprucehealth_list_contact_conversations | read | List a contact's conversations The conversations (secure, SMS/phone, email, fax…) associated with one contact. GET /contacts/{contactId}/conversations. |
sprucehealth_list_contact_integration_links | read | List a contact's integration links Links between a contact and external systems (Elation, Hint, athena, custom): type, external id, url. GET /contacts/{contactId}/integrationlinks. |
sprucehealth_list_contact_tags | read | List contact tags All contact tags of the organization. Paged with hasMore/paginationToken; totalCount included. GET /contacts/tags. |
sprucehealth_list_contact_fields | read | List organization contact fields The organization-wide contact fields shown on every contact. Paged; totalCount included. GET /contacts/fields. |
sprucehealth_list_conversations | read | List conversations Conversations of the organization (title, type, tags, archived, assignee, participants, last message time), ordered by creation or last message. With start_from, only conversations whose ordering time is at or after it (useful for 'what changed since…'). Eventually consistent. Paged; give start_from OR pagination_token, not both. GET /conversations. |
sprucehealth_get_conversation | read | Get a conversation One conversation by id (t_…). GET /conversations/{conversationId}. |
sprucehealth_list_conversation_items | read | List conversation messages The items (messages, internal notes, calls, voicemails, faxes, attachments with short-lived signed URLs) in one conversation. Order newest_first (default) or oldest_first; start_from = only items created after that time. Paged with hasMore/paginationToken; totalCount is a best-effort count. GET /conversations/{conversationId}/items. |
sprucehealth_get_conversation_item | read | Get a conversation message One conversation item (message, note, call, voicemail…) by id (ti_…). GET /conversationItems/{conversationItemId}. |
sprucehealth_list_read_receipts | read | List a message's read receipts Who has read one conversation item and when they first read it (oldest first). GET /conversationItems/{conversationItemId}/readReceipts. |
sprucehealth_get_transcription | read | Get a call or voicemail transcription The full transcription text and its summary (if any) for a transcription id (the transcriptionId on a call/voicemail attachment). Status pending/completed/failed/noSpeech. GET /transcriptions/{transcriptionId}. |
sprucehealth_list_conversation_tags | read | List conversation tags All conversation tags of the organization. Paged; totalCount included. GET /conversations/tags. |
sprucehealth_list_conversation_scheduled_messages | read | List a conversation's scheduled messages Messages scheduled to be sent later in one conversation (read only; nothing is sent or cancelled). GET /conversations/{conversationId}/scheduledmessages. |
sprucehealth_list_scheduled_messages | read | List scheduled messages All messages scheduled to be sent from the organization (read only). Paged with hasMore/paginationToken; totalCount included. GET /scheduledmessages. |
sprucehealth_list_saved_messages | read | List saved messages Saved message templates (private and organization-wide): title, text, internal/shared flags. Paged with hasMore/paginationToken. GET /savedmessages. |
sprucehealth_list_internal_endpoints | read | List internal endpoints The organization's own channels: Spruce phone and fax numbers, email addresses and Spruce Links, with their owner and members. GET /internalendpoints. |
sprucehealth_list_phone_lines | read | List phone lines All phone lines of the organization (id, name); totalCount included. GET /phonelines. |
sprucehealth_get_phone_line | read | Get a phone line One phone line by id (pd_…). GET /phonelines/{phonelineId}. |
sprucehealth_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. | |
sprucehealth_request_feature | Request a missing feature Tell usefulapi that the user needs something the Spruce 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. | |
sprucehealth_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Spruce 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. | |
sprucehealth_cancel_subscription | Cancel the Pro subscription Cancel the caller's Spruce 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 sprucehealth_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 Spruce Health server only. Subscribe with sprucehealth_upgrade (it returns a Stripe Checkout link). Cancel any time with sprucehealth_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running sprucehealth_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 Spruce Health. The server calls the Spruce Health API with your own Spruce 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 Spruce API token. See Before you connect for where to find it.
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 Spruce API token. 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 Spruce 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 Spruce Health.
All 24 Spruce 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 Spruce Health server only. Cancel any time: Pro then runs to the end of the paid period. Run sprucehealth_usage_status to see how many calls you used.
Ask the AI to run sprucehealth_upgrade: it returns a Stripe Checkout link. To cancel, run sprucehealth_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 sprucehealth_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.