Read Spoke Dispatch plans, stops, routes and drivers; create and optimize plans; send routes. Hosted by usefulapi — connect from Claude, 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": {
"spoke-dispatch": {
"url": "https://spoke-dispatch.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"spoke-dispatch": {
"type": "http",
"url": "https://spoke-dispatch.usefulapi.io/mcp"
}
}
}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.
The login page asks for your Spoke Dispatch API key.
Create a key in Spoke Dispatch under Settings → Integrations → API. The key acts for your whole team; keep it secret. Your key is used only to call the Spoke Dispatch 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 Spoke Dispatch API key. 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.
| Tool | Type | What it does |
|---|---|---|
spoke_list_plans | read | List plans List route plans (a plan = one day's delivery job: date, depot, drivers, routes), newest first, in pages of up to 20. Filter with e.g. {"title":"Monday run"} or {"startsGte":"2026-10-01"}. GET /plans. |
spoke_get_plan | read | Get plan One plan: title, start date, depot, driver ids, route ids, whether it is distributed/writable, optimization state and route overrides. GET /plans/{planId}. |
spoke_list_plan_stops | read | List plan stops List the stops of a plan, in pages of up to 10. Stops include recipient names, phones, e-mails and addresses (personal data): page only as far as needed. GET /plans/{planId}/stops. |
spoke_get_stop | read | Get stop One stop of a plan with address, recipient, timing, ETA, route and delivery outcome (attempted, succeeded, notes, photo/signature links). Contains personal data. GET /plans/{planId}/stops/{stopId}. |
spoke_search_stops | read | Search stops Search all stops of the team (planned, unassigned, past) by keyword and/or Spoke's filter language, up to 20 per page. Example filter: address.countryCode = "DE" and deliveryInfo.attempted = false. Filterable: planId, routeId, type, activity, notes, address.*, createdAt, recipient.name/email/phone/externalId, deliveryInfo.state/attempted/succeeded, orderInfo.*. Results include personal data. The search index lags real time by a short while. GET /stops:search. |
spoke_list_unassigned_stops | read | List unassigned stops List stops that are not on any plan yet (the inbox of imported orders), in pages of up to 20 (default 20). Contains personal data. GET /unassignedStops. |
spoke_get_unassigned_stop | read | Get unassigned stop One unassigned stop by id. Contains personal data. GET /unassignedStops/{id}. |
spoke_list_drivers | read | List drivers List the team's drivers (name, e-mail/phone, active flag, depots, route overrides), up to 50 per page. Contains personal data. GET /drivers. |
spoke_get_driver | read | Get driver One driver by id. Contains personal data. GET /drivers/{driverId}. |
spoke_list_depots | read | List depots List depots (start/end addresses, working hours, vehicle type, max stops), up to 20 per page. Use the ids when creating plans. GET /depots. |
spoke_get_depot | read | Get depot One depot by id. GET /depots/{depotId}. |
spoke_list_routes | read | List routes List routes (one driver's run of a plan: stop count, driver, distributed/started/completed state), up to 20 per page. GET /routes. |
spoke_get_route | read | Get route One route: title, driver, stop count and state (distributed, started, completed, recipients notified). GET /routes/{routeId}. |
spoke_list_route_stops | read | List route stops List the stops of one route in driving order, in pages of up to 10. Contains personal data: page only as far as needed. GET /routes/{routeId}/stops. |
spoke_list_operations | read | List operations List long-running operations (plan optimizations): type, done flag, who started it, result (optimized and skipped stops), up to 20 per page. GET /operations. |
spoke_get_operation | read | Get operation One operation, e.g. the optimization started by spoke_optimize_plan: poll until done is true. GET /operations/{operationId}. |
spoke_list_custom_stop_properties | read | List custom stop properties The team's custom stop property definitions (ids and names). Their ids are the keys of customProperties on stops. Needs a subscription that includes custom properties (HTTP 403 otherwise). GET /team/customStopProperties. |
spoke_create_plan | write | Create plan WRITE: create a new route plan for a date (no stops yet, nothing is sent to drivers). Optionally assign drivers (up to 50, they must be active and share the plan's depot) and a depot (default: the team's main depot). Does not optimize or distribute. POST /plans. |
spoke_update_plan | write | Update plan WRITE: change a plan's title, date, drivers and/or depot. Only the fields you pass change, but driver_ids REPLACES the plan's whole driver list. Fails if the plan is not writable (already distributed). Nothing is sent to drivers. PATCH /plans/{planId}. |
spoke_create_stop | write | Create stop WRITE: add one stop to a writable (not yet distributed) plan. Needs an address (text fields or latitude+longitude). The recipient's phone/e-mail are stored on the stop and Spoke may contact the recipient later when the route runs; nothing is sent now. For many stops use spoke_import_stops. POST /plans/{planId}/stops. |
spoke_import_stops | write | Import stops WRITE: add up to 100 stops to a writable (not yet distributed) plan in one request (better geocoding than one at a time; Spoke limits imports to 30 requests a minute). Returns the created stop ids and any failures. Recipient contact data is stored on the stops; nothing is sent now. POST /plans/{planId}/stops:import. |
spoke_optimize_plan | write | Optimize plan WRITE: start the route optimization of a plan (orders and assigns its stops to its drivers). Rewrites the plan's routes if it was optimized before, and uses Spoke's optimization quota (30 per minute, 100 per 10 minutes). Does NOT send anything to drivers. Returns an operation: poll spoke_get_operation until done. Needs at least one driver and one stop. POST /plans/{planId}:optimize. |
spoke_distribute_plan | write | Distribute plan to drivers WRITE (SENDS TO REAL PEOPLE): distribute an optimized plan, which immediately sends each driver of the plan their route on their phone (push notification / message) and locks the plan for edits. Cannot be undone. Only for a plan with 1-10 drivers, and only after the user has explicitly said to send the routes: set confirm_send_to_drivers to true. POST /plans/{planId}:distribute. |
spoke_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
spoke_request_feature | Request a missing feature Tell usefulapi that the user needs something the Spoke Dispatch 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. | |
spoke_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Spoke Dispatch tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
spoke_cancel_subscription | Cancel the Pro subscription Cancel the caller's Spoke Dispatch Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run spoke_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Proper team | $9/mo · $90/yr | Unlimited |
Pro covers this Spoke Dispatch server only. Subscribe with spoke_upgrade (it returns a Stripe Checkout link). Cancel any time with spoke_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running spoke_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 Spoke Dispatch. The server calls the Spoke Dispatch API with your own Spoke Dispatch access, so it sees only the data that your account can see.
The login page asks for your Spoke Dispatch API key. 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 Spoke Dispatch API key. 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 Spoke Dispatch 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 Spoke Dispatch.
Yes, if you approve it. 6 of the 23 Spoke Dispatch tools can create or change data. The other 17 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this Spoke Dispatch server only. Run spoke_usage_status to see how many calls you used.
Ask the AI to run spoke_upgrade: it returns a Stripe Checkout link. To cancel, run spoke_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 spoke_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, 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.