Read Homerun vacancies, applications, notes and tags; move an application to a stage or add a note. 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": {
"homerun": {
"url": "https://homerun.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"homerun": {
"type": "http",
"url": "https://homerun.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 Homerun API key.
Create it in Homerun → Settings → Integrations (the Public API needs a plan that includes it). Give the key only the scopes you need: vacancies:read, job-applications:read, job-application-notes:read, tags:read and job-application-tags:read for reading; add job-applications:write and job-application-notes:write only if you want to move candidates between stages or add notes. Your key is used only to call the Homerun 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 Homerun 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 |
|---|---|---|
homerun_list_vacancies | read | List vacancies List job vacancies (draft, private, public, ...) with title, status, type, location type and expiry. Optionally include location, department, hiring stages (their ids are what homerun_move_application_to_stage needs), salary indication and the candidate count. GET /vacancies (scope vacancies:read). |
homerun_get_vacancy | read | Get vacancy One vacancy by id with description, location, department, hiring stages (id + name), salary indication, candidate count and the public job and application-form URLs. GET /vacancies/{vacancy_id} (scope vacancies:read). |
homerun_list_applications | read | List applications (candidates) List job applications, newest page first as the API orders them. Each item has name, e-mail, vacancy id, current stage (id + name), rating, created/hired dates and disqualified flag. Personal data: no phone number, date of birth, photo or files are returned here; ask for one application with homerun_get_application. Filter by vacancy, stage name or disqualified state and page through; do not use it to export all candidates. GET /job-applications (scope job-applications:read). |
homerun_get_application | read | Get application (candidate) One job application in full: contact details (name, e-mail, phone, city, country), links, experience/education, current stage, rating, sources and file names (notes: use homerun_list_notes). Date of birth, photo URL and file download links are never returned. Optionally include the answers to the application-form questions. Personal data: fetch only the candidate you need. GET /job-applications/{job_application_id} (scope job-applications:read). |
homerun_list_notes | read | List application notes List the notes on one application: id, author display name, text, sensitive flag and timestamps. GET /job-applications/{job_application_id}/notes (scope job-application-notes:read). |
homerun_list_tags | read | List tags List the company's candidate tags (id + name). GET /tags (scope tags:read). |
homerun_list_application_tags | read | List an application's tags The tags attached to one application. GET /job-applications/{job_application_id}/tags (scope job-application-tags:read). |
homerun_move_application_to_stage | write | Move application to a stage WRITE: move ONE application to another hiring stage of its vacancy (PATCH with only the stage id; nothing else on the application changes). Get stage ids from homerun_get_vacancy. Homerun's own automations for that stage may run (for example automatic e-mails configured in Homerun); this tool sends no e-mail itself and does not reject or delete anyone. PATCH /job-applications/{job_application_id} (scope job-applications:write). |
homerun_add_note | write | Add a note to an application WRITE: add ONE note (1-2000 characters) to one application. It becomes visible to the hiring team in Homerun and cannot be removed with this server. display_name is free text shown as the author. Nothing is sent to the candidate. POST /job-applications/{job_application_id}/notes (scope job-application-notes:write). |
homerun_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. | |
homerun_request_feature | Request a missing feature Tell usefulapi that the user needs something the Homerun 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. | |
homerun_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Homerun 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. | |
homerun_cancel_subscription | Cancel the Pro subscription Cancel the caller's Homerun 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 homerun_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 user | $9/mo · $90/yr | Unlimited |
Pro covers this Homerun server only. Subscribe with homerun_upgrade (it returns a Stripe Checkout link). Cancel any time with homerun_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running homerun_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 Homerun. The server calls the Homerun API with your own Homerun access, so it sees only the data that your account can see.
The login page asks for your Homerun 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 Homerun 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 Homerun 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 Homerun.
Yes, if you approve it. 2 of the 9 Homerun tools can create or change data. The other 7 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 Homerun server only. Run homerun_usage_status to see how many calls you used.
Ask the AI to run homerun_upgrade: it returns a Stripe Checkout link. To cancel, run homerun_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 homerun_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.