Read CATS candidates, jobs and pipelines, and make explicitly confirmed recruiting changes. For recruiters and hiring teams managing candidates and job pipelines in CATS. 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": {
"cats-ats": {
"url": "https://cats-ats.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"cats-ats": {
"type": "http",
"url": "https://cats-ats.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.
Search candidate records or apply field filters, then open the matching record for review.
cats_search_candidates cats_filter_candidates cats_get_candidate
Inspect job details and the candidates linked to its pipeline, including their current stages.
cats_get_job cats_list_job_pipelines
Review activity, tasks and attachment metadata for a chosen candidate without downloading files.
cats_list_candidate_activities cats_list_candidate_tasks cats_list_candidate_attachments
After explicit confirmation, create a recruiting task with an assignee and due date. CATS may notify the assignee.
Changes data · cats_create_task
Apply a stage you have chosen after confirmation. The connector requests trigger suppression; independent account webhooks may still run.
Changes data · cats_change_pipeline_status
The login page asks for your CATS API key.
Create it in CATS under Settings → Administration → API (a v3 key; old Transaction Codes do not work). Authorize UsefulAPI and your chosen AI client to process only the recruiting data you are entitled to share. Keep government IDs, health data, personal financial data and other CATS Prohibited Data out of this workflow. Use an authorized key appropriate for this workflow; the key-generation form offers no read-only scope selector. CATS documents a rolling 500 API requests per hour (the counter scope is unspecified). Writes require explicit confirmation and may cause configured account automation or webhooks. Requests are not replayed automatically. Your key is used only to call the CATS 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 CATS 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.
Turn on the CATS connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
cats_get_site | read | Get CATS site The CATS site (account) this API key belongs to: id, mode (recruiter or employer) and subdomain. GET /site. |
cats_list_users | read | List users List the CATS users (recruiters) with id, name, title and access level. Use the ids as owner or assignee. GET /users. |
cats_list_candidates | read | List candidates List candidates (personal data: name, emails, address, employer, skills, notes), one page at a time, max 100 per page. Use cats_search_candidates or cats_filter_candidates to find specific people. GET /candidates. |
cats_get_candidate | read | Get candidate One candidate by id (personal data). GET /candidates/{id}. |
cats_search_candidates | read | Search candidates Free-text search over candidates (name, email, skills, resume text...), paged. GET /candidates/search?query=. |
cats_filter_candidates | read | Filter candidates Filter candidates by fields (read-only, although it is a POST): first_name, last_name, title, emails.primary, address.city/state/postal_code, country_code, current_employer, key_skills, notes, dates (date_created, date_modified), owner_id, is_hot... Each condition is {field, filter, value}; filters: exactly, contains, between {gte,lte}, greater_than, less_than, is_empty, geo_distance. Paged. POST /candidates/search. |
cats_list_candidate_pipelines | read | List a candidate's pipelines The jobs a candidate is in the pipeline for, with rating, workflow and current status id. GET /candidates/{id}/pipelines. |
cats_list_candidate_activities | read | List a candidate's activities The activity log of a candidate (calls, meetings, notes, pipeline changes), paged. GET /candidates/{id}/activities. |
cats_list_candidate_tasks | read | List a candidate's tasks Tasks attached to a candidate. GET /candidates/{id}/tasks. |
cats_list_candidate_attachments | read | List a candidate's attachments (metadata) File names, sizes and whether each file is a resume, for a candidate's attachments. Metadata only: file contents are never downloaded. GET /candidates/{id}/attachments. |
cats_list_jobs | read | List jobs List job orders with title, location, company, recruiter, status and workflow ids, dates. Paged. GET /jobs. |
cats_get_job | read | Get job One job order by id, with its description. GET /jobs/{id}. |
cats_search_jobs | read | Search jobs Free-text search over job orders, paged. GET /jobs/search?query=. |
cats_list_job_pipelines | read | List a job's pipeline The candidates in the pipeline of a job: pipeline id, candidate id, rating and current status id. Paged. GET /jobs/{id}/pipelines. |
cats_list_job_statuses | read | List job statuses The statuses a job order can have (Active, OnHold, Closed...). GET /jobs/statuses. |
cats_list_pipelines | read | List pipelines List candidate-to-job pipelines (candidate id, job id, rating, workflow id, status id), paged. GET /pipelines. |
cats_get_pipeline | read | Get pipeline One pipeline (a candidate on a job) by id. GET /pipelines/{id}. |
cats_filter_pipelines | read | Filter pipelines Filter pipelines by id, candidate_id, job_id, status_id, rating, date_created or date_modified (read-only, although it is a POST). Each condition is {field, filter, value}. Paged. POST /pipelines/search. |
cats_get_pipeline_status_history | read | Get pipeline status history The status changes of a pipeline over time (status, who, when). GET /pipelines/{id}/statuses. |
cats_list_workflows | read | List pipeline workflows The pipeline workflows (sets of statuses such as Contacted, Interviewing, Offered). GET /pipelines/workflows. |
cats_list_workflow_statuses | read | List workflow statuses The statuses of one pipeline workflow (id, title, prerequisites, triggers). Use the ids with cats_change_pipeline_status. GET /pipelines/workflows/{id}/statuses. |
cats_list_companies | read | List companies List client companies (name, address, website, owner), paged. GET /companies. |
cats_get_company | read | Get company One company by id. GET /companies/{id}. |
cats_search_companies | read | Search companies Free-text search over companies, paged. GET /companies/search?query=. |
cats_list_contacts | read | List contacts List client contacts (personal data: name, title, emails, company), paged. GET /contacts. |
cats_get_contact | read | Get contact One client contact by id (personal data). GET /contacts/{id}. |
cats_search_contacts | read | Search contacts Free-text search over client contacts, paged. GET /contacts/search?query=. |
cats_list_tasks | read | List tasks List tasks (description, priority 1-5, due date, assignee, completion, the record it is about), paged. GET /tasks. |
cats_get_task | read | Get task One task by id. GET /tasks/{id}. |
cats_list_activities | read | List activities The site-wide activity log (calls, emails logged, meetings, notes) with the record each is about, paged. GET /activities. |
cats_add_candidate_activity | write | Add an activity (note) to a candidate WRITE: Requires confirm:true. log an activity (a call, meeting, note...) on a candidate's record. It only records the entry in CATS: no email/SMS-send request is made, even for type 'email' or 'text_message'. Creates a new entry each time (not idempotent). POST /candidates/{id}/activities. |
cats_create_task | write | Create a task WRITE: Requires confirm:true. create a task in CATS, optionally about a candidate, contact, company or job and assigned to a user. Creates a new task each time (not idempotent); CATS may notify the assignee. POST /tasks. |
cats_change_pipeline_status | write | Move a candidate to another pipeline status WRITE: Requires confirm:true. change the status of a pipeline (move a candidate to another stage of a job's workflow, e.g. Interviewing, Offered, Rejected). Get the pipeline id from cats_list_candidate_pipelines and the status id from cats_list_workflow_statuses. Requires confirm:true. Requests that status triggers (which can e-mail people or change records) be suppressed: every trigger attached to the target status is sent with fire=false. CATS remains responsible for enforcing its trigger semantics; independently configured webhooks may still run. The change is recorded in the pipeline's status history. POST /pipelines/{id}/status. |
cats_create_candidate | write | Create a candidate WRITE: Requires confirm:true. create one candidate record (personal data) with name, optional contact details and notes. Refuses when CATS finds a duplicate (check_duplicate=true, the default). Creates a new record each time (not idempotent); no email-send request is made to the candidate and no login is created. POST /candidates. |
cats_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. | |
cats_request_feature | Request a missing feature Tell usefulapi that the user needs something the CATS 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. | |
cats_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on CATS (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+, $39/month or $390/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. | |
cats_cancel_subscription | Cancel the Pro subscription Cancel the caller's CATS 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 cats_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Freeper connected CATS site | $0 | 50 tool calls / month |
| Proper connected CATS site | $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 CATS server only. Subscribe with cats_upgrade (it returns a Stripe Checkout link). Cancel any time with cats_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running cats_upgrade before then undoes the cancel. Or write to [email protected].
Find a specific candidate. Review a job’s pipeline. Read candidate history. Create a follow-up task. Record a human-selected stage. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by CATS. The server calls the CATS API with your own CATS access, so it sees only the data that your account can see.
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 CATS 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 CATS 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 CATS 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 CATS.
Yes, if you approve it. 4 of the 34 CATS tools can create or change data. The other 30 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
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 CATS server only. Cancel any time: Pro then runs to the end of the paid period. Run cats_usage_status to see how many calls you used.
Ask the AI to run cats_upgrade: it returns a Stripe Checkout link. To cancel, run cats_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 cats_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.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.