Read candidates, jobs, stages and clients; add notes to candidates in Traffit. For recruiters and staffing teams that manage candidates and jobs in the Traffit ATS. 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": {
"traffit": {
"url": "https://traffit.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"traffit": {
"type": "http",
"url": "https://traffit.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.
List candidates with a filter on the creation date. Open one candidate to read the contact data and status.
traffit_list_candidates traffit_get_candidate
Get the number of candidates per pipeline stage of one job. List the candidates in one stage.
traffit_get_job_stage_counts traffit_list_job_states traffit_list_stage_candidates
Read the activities of a candidate: notes, stage moves and mails. List the jobs that the candidate takes part in.
traffit_get_candidate_activities traffit_get_candidate_jobs
List client companies and the contact people. Read the CRM activities such as calls and meetings.
traffit_list_clients traffit_list_contacts traffit_list_crm_activities
Add a text note to the activity history of a candidate, so the team sees what you discussed.
Changes data · traffit_add_candidate_note
The login page asks for your Traffit account, Integration client id and Client secret.
Optional: Scopes (space separated).
In Traffit open Settings → Integration with the Traffit API, click + Add client, tick the scopes you want (API V2), then Generate Client Secret. The client id has the form youraccount_clientname. Type the same scopes below. Your secret is used only to call the API for you and to derive a private account id; 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 Traffit account, Integration client id and Client secret. 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 Traffit connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
traffit_list_candidates | read | List candidates List candidates in the ATS with paging, filters (e.g. created_at, name, lastname) and sort. Returns total_count and items. Scope: employee. GET /employees/. |
traffit_get_candidate | read | Get a candidate Get one candidate by id with contact data, status, files list and custom fields. Scope: employee. GET /employees/{id}. |
traffit_get_candidate_tags | read | Get candidate tags List the tags of one candidate. Scope: employee. GET /employees/{id}/tags. |
traffit_get_candidate_jobs | read | Get candidate jobs List the jobs (recruitments) a candidate takes part in. Scope: employee. GET /employees/{id}/recruitments. |
traffit_get_candidate_activities | read | Get candidate activities List the activity history of one candidate (notes, stage moves, mails). Scope: employee. GET /employees/{id}/activities. |
traffit_get_candidate_files | read | Get candidate files List the files (file names and upload dates) of one candidate. Scope: employee. GET /employees/{id}/files. |
traffit_get_candidate_sources | read | Get candidate sources List where one candidate came from (source records). Scope: source. GET /sources/employees/{id}. |
traffit_list_jobs | read | List jobs List jobs (recruitments) with paging, filters and sort. Scope: recruitment. GET /recruitments/. |
traffit_get_job | read | Get a job Get one job (recruitment) by id with client, responsible people, status and custom fields. Scope: recruitment. GET /recruitments/{id}. |
traffit_list_job_candidates | read | List candidates of a job List the candidates attached to one job. Scope: recruitment. GET /recruitments/{id}/employees. |
traffit_list_job_states | read | List job stages List the pipeline stages (states) of one job. Scope: recruitment. GET /recruitments/{id}/states. |
traffit_get_job_stage_counts | read | Count candidates per stage Count the candidates in each stage of one job. Scope: recruitment. GET /recruitments/{id}/states/counter. |
traffit_list_stage_candidates | read | List candidates in a job stage List the candidates that are now in one stage of one job. Get stage ids from traffit_list_job_states. Scope: recruitment. GET /recruitments/{job}/states/{state}/employees. |
traffit_list_clients | read | List clients List client companies (CRM) with paging, filters and sort. Scope: client. GET /clients/. |
traffit_get_client | read | Get a client Get one client company by id. Scope: client. GET /clients/{id}. |
traffit_list_contacts | read | List client contacts List contact people (crm_persons) of client companies. Scope: crm_person. GET /crm_persons/. |
traffit_get_contact | read | Get a client contact Get one contact person by id. Scope: crm_person. GET /crm_persons/{id}. |
traffit_list_crm_activities | read | List CRM activities List CRM activities (calls, meetings, notes on clients and contacts). Scope: crm_activity. GET /crm_activities/. |
traffit_list_users | read | List users List users of the Traffit account with their groups and permission groups. Scope: user. GET /users/. |
traffit_get_user | read | Get a user Get one Traffit user by id. Scope: user. GET /users/{id}. |
traffit_list_talent_pools | read | List talent pools List talent pools (named groups of candidates). Scope: talent. GET /talents. |
traffit_list_sources | read | List sources List candidate sources (job boards, referrals). Scope: source. GET /sources. |
traffit_get_workflow | read | Get a workflow Get one recruitment workflow by id with its stages. Scope: dictionary. GET /workflows/{id}. |
traffit_add_candidate_note | write | Add a note to a candidate WRITE: add a text note to one candidate's activity history. Each call adds a new note, so do not repeat a call that succeeded. Scope: employee. POST /employees/{id}/notes. |
traffit_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. | |
traffit_request_feature | Request a missing feature Tell usefulapi that the user needs something the Traffit 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. | |
traffit_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Traffit (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. | |
traffit_cancel_subscription | Cancel the Pro subscription Cancel the caller's Traffit 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 traffit_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 user | $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 Traffit server only. Subscribe with traffit_upgrade (it returns a Stripe Checkout link). Cancel any time with traffit_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running traffit_upgrade before then undoes the cancel. Or write to [email protected].
See the candidates that were added recently. Count the candidates in each stage of a job. Read the history of a candidate. Review client companies and their contacts. Record a note after a call. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by Traffit. The server calls the Traffit API with your own Traffit 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 Traffit account, Integration client id and Client secret. 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 Traffit account, Integration client id and Client secret. 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 Traffit 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 Traffit.
Yes, if you approve it. 1 of the 24 Traffit tools can create or change data. The other 23 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 Traffit server only. Cancel any time: Pro then runs to the end of the paid period. Run traffit_usage_status to see how many calls you used.
Ask the AI to run traffit_upgrade: it returns a Stripe Checkout link. To cancel, run traffit_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 traffit_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.