# Teamtailor MCP connector

The Teamtailor connector lets Claude, ChatGPT, Cursor, Microsoft Copilot, or any MCP client create and update jobs, candidates, applications and notes in your Teamtailor account, with every action tied to the person who asked for it and recorded in an audit log.

Source: https://elaichi.ai/connectors/teamtailor/

## Facts

| | |
| --- | --- |
| Application | Teamtailor |
| Category | ATS |
| AI tools | 12 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Teamtailor is connected

- Summarize new job applications for the Engineering roles this week.
- Add a note on the shortlisted candidates for Account Executive.
- Which open jobs have no applications in the last 14 days?

## Connect Teamtailor in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Teamtailor.
2. Optionally set Share with, then press Connect.
3. Paste a Teamtailor API key. One person generates a token in Teamtailor and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Teamtailor tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Teamtailor MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Teamtailor MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Teamtailor MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Teamtailor MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Teamtailor MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Teamtailor to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete data and remove access", which you tick yourself. Calling a Teamtailor tool needs "Run your connected tools". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Run your connected tools, which can also delete in connected apps and cannot be undone.

## What teams do with Teamtailor through Elaichi

### Post a new role from a brief

Recruiting. Turn a hiring manager's brief into a job in Teamtailor, then refine the title, description or status as the role takes shape.

### Add a referred candidate in one step

Recruiting. Create the candidate in Teamtailor, attach their CV, and open an application against the right job without switching screens.

### Leave interview feedback where recruiters see it

Hiring managers. Add a note to the candidate straight after the interview, and update it later if a second conversation changes your view.

### Catch the application up after a screen

Talent acquisition. After a phone screen, update the job application in Teamtailor so its stage and details reflect where things actually stand.

### Keep candidate records accurate

People operations. Correct a misspelled name, update contact details, fix a note, or remove one that was added to the wrong candidate.

### Rewrite a job ad that is not landing

Employer branding. Redraft the wording of a live job and push the update to Teamtailor so the career site shows the new version.

## Elaichi vs Zapier MCP vs Composio for Teamtailor

All three can connect Teamtailor to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Teamtailor tools | Allow or restrict single Teamtailor tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Teamtailor call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Teamtailor to Claude?

In Elaichi, choose Teamtailor and paste in an API key from your Teamtailor settings. There is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Sign in with your Elaichi account and Teamtailor is available in the conversation.

### Does Teamtailor work with ChatGPT and Cursor as well as Claude?

Yes. Once Teamtailor is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client, and the Elaichi Agent. You connect Teamtailor once and every client picks it up.

### What can an AI agent actually do with my Teamtailor data?

With Teamtailor connected, an agent can create a job and update its details, add a candidate and attach their CV or other files, open a job application and update it as the candidate moves through the process, and write, edit, read or delete notes on a candidate. In practice that means drafting a job ad and posting it, logging a referral, or leaving interview feedback, all from a chat.

### Does connecting Teamtailor give the AI access to my whole account?

No. The Teamtailor connection carries only the access of the account that connected it, and every person using it signs in to Elaichi as themselves, so their actions are recorded under their own name. Elaichi can narrow what the agent is allowed to do in Teamtailor, for example allowing notes but not job changes, and it can never grant more than the connected account already has.

### Can my team share one Teamtailor connection?

Yes. One person connects Teamtailor in Elaichi and shares it with a team, and nobody else ever sees or handles the API key. Each teammate still signs in as themselves, so the audit log names the person who created a candidate or updated a job, not the person who set up the connection.

### Can I stop an agent from deleting or changing things in Teamtailor?

Yes. Restrictions in Elaichi work per action, so you can allow an agent to create and read notes in Teamtailor while restricting note deletion or job updates. A restricted action still appears in Elaichi's tool search, flagged as restricted, but Claude, ChatGPT or any other client cannot run it, whatever the prompt says.

### What happens to a Teamtailor connection when someone leaves?

When you offboard someone in Elaichi, their access to Teamtailor through Elaichi ends immediately. A connection shared with the team keeps working for everyone else. If you disconnect Teamtailor in Elaichi, it disappears from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client at once.

### Does the Teamtailor MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Teamtailor is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Teamtailor?

Yes. Both let Claude, ChatGPT or Cursor use Teamtailor. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Teamtailor call.

### How is Elaichi different from Composio for Teamtailor?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Teamtailor: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 12 Teamtailor tools

Every tool below is callable through https://api.elaichi.ai/mcp once Teamtailor is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Create a Teamtailor job** (Create). Create a new job in Teamtailor. Requires user, title, and body. Returns fields including id, title, status, human-status, pitch, created-at, updated-at, and key relationship links for job resources.
- **Update a Teamtailor job by ID** (Update). Update a job in Teamtailor using id. Returns fields including title, status, tags, updated-at, and links to related resources such as division, role, and location.
- **Create a Teamtailor candidate** (Create). Create a candidate in Teamtailor. Requires email unless sourced is true. Use merge to combine attributes with existing candidates. Returns candidate details including id, first-name, last-name, email, and pitch.
- **Update a Teamtailor candidate by ID** (Update). Update candidate in Teamtailor. Requires id. Returns updated candidate data including key fields such as id, type, and attributes reflecting modified details.
- **Create a Teamtailor upload** (Create). Create an upload for a specific candidate in Teamtailor. Requires a public url and candidate id. Returns id, url, file-name, internal, and related candidate, job, and answer links in the response.
- **Create a Teamtailor job application** (Create). Create a new job application in Teamtailor. Requires candidate and job relationships in the request body. Returns id, created-at, sourced, updated-at, and relationship links for candidate, job, stage, and reject-reason.
- **Update a Teamtailor job application by ID** (Update). Update a specific job application in Teamtailor by id. Returns cover-letter, created-at, updated-at, sourced, and relationship links for candidate, job, stage, and reject-reason.
- **Create a Teamtailor note** (Create). Create a new note in Teamtailor for a candidate using their id and user id. Returns fields such as id, note, created-at, updated-at, candidate-id, and user-id in the response.
- **Update a Teamtailor note by ID** (Update). Update a specific note in Teamtailor using id. Returns the updated note attributes including note text, created-at, updated-at, candidate-id, and user-id.
- **Delete a Teamtailor note by ID** (Delete). Delete a specific note in Teamtailor using id. Permanently removes the note and returns no content in the response.
- **Get single Teamtailor note by ID** (Get). Get a specific note in Teamtailor using id. Returns id, note text, created-at, updated-at, private-note, candidate-id, and user-id fields for detailed note information.
- **Create a Teamtailor transient upload** (Create). Create a transient upload in Teamtailor. Upload a file and return its transient URI, which can be used to attach the file to another resource. The URI is exposed once and must be stored immediately for reuse.
