# Manatal MCP connector

The Manatal connector lets Claude, ChatGPT, Cursor and the Elaichi Agent add notes, resumes and attachments to Manatal candidates and read a candidate's note history, with every action tied to the recruiter who signed in.

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

## Facts

| | |
| --- | --- |
| Application | Manatal |
| Category | ATS |
| AI tools | 5 |
| Authentication | Connects with an API key |
| Needs your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | Yes |

## What you can ask once Manatal is connected

- Summarize the notes on this week's shortlisted candidates.
- Add an interview note to the backend engineer candidate.
- List all notes on candidates for the sales role.

## Connect Manatal in Elaichi

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

1. Open Connections, choose Add connection, and pick Manatal.
2. Optionally set Share with, then press Connect.
3. Paste a Manatal API key. One person generates a token in Manatal 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 Manatal tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Connect Manatal to 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.

## Connect Manatal to 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 today. The plugin directory lives at chatgpt.com/plugins.

## Connect Manatal to 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.

## Connect Manatal 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

Only Read is granted by default, which is not enough to call a Manatal tool. 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. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Manatal through Elaichi

### Write up a screening call in Manatal

Recruiting. After a phone screen, dictate what you learned and have it saved as a note on the candidate's Manatal record while the details are still fresh.

### Read a candidate's history before an interview

Recruiting. Ask for every note left on a candidate in Manatal and get a short summary of what previous interviewers said, so you walk in prepared.

### Attach an updated resume to a candidate

Talent acquisition. When a candidate sends a newer resume, have it added to their Manatal profile without leaving the conversation you are already in.

### Leave interview feedback where recruiters see it

Hiring managers. Hiring managers can drop their feedback as a note on the Manatal candidate instead of emailing it, so the whole panel reads the same record.

### File reference checks and signed documents

HR. Attach reference check summaries, signed offer letters or work samples to the candidate's Manatal record so everything about the hire sits in one place.

### Tidy duplicate or outdated candidate notes

Agency recruiters. Spot notes that were added twice or no longer apply and remove them from Manatal, keeping the candidate's history clear for the next consultant.

## Frequently asked questions

### How do I connect Manatal to Claude?

First, connect Manatal in Elaichi by pasting your Manatal API key, which you copy from your Manatal account settings. There is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Sign in as yourself and Manatal is ready to use in Claude.

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

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

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

Through this connector an AI agent can add a note to a Manatal candidate, read back all the notes on a candidate and summarize them, remove a note, and attach a resume or another file such as a portfolio or signed offer letter to the candidate's record. It works at the level of individual candidates you already have in Manatal. It cannot search for candidates, edit jobs or change pipeline stages through this connector.

### Does connecting Manatal give the AI access to every candidate?

No. Every call to Manatal runs inside the access of the person who signed in, so the AI can only reach candidates that person can already reach in Manatal. Elaichi can narrow that access further, for example by blocking note deletion for a team, but it can never widen it beyond what the person already has.

### Can my team share one Manatal connection?

Yes. One person connects Manatal with their API key in Elaichi and shares the connection with a team, and nobody else ever sees or handles that key. Each teammate still signs in as themselves, so the audit log names the actual recruiter who added or removed a note on a Manatal candidate.

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

Yes. Restrictions in Elaichi apply per action, so you can allow adding notes and resumes to Manatal candidates while blocking note deletion entirely. A blocked action is never advertised to Claude, ChatGPT or any other client, so no prompt, however worded, can reach it.

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

When you offboard someone in Elaichi, their access to Manatal through the endpoint ends at once. A shared Manatal connection keeps working for everyone else on the team. If you ever want to remove Manatal completely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.

## All 5 Manatal tools

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

- **Create a Manatal candidate attachment** (Create). Create a candidate attachment in Manatal. Requires candidate_id. Returns id, name, description, file (URL of the attachment), creator, and created_at fields in the response.
- **Create a Manatal candidate note** (Create). Create a new note for a specific candidate in Manatal using candidate_id. Returns id, info, creator, and created_at of the created note.
- **List all Manatal candidate notes** (List). List candidate-notes for a specific candidate in Manatal. Requires candidate_pk. Returns id, info, creator, and created_at fields for each note.
- **Delete a Manatal candidate note by ID** (Delete). Delete a specific candidate note in Manatal using candidate_pk and id. Returns a 204 response to confirm successful deletion.
- **Create a Manatal candidate resume** (Create). Create a resume for a specific candidate in Manatal using candidate_id. Returns id, resume_file (URL to the uploaded file), and created_at (timestamp of upload).
