# Shapes MCP connector

The Shapes connector brings your people data, headcount, attrition risk and compensation, to Claude, ChatGPT, Cursor and any MCP client, so each person can ask questions in plain language within their own Shapes permissions.

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

## Facts

| | |
| --- | --- |
| Application | Shapes |
| Category | HRIS |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Shapes builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | intercom.help/Shapes-help-center/en |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, 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 Shapes is connected

- What is our current headcount by department?
- Which teams show the highest attrition risk this quarter?
- Show compensation gaps between levels in Engineering.

## Connect Shapes in Elaichi

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

1. Open Connections, choose Add connection, and pick Shapes.
2. Optionally set Share with, then press Connect.
3. Approve it in Shapes. Shapes's own window opens. Whoever approves it decides what this connection can reach.

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

## Shapes 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.

## Shapes 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 today. The plugin directory lives at chatgpt.com/plugins.

## Shapes 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.

## Connect Shapes 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 Shapes 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 Shapes through Elaichi

### Answer a headcount question before the meeting

People. Ask how many people sit in each department in Shapes, how that changed this quarter, and where the open roles are. The answer comes from the live record, not from a spreadsheet exported last month.

### Check compensation gaps across a department

Finance. Ask Shapes where pay sits outside the band for a level or location and get the figures back before the budget review, limited to the compensation you are already allowed to see.

### Spot attrition risk on your team

Managers. Ask which people on your team Shapes flags as attrition risks and why, so the conversation happens before the resignation letter does.

### Pull a headcount trend for the board deck

Leadership. Ask for headcount by region over the last four quarters and have the numbers summarized in plain language, ready to paste into the deck.

### Find where the organization is thinly staffed

Recruiting. Ask Shapes which teams are under their planned headcount and which roles have stayed open longest, so hiring effort goes where it is needed.

### Compare pay across levels and locations

People analytics. Ask Shapes how compensation compares between two offices or two levels and get the comparison back in a sentence or a table, inside your Shapes permissions.

## Elaichi vs Zapier MCP vs Composio for Shapes

All three can connect Shapes 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 Shapes tools | Allow or restrict single Shapes 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 Shapes 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 | $15 per user per month. | 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 Shapes to Claude?

First, connect Shapes in Elaichi: choose Shapes from the catalog, sign in to Shapes in the browser window that opens and approve access. There is no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Claude will ask you to sign in to Elaichi, and from then on your Shapes people data is available in the conversation.

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

Yes. Once Shapes 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 Shapes once and every client picks it up.

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

It can answer questions about the people data you already have in Shapes: headcount by department or region, who is flagged as an attrition risk, and where compensation falls outside a band. What it can reach depends on what your Shapes account has set up and on your own Shapes permissions. Short, concrete asks such as "headcount in Sales by country" work better than long paragraphs.

### Does connecting Shapes give the AI access to everyone's records and pay?

No. Every call to Shapes runs as the person who signed in, so the AI sees only the employees, departments and compensation that person can already see in Shapes. Elaichi can narrow that further with roles and restrictions, and it can never widen it beyond what Shapes allows.

### Can my team share one Shapes connection?

Yes. One person connects Shapes in Elaichi and shares the connection with a team, and nobody else on the team ever handles a credential. Each person still signs in to Elaichi as themselves, so every question asked of Shapes is logged under their own name.

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

Yes. Restrictions in Elaichi apply per action, so you can allow questions about Shapes people data while blocking anything that would change a record. A restricted action is never shown to Claude, ChatGPT or Cursor at all, so no prompt can reach it.

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

Offboarding a person in Elaichi ends their access to Shapes through every client at once, with no separate steps in Claude, ChatGPT or Cursor. If they connected a shared Shapes account, that connection keeps working for everyone else on the team. Disconnecting Shapes once in Elaichi removes it from every client.

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

Yes. Shapes 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, 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 Shapes?

Yes. Both let Claude, ChatGPT or Cursor use Shapes. 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 Shapes call.

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

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 Shapes: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.