# Metaview MCP connector

The Metaview connector lets Claude, ChatGPT, Cursor and the Elaichi Agent search interview transcripts, notes and sourcing reports in Metaview, with each person signed in as themselves and every request recorded.

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

## Facts

| | |
| --- | --- |
| Application | Metaview |
| Category | ATS |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Metaview builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | support.metaview.ai |
| 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 Metaview is connected

- Summarize what came up across Sarah Chen's interviews this week
- Which questions did the panel ask about leadership for the PM role?
- Show sourcing activity for the Backend Engineer search since Monday

## Connect Metaview in Elaichi

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

1. Open Connections, choose Add connection, and pick Metaview.
2. Optionally set Share with, then press Connect.
3. Approve it in Metaview. Metaview'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 Metaview tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Metaview 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.

## Metaview 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.

## Metaview 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 Metaview 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 Metaview 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 Metaview through Elaichi

### Catch up on a candidate before debrief

Recruiting. Ask for what came up across a candidate's interviews and get the themes pulled from the transcripts and notes in Metaview, not a memory of who said what.

### Check what the panel actually asked

Hiring managers. See which questions each interviewer covered for a role so the next round fills the gaps instead of repeating them.

### Review this week's sourcing activity

Talent sourcing. Pull outreach and pipeline numbers from Metaview reporting for a role and compare them with last week without opening a dashboard.

### Find the moment a candidate explained a decision

Interviewers. Search a transcript for a specific topic, like how the candidate handled a missed deadline, and read that part of the conversation.

### Spot inconsistent interviewing across teams

People. Look at how interviews run for the same role across different panels to see where structure, question coverage or depth drifts.

### Get a hiring update in plain language

Leadership. Ask how a critical search is going and get interview volume, sourcing activity and recurring candidate feedback summarized from Metaview.

## Elaichi vs Zapier MCP vs Composio for Metaview

All three can connect Metaview 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 Metaview tools | Allow or restrict single Metaview 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 Metaview 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 Metaview to Claude?

Connect Metaview in Elaichi first, then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. The Metaview step is a standard sign-in screen: you log in with your Metaview account and approve access, and there is no client ID or secret to generate. Once that is done, Claude can search interview transcripts and notes in Metaview as you.

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

Yes. Connect Metaview once in Elaichi and the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any MCP client and the Elaichi Agent. You do not set Metaview up again for each one.

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

It can search interview conversations, transcripts and notes in Metaview, pull out themes across a candidate's interviews, and review sourcing activity and reporting for a role. Short, concrete asks work best, such as the questions one interviewer asked about leadership, rather than long open-ended requests. What is available depends on what your account has set up in Metaview.

### Does connecting Metaview give the AI every interview and every candidate?

No. The AI works inside the Metaview access of the person who signed in, so an interviewer who can only see their own interviews gets only those, and nobody gets more than Metaview already allows them. Elaichi can narrow that further for a team and never widens it.

### Can my team share one Metaview connection?

Yes. One person connects Metaview in Elaichi and shares it with a team, and nobody else handles a credential or signs in to Metaview separately. Each teammate still signs in to Elaichi as themselves, so the audit log names the person who searched a transcript, not the person who set up the connection.

### Can I stop an agent from changing things in Metaview?

Yes. Restrictions in Elaichi apply per action, so you can limit a team to searching transcripts and reviewing reports in Metaview and nothing more. A restricted action is never shown to Claude, ChatGPT or any other client, so no prompt can reach it.

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

Offboarding that person in Elaichi ends their Metaview access through every client at once. A shared Metaview connection keeps working for everyone else on the team. If you disconnect Metaview in Elaichi, it is removed from Claude, ChatGPT, Cursor and every other client in one step.

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

Yes. Metaview 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 Metaview?

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

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

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