Connect Any AI Assistant

Stori speaks the Model Context Protocol, so it is not tied to one assistant. Claude, ChatGPT, Gemini, Cursor or your own code can work in your workspace, under the same permissions your admin sets.

Two Ways to Connect

Every assistant connects to the same address. What differs is how it proves who it is.

  • Sign-in (OAuth): the assistant opens a Stori sign-in and you click Allow. Used by Claude and ChatGPT. Nothing to copy or store, and it can read and, within your permissions, act. See Connect Claude to Stori.
  • API key: you paste a key into a settings file. Used by Gemini CLI, Cursor, the OpenAI API, and anything you build yourself. A key you create in Stori reads your jobs, candidates and credit balances; to make changes, connect with sign-in.

Both are locked to your workspace and both sit under the ceiling your admin sets in Settings > Integrations > AI Apps.

https://www.onestori.com/api/mcp

The setup steps for Claude, ChatGPT, Gemini and Slack are also in Stori under Settings > Integrations > AI Apps: pick the assistant and its steps appear, with the address ready to copy.

Create an API Key

Workspace admins create keys at the foot of Settings > Integrations > AI Apps, under API keys.

  1. Click New key.
  2. Under What is this key for?, name it after where it will live. "Cursor, Priya" beats "key 2" when you come to revoke it.
  3. Under Access, tick what it may read: Jobs, Candidates and Credits.
  4. Click Create key and copy it. It is shown once and never again; Stori keeps only a fingerprint of it. Click I have saved it when you have.

A key is a workspace credential: anyone holding one with Candidates ticked can read every candidate you have interviewed. Treat it like a password, keep it out of shared documents and source control, and revoke it the moment a laptop or a person leaves.

ChatGPT

ChatGPT connects by sign-in, with no key:

  1. In ChatGPT > Settings > Apps & Connectors, open Advanced settings and turn on Developer mode.
  2. Choose Create, name it Stori, paste the address above and pick OAuth.
  3. Sign in with your Stori company workspace account and click Allow.

Stori is in review for the ChatGPT app directory. Once it is listed you can add it from there instead, without developer mode.

For your own assistant on the OpenAI Responses API, add Stori as a remote MCP tool with a key:

{
  "type": "mcp",
  "server_label": "stori",
  "server_url": "https://www.onestori.com/api/mcp",
  "headers": {
    "Authorization": "Bearer sk_live_your_key_here"
  }
}

Google Gemini

  1. Have an admin create an API key, as above.
  2. Add this to Gemini CLI's settings file, ~/.gemini/settings.json, with your key in place of the placeholder.
  3. Restart Gemini CLI and run /mcp to see the Stori tools.
{
  "mcpServers": {
    "stori": {
      "httpUrl": "https://www.onestori.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk_live_your_key_here"
      }
    }
  }
}

Gemini Enterprise and the Gemini SDKs connect the same way: point them at the address with the key as a bearer token.

Cursor

The quickest route is the one-click install link, which fills in the server for you; you add your key afterwards:

Add Stori to Cursor

Or add it by hand to .cursor/mcp.json in your project, or ~/.cursor/mcp.json to have it everywhere:

{
  "mcpServers": {
    "stori": {
      "url": "https://www.onestori.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk_live_your_key_here"
      }
    }
  }
}

Restart Cursor and the Stori tools appear in the MCP panel.

Claude Code

claude mcp add stori --transport http https://www.onestori.com/api/mcp --header "Authorization: Bearer sk_live_your_key_here"

Anything Else

Stori implements MCP over Streamable HTTP, stateless, supporting protocol versions 2024-11-05, 2025-03-26 and 2025-06-18. Any compliant client works: Claude Desktop, VS Code, Windsurf, Zed, n8n, or your own code. Point it at the address, send the key as a bearer token, and call tools/list.

To check a connection from a terminal:

curl -X POST https://www.onestori.com/api/mcp \
  -H "Authorization: Bearer sk_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

What a Connection Can and Cannot Do

A connected assistant reads your jobs, a job's pool or a person found by name or email, interview transcripts with quotes and timestamps, candidate reports, candidates side by side, and a pool ordered by strength of evidence. A sign-in connection also reads your pipeline and hiring numbers, outreach, interviews and offers.

Within the permissions your admin has switched on, a sign-in connection can also add notes, move candidates, reject with a reason, create and edit roles, invite to interview and schedule, draft offers against the salary band and route them for approval, source candidates externally, reveal contact details, and draft or send outreach. Every change is written to the audit log against the person whose connection made it.

It cannot:

  • See any other company's data: access is locked to your workspace
  • Send an offer to a candidate: that stays a deliberate act in the app
  • Read pay from a list of offers: figures appear only for a single offer
  • Go past the workspace ceiling: a capability switched off in Settings is refused, whatever the key or sign-in was approved for

Candidate reports and transcripts open per candidate, on the same terms as in the app. A candidate you have not unlocked returns their identity and a note explaining what would release the rest.

Revoking Access

Both kinds of access are revoked in the same place, Settings > Integrations > AI Apps: Disconnect a sign-in connection under Connected apps, or Revoke an API key under API keys. Either takes effect at once; the next request from that assistant is refused.

Each key shows when it was created and last used, which is the quickest way to spot one nobody needs any more.