Herd Security MCP connector

Connect Herd Security in Elaichi first: pick it from the catalog and paste in a Herd Security API key, since that is how Herd Security signs in. 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 the endpoint https://api.elaichi.ai/mcp. Sign in to Elaichi when prompted and Herd Security enrollments, users, tags, and tag trainings are available in Claude.

Yes. Once Herd Security 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 Herd Security once and every client picks it up.

With Herd Security connected, an agent can list your enrollments, list your users, list your tags, and list the trainings attached to each tag. That means you can ask who is enrolled, which people are in Herd Security, how users are grouped, and what training a given group receives, then have the answer summarized in plain language. This connector reads from Herd Security; it does not create or change anything there.

No. A Herd Security connection carries the access of the API key it was set up with, and every request runs inside that access, so the agent sees no more of Herd Security than that key allows. Elaichi can narrow what is exposed further, for example by leaving out enrollments for a particular team, but it can never widen access beyond what Herd Security itself permits.

Yes. One person connects Herd Security with the API key and shares the connection with a team in Elaichi, and nobody else on that team ever sees or handles the key. Each teammate still signs in to Elaichi as themselves, so the audit log names the actual person behind every Herd Security request.

This Herd Security connector only lists enrollments, users, tags, and tag trainings, so there is nothing in it that deletes or changes records. Beyond that, Elaichi restrictions work per action, and any action you block is never advertised to Claude, ChatGPT, Cursor, or any other client. A blocked action cannot be reached by any prompt because the AI does not know it exists.

When you offboard a person in Elaichi, their access to Herd Security through Elaichi ends at once, in every client they had connected. If they shared a Herd Security connection with a team, that connection keeps working for everyone else. If you want to remove Herd Security entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client together.

Yes. Herd Security 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.

Yes. Both let Claude, ChatGPT or Cursor use Herd Security. 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 Herd Security call.

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