# Herd Security MCP connector The Herd Security connector brings enrollments, users, tags, and tag trainings into Claude, ChatGPT, Cursor, and the Elaichi Agent, so each person can ask about security training coverage within their own access, with every request logged. Source: https://elaichi.ai/connectors/herdsecurity/ ## Facts | | | | --- | --- | | Application | Herd Security | | Category | Security | | AI tools | 4 | | 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 Herd Security is connected - Which users have open Herd Security enrollments this month? - List tag trainings assigned to the Contractors tag. - Show Herd Security users with no completed training. ## Connect Herd Security in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Herd Security. 2. Optionally set Share with, then press Connect. 3. Paste a Herd Security API key. One person generates a token in Herd Security 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 Herd Security tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Connect Herd Security 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 Herd Security 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 Herd Security 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 Herd Security 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 Herd Security 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 Herd Security through Elaichi ### Check who is enrolled in training Security. Ask which users are enrolled in Herd Security training before the quarterly review, and spot anyone who has not been picked up yet. ### Confirm new hires appear in Herd Security IT. Pull the Herd Security user list after a batch of new starters and compare it against the accounts you provisioned that week. ### Gather training coverage for an audit Compliance. List enrollments and the trainings attached to each tag so the evidence an auditor asks for is ready without logging in to export it. ### See which trainings a group receives People. Ask what trainings apply to a tag such as a department or office, so you can tell a manager exactly what their team is assigned. ### Find tags with nothing assigned Security. List every Herd Security tag alongside its trainings to catch groups of users who have no training tied to them. ### Answer a manager's training question fast Operations. When a team lead asks whether their people are covered, pull the enrollments for that group and reply in the same conversation. ## Frequently asked questions ### How do I connect Herd Security to Claude? 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. ### Does Herd Security work with ChatGPT and Cursor as well as 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. ### What can an AI agent actually do with my Herd Security data? 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. ### Does connecting Herd Security give the AI access to everything in my account? 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. ### Can my team share one Herd Security connection? 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. ### Can I stop an agent from deleting or changing things in Herd Security? 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. ### What happens to a Herd Security connection when someone leaves? 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. ## All 4 Herd Security tools Every tool below is callable through https://api.elaichi.ai/mcp once Herd Security is connected, subject to the toolbox it is in and the restrictions on the caller. - **List all Herd Security enrollments** (List). List all training enrollments and completion statuses for your herdsecurity organization. Returns: enrollment_id, user_id, tag_id, training_id, enrollment_date, completion_date, status. - **List all Herd Security users** (List). List users in herdsecurity for your organization. Returns: user_id, first_name, last_name, email, status. - **List all Herd Security tags** (List). List all tags used to categorize trainings in your herdsecurity organization. Returns: tag_id, name, status, start_date, end_date, created_at. - **List all Herd Security tag trainings** (List). List all trainings associated with a specific tag in herdsecurity. Returns: training_id, title, description. Required: tag_id.