# Hyperbound MCP connector Connect Hyperbound to Elaichi and Claude, ChatGPT or Cursor can review your calls, reps, teams and scorecards, ask Kota for coaching advice, and create bots and scorecards, with every call running as the person who signed in. Source: https://elaichi.ai/connectors/hyperbound/ ## Facts | | | | --- | --- | | Application | Hyperbound | | Category | Sales Intelligence | | Authentication | Connects over OAuth | | Bring your own OAuth app | No | | Native MCP | Yes. Hyperbound builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top | | Support for its tools | support.hyperbound.ai/articles/8696502812-hyperbound-mcp-server | | 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 | ## Why connect Hyperbound's MCP server through Elaichi Hyperbound builds and runs this MCP server. Elaichi sits in front of it, so Hyperbound's tools follow the same sign-in, access rules and audit log as every other connector your organization uses. Calls an AI client makes to Hyperbound's server directly, outside Elaichi, get none of this. - **One address for every AI client.** Claude, ChatGPT and Cursor reach Hyperbound's tools at https://api.elaichi.ai/mcp, the same address as every other connected app. Nobody adds Hyperbound's server to each client one by one. - **Each person signs in as themselves.** Each person signs in to Elaichi as themselves. Members connect with their own Hyperbound sign-in, and a connection someone shares runs on its owner's account. The credential stays in Elaichi's separate credential service, and the AI client holds only its Elaichi sign-in. - **Rules checked before a call leaves.** Restrictions on a role or a person, for the whole connector or a single tool, are checked before a call reaches Hyperbound's server. By default, a tool Hyperbound does not mark read-only or non-destructive counts as destructive, and over MCP it needs the "Delete data and remove access" consent. - **One audit log for every app.** Each call that runs is recorded with the person, the tool, the connection and the AI client that made it, in the same audit log as every other app. - **Tool issues go to Hyperbound.** Hyperbound builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the Hyperbound team. Contact: [support.hyperbound.ai/articles/8696502812-hyperbound-mcp-server](https://support.hyperbound.ai/articles/8696502812-hyperbound-mcp-server). More: [why run a vendor's MCP server through Elaichi](https://elaichi.ai/blog/vendor-mcp-servers-through-elaichi/) ## What you can ask once Hyperbound is connected - Which reps scored lowest on discovery calls this week? - Ask Kota how I can handle the pricing objection better. - Create a scorecard for the new cold call bot. ## Connect Hyperbound in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Hyperbound. 2. Optionally set Share with, then press Connect. 3. Approve it in Hyperbound. Hyperbound'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 Hyperbound tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Hyperbound 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. ## Hyperbound MCP connector for Claude Code Endpoint: https://api.elaichi.ai/mcp 1. In a terminal, run `claude mcp add` with the endpoint. 2. Start Claude Code and run `/mcp`. 3. Pick elaichi, then sign in and approve in the browser. ```bash claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp ``` Use `--scope project` instead to share it with the repository through `.mcp.json`. ## Hyperbound 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. ## Hyperbound 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 Hyperbound 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 Every scope the client asks for starts ticked except "Delete data and remove access", which you tick yourself. Calling a Hyperbound tool needs "Run your connected tools". 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. Think hard before granting Delete, which reaches into connected apps and cannot be undone. ## What teams do with Hyperbound through Elaichi ### Get coaching on last night's practice call Sales. A rep asks what went wrong on their discovery roleplay and gets the scorecard breakdown plus Kota's advice on the objection they fumbled, without opening Hyperbound. ### Spot which reps need attention this week Sales management. A manager asks which reps on the team scored lowest on cold calls this week and gets names, scores and the skills that slipped, ready for the one-on-one. ### Build a bot for the new pitch Enablement. An enablement lead describes the persona and objections they want reps to practice against and has the bot and its folder created in Hyperbound while they are still in the chat. ### Update a scorecard after the messaging change Enablement. When the talk track changes, the criteria on the affected scorecard are updated from a plain request instead of a click-through edit in Hyperbound. ### Compare team call performance across regions Revenue operations. RevOps asks how the EMEA and US teams compare on scorecard results this quarter and gets a summary they can paste into the pipeline review. ### Review a candidate's screening roleplay Recruiting. A hiring manager asks for the scores and highlights from a candidate's Hyperbound screening call and decides whether to move them forward. ## Elaichi vs Zapier MCP vs Composio for Hyperbound All three can connect Hyperbound 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 Hyperbound tools | Allow or restrict single Hyperbound 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 Hyperbound 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 Hyperbound to Claude? Connect Hyperbound in Elaichi first: pick it from the connector list, sign in to your Hyperbound account over OAuth, and approve. There is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Hyperbound is now available in Claude as you. ### Does Hyperbound work with ChatGPT and Cursor as well as Claude? Yes. The same Elaichi endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any MCP client and the Elaichi Agent. Connect Hyperbound once in Elaichi and every client picks it up. ### What can an AI agent actually do with my Hyperbound data? It can look at your Hyperbound calls, reps, teams and scorecards and tell you how a call went, which reps are slipping and how teams compare. It can ask Kota for coaching advice on a specific call or skill. It can also create or update bots, scorecards and folders in Hyperbound from a plain request. Short, concrete asks work better than long paragraphs. ### Does connecting Hyperbound give the AI everything in my workspace? No. The AI acts as the person who signed in to Hyperbound, so it sees the calls, reps, teams and scorecards that person can already see and nothing more. Elaichi can narrow that further by role and restriction, and it never widens it beyond what Hyperbound itself allows. ### Can my team share one Hyperbound connection? Yes. One person connects Hyperbound in Elaichi and shares it with a team, and nobody else ever handles a credential. Each teammate still signs in to Elaichi as themselves, so the audit log names the person who reviewed a call or edited a scorecard, not the person who connected the account. ### Can I stop an agent from deleting or changing things in Hyperbound? Yes. Restrictions in Elaichi apply per action, so you can allow reading Hyperbound calls and scorecards while blocking changes to bots, scorecards or folders. A restricted action is left out of the tool list the AI client sees and cannot be called, whatever the prompt says. ### What happens to a Hyperbound connection when someone leaves? Offboarding someone in Elaichi ends their access to Hyperbound through every AI client at once. If they had shared a Hyperbound connection with a team, it keeps working for everyone else. Disconnecting Hyperbound once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together. ### Does the Hyperbound MCP connector work with Gemini, Codex, Claude Code or other MCP clients? Yes. Hyperbound 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 Hyperbound? Yes. Both let Claude, ChatGPT or Cursor use Hyperbound. 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 Hyperbound call. ### How is Elaichi different from Composio for Hyperbound? 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 Hyperbound: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.