# Plaud MCP connector The Plaud connector brings your Plaud recordings, notes and transcripts to Claude, ChatGPT, Cursor and the Elaichi Agent, so you can ask about any conversation you recorded and get answers drawn from the transcript itself. Source: https://elaichi.ai/connectors/plaud/ ## Facts | | | | --- | --- | | Application | Plaud | | Category | Conversational Intelligence | | AI tools | 5 | | Authentication | Connects over OAuth | | Bring your own OAuth app | No | | Native MCP | Yes. Plaud builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top | | Support for its tools | support@plaud.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 | ## Why connect Plaud's MCP server through Elaichi Plaud builds and runs this MCP server. Elaichi sits in front of it, so Plaud'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 Plaud's server directly, outside Elaichi, get none of this. - **One address for every AI client.** Claude, ChatGPT and Cursor reach Plaud's tools at https://api.elaichi.ai/mcp, the same address as every other connected app. Nobody adds Plaud'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 Plaud 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 Plaud's server. By default, a tool Plaud 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 Plaud.** Plaud builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the Plaud team. Contact: [support@plaud.ai](mailto:support@plaud.ai). More: [why run a vendor's MCP server through Elaichi](https://elaichi.ai/blog/vendor-mcp-servers-through-elaichi/) ## What you can ask once Plaud is connected - Summarize yesterday's call with Acme into three follow-ups - Find the transcript where the customer asked about pricing - Pull the action items from Tuesday's leadership meeting notes ## Connect Plaud in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Plaud. 2. Optionally set Share with, then press Connect. 3. Approve it in Plaud. Plaud'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 Plaud tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Plaud 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. ## Plaud 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. ## Plaud 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 Plaud 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 Plaud 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 Plaud through Elaichi ### Catch the deal up after a call Sales. Ask for the transcript of this morning's call with a prospect and get the objections, the pricing questions and the next steps pulled out before you update the deal. ### Find what the customer actually said Support. Search your Plaud files for the escalation call and have the agent quote the exact wording of the complaint, so the handoff note is accurate. ### Prepare for a renewal in minutes Customer success. Pull every recorded conversation with an account this quarter and ask for the recurring themes, the promises made and the open risks. ### Turn interview recordings into structured feedback People. Ask for the transcript of each candidate interview and get the answers to the scorecard questions laid out side by side. ### Mine customer interviews for patterns Product. Point the agent at a set of research call notes and ask which feature requests came up most and who raised them. ### Get the gist of a meeting you missed Leadership. Ask for the notes and transcript from yesterday's leadership meeting and get the decisions, the owners and the deadlines in a short brief. ## Elaichi vs Zapier MCP vs Composio for Plaud All three can connect Plaud 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 Plaud tools | Allow or restrict single Plaud 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 Plaud 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 Plaud to Claude? Connect Plaud in Elaichi first: you sign in to your Plaud account with OAuth, the same way you would sign in to Plaud on the web, and there is no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Claude asks you to sign in to Elaichi once, and from then on it can read your Plaud recordings, notes and transcripts as you. ### Does Plaud work with ChatGPT and Cursor as well as Claude? Yes. Once Plaud 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 Plaud once and add the endpoint to whichever clients your team uses. ### What can an AI agent actually do with my Plaud data? With Plaud connected, an agent can list your recorded files, open a specific recording, read the notes Plaud produced for it and read the full transcript. That means you can ask for a summary of a call, the exact words a customer used, or the action items from a meeting, and the answer comes from the transcript rather than from memory. Short, specific asks such as naming the meeting or the day work better than long instructions. ### Does connecting Plaud give the AI access to every recording in my account? An agent sees the Plaud recordings the person who signed in can see, and nothing more. Elaichi can narrow that further, for example limiting a team to reading transcripts only, but it can never widen access beyond what your Plaud account already allows. ### Can my team share one Plaud connection? Yes. One person connects Plaud in Elaichi and shares it with a team, and nobody else ever handles a credential or signs in to Plaud themselves. Each person still signs in to Elaichi as themselves, so the audit log names who read which transcript. ### Can I stop an agent from deleting or changing things in Plaud? The Plaud connector only reads: it lists files and returns notes and transcripts, and it has no way to delete or edit a recording. Elaichi restrictions also apply per action, so if you want a team to read notes but not full transcripts, that action is left out of the tool list the AI client sees and cannot be called, whatever the prompt says. ### What happens to a Plaud connection when someone leaves? When you offboard someone in Elaichi, their access to Plaud through every AI client ends at once. A Plaud connection they shared keeps working for everyone else on the team. If you want the connector gone entirely, disconnecting Plaud once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time. ### Does the Plaud MCP connector work with Gemini, Codex, Claude Code or other MCP clients? Yes. Plaud 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 Plaud? Yes. Both let Claude, ChatGPT or Cursor use Plaud. 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 Plaud call. ### How is Elaichi different from Composio for Plaud? 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 Plaud: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call. ## All 5 Plaud tools Every tool below is callable through https://api.elaichi.ai/mcp once Plaud is connected, subject to the toolbox it is in and the restrictions on the caller. - **Get current user** (Get). Shows the details of the Plaud account you signed in with. - **List files** (List). Lists your recordings. Filter by a keyword in the recording name (query) and a date range (date_from, date_to as YYYY-MM-DD), or page through all of them. - **Get file** (Get). Returns full details for a single recording. - **Get note** (Get). Returns the AI-generated summary, action items and key topics for a recording. - **Get transcript** (Get). Returns the full transcript of a recording, with timestamps and speaker labels.