---
title: "Plaud MCP: Setup, Tool Reference, and Limits | Kylon"
description: "A technical guide to Plaud MCP: install paths for Claude, Cursor and ChatGPT, the seven tools it exposes, the fields list_files and get_file return, pagination and scan limits, and how to connect Plaud to a shared workspace."
url: "https://kylon.io/blog/plaud-mcp"
language: "en"
---

[HOME](https://kylon.io/)\>[Blog](https://kylon.io/blog)\>[Integrations & connections](https://kylon.io/blog/topics/integrations)\>Plaud MCP: How to Connect Your Recordings to an AI Agent

Guide9 min read

# Plaud MCP: How to Connect Your Recordings to an AI Agent

Plaud MCP lets any MCP-compatible client read your recordings, transcripts, and AI notes. Here is the actual tool surface, the fields each call returns, what the install does to your machine, and where the limits are.

Kylon TeamProduct

September 17, 2026

[A narrated line-art explainer of Plaud MCP: How to Connect Your Recordings to an AI Agent, with subtitles](https://static.purework.app/files/b9a51f119f14469d3b76beaf09106cb1/explainer-plaud-mcp.mp4)

Plaud sells a recorder and the cloud that transcribes it. The gap most teams hit is the next step: the meeting is captured, summarized, and then sits in an app nobody opens while writing the follow-up.

Plaud MCP closes that gap by exposing your account to an AI client as a set of callable tools. It has been generally available since [12 May 2026](https://docs.plaud.ai/plaud-mcp-cli/changelog.md), shipped as `@plaud-ai/mcp` alongside the `@plaud-ai/cli` terminal client.

This is a reference for what the connection actually gives an agent, written from Plaud's own documentation rather than the marketing page.

## What it is

MCP is a client-server protocol. Plaud runs the server, your AI client is the consumer, and the tools are the contract between them. Once connected, the client can ask your account questions mid-conversation rather than waiting for you to paste a transcript in.

Plaud positions MCP as the route for [extracting your own Plaud data](https://docs.plaud.ai/llms.txt), as distinct from Plaud Embedded, which is the SDK route for building a product on Plaud hardware. If you are evaluating the product route instead, that distinction is covered in our [Plaud Embedded and CRM workflow guide](https://kylon.io/blog/plaud-meeting-notes-to-crm).

## The tool surface

Seven tools, per [Plaud's MCP documentation](https://docs.plaud.ai/plaud-mcp-cli/mcp):

| Tool | What it does |
| --- | --- |
| `login` | Opens your browser for OAuth sign-in |
| `logout` | Signs out and revokes your authorization |
| `get_current_user` | Shows your current account details |
| `list_files` | Lists your recordings, with optional filters |
| `get_file` | Returns full details for a single recording |
| `get_note` | Returns the AI-generated summary, action items, and key topics |
| `get_transcript` | Returns the full transcript with timestamps and speaker labels |

Three of those are session management. The working surface is four calls: find recordings, open one, read its notes, read its transcript.

Worth stating plainly, because it decides whether this fits your workflow: nothing here writes. There is no documented tool to rename a recording, correct a transcript, or upload audio. Plaud MCP reads an archive that the device and the Plaud app have already produced.

## Filters and pagination

`list_files` accepts four parameters ([source](https://docs.plaud.ai/plaud-mcp-cli/mcp)):

| Parameter | Description |
| --- | --- |
| `query` | Case-insensitive keyword match on recording name |
| `date_from` | Start date, `YYYY-MM-DD` |
| `date_to` | End date, `YYYY-MM-DD` |
| `page` / `page_size` | Pagination, ignored when filters are set |

Two details matter more than they look.

The match is on the **recording name only**, not the transcript body. If your recordings are named "New Recording 14", search will not find the meeting where pricing came up. Naming discipline is what makes this connection useful.

Filtering is also a **scan**, not a query. The equivalent Plaud CLI search [scans up to the 500 most recent recordings](https://docs.plaud.ai/plaud-mcp-cli/cli.md), and the same budget applies here. An empty result for last March may mean the scan never reached March, not that nothing matched. Check how far back the scan went before treating a result as exhaustive.

## What comes back

`list_files` and `get_file` both return these fields ([source](https://docs.plaud.ai/plaud-mcp-cli/mcp)):

| Field | Type | Description |
| --- | --- | --- |
| `id` | string | Unique recording ID |
| `name` | string | Recording name |
| `created_at` | string | Creation time (ISO 8601) |
| `start_at` | string | Recording start time (ISO 8601) |
| `duration` | number | Duration in milliseconds |
| `serial_number` | string | Device serial number |

`get_file` adds three more:

| Field | Type | Description |
| --- | --- | --- |
| `presigned_url` | string | Temporary audio download URL, valid 24 hours |
| `source_list` | array | Transcript segments with timestamps and speaker labels |
| `note_list` | array | AI-generated notes in Markdown |

`presigned_url` is the one to plan around. It is a signed link with a 24 hour life, which makes it fine for an agent to fetch audio during a task and wrong to paste into a ticket as a permanent reference. Store the recording `id` instead and re-resolve the URL when you need it.

## Installing it

Prerequisites are Node.js 20 or higher and a Plaud account ([source](https://docs.plaud.ai/plaud-mcp-cli/mcp)). One command detects your clients, writes their MCP configuration, and opens a browser to authorize:

Terminal

```
npx -y @plaud-ai/mcp@latest install
```

Two flags are worth knowing: `--yes` configures every detected local client without prompting, and `--no-login` skips the browser step, which is what you want on a headless or remote machine.

Which clients are handled automatically, and what each needs afterwards:

| Client | Auto-configured | Restart after install |
| --- | --- | --- |
| Claude Desktop | Yes | Quit and reopen |
| Claude Code | Yes | Exit, then start a new `claude` session |
| Codex Desktop | Yes | Quit and reopen |
| Cursor, Windsurf, VS Code, Zed | Yes | Reload per client UI |
| Claude Web, ChatGPT Web | Interactive guide | No restart needed |
| Kiro | Yes | No restart needed |

A full restart is genuinely required for the desktop clients. Closing the window is not the same as quitting the app, and this is the most common reason the tools do not show up.

For a client the installer does not detect, the manual configuration is:

Terminal

```
{
  "mcpServers": {
    "plaud": {
      "command": "npx",
      "args": ["-y", "@plaud-ai/mcp@latest"]
    }
  }
}
```

## Skills that ship with it

The installer also loads six prewritten instruction sets, so common phrasings map to the right sequence of calls without you describing the workflow each time ([source](https://docs.plaud.ai/plaud-mcp-cli/mcp)):

| Skill | Triggered by asking for |
| --- | --- |
| `plaud-browse` | "list my recordings", "show recent files" |
| `plaud-find` | "find the Weekly Sync", "the meeting from Monday" |
| `plaud-read` | "show the transcript", "summarize this recording" |
| `plaud-digest` | "weekly report", "what meetings did I have this week" |
| `plaud-followup` | "draft a follow-up email", "list the action items" |
| `plaud-export` | "save to Notion", "post to Slack" |

## Where the data goes

For browser clients connecting over HTTP, Plaud states that recording data passes through its MCP server hosted in the US, and that Plaud does not store this data after the request completes, processing it in transit only, governed by [Plaud's privacy policy](https://plaud.ai/privacy) ([source](https://docs.plaud.ai/plaud-mcp-cli/mcp)).

If your recordings include client conversations, clinical discussions, or anything with a residency obligation, settle this before rollout rather than after. The local install path keeps the transport between your machine and Plaud, which is a different profile from the hosted HTTP path.

## MCP or the CLI

Both read the same account. They suit different jobs.

|  | Plaud MCP | Plaud CLI |
| --- | --- | --- |
| Shape | Tools an AI client calls mid-conversation | Commands you run in a terminal |
| Install | `npx -y @plaud-ai/mcp@latest install` | `npm install -g @plaud-ai/cli` |
| Good for | "Summarize Tuesday's standup and draft the follow-up" | Batch export, scripting, piping to a file |
| Output | Interpreted by the model | Clean stdout, errors to stderr |

The CLI is the better tool when you want determinism. It has [documented exit codes](https://docs.plaud.ai/plaud-mcp-cli/cli.md) (`2` for auth failure, `3` for network, `4` for timeout) and keeps stdout clean for piping, which makes it scriptable in a way a conversational tool call is not.

## Connecting Plaud to a shared workspace

The single-user install has a ceiling. It connects _your_ Plaud account to _your_ client on _your_ machine, so the meeting context stops at your laptop. When a colleague needs the same recording, you are back to copying a summary into a message.

In Kylon, Plaud is a workspace connection rather than a local config file. You authorize it once from an authorization card, and from then on the agents you grant access to can read your recordings inside the room where the work is already being discussed.

The connection exposes four tools, matching the read surface above:

-   `list_files` for finding recordings, with the same name-match and 500-record scan budget, plus an explicit flag on whether the scan was exhaustive
-   `get_file` for the full record, including the 24 hour audio URL
-   `get_note` for the notes, returning one entry per tab in the app, so the AI summary, any template tab, a saved Ask Plaud answer, and highlights come back separately
-   `get_transcript` for the timestamped transcript with real speaker names, paginated by cursor, with `outline`, `transaction_polish` and `mark_memo` blocks available for the outline, the polished text, and the moments flagged with the device's highlight button

There is no `login` tool in that list, because authorization is handled by the connection rather than by a tool call in the conversation.

What changes in practice is who can act on the recording. A transcript read in a room can become a CRM update, an issue record, and a follow-up draft that a colleague reviews in the same thread, instead of three manual copies. That routing pattern, including the review step that keeps a person on anything touching customer data, is covered in the [meeting notes to CRM workflow](https://kylon.io/blog/plaud-meeting-notes-to-crm).

## When it does not show up

Plaud's [troubleshooting table](https://docs.plaud.ai/plaud-mcp-cli/mcp) covers the common failures:

-   **Tools missing after install.** A full client restart is required. For Claude Code, exit and start a new `claude` session.
-   **`401` or "Not authenticated".** Ask the client "log me into Plaud".
-   **Token refresh errors.** Delete `~/.plaud/tokens-mcp.json` and sign in again.
-   **Browser does not open during sign-in.** Copy the printed URL and open it manually. On a remote machine, forward port 8199 first with `ssh -L 8199:localhost:8199 user@host`.
-   **"Server disconnected" in Claude Desktop.** Re-run `plaud-mcp unsetup && plaud-mcp setup`, then restart.

To upgrade, run `npm install -g @plaud-ai/mcp@latest` and restart the client. To remove it entirely, uninstall per client, then `npm uninstall -g @plaud-ai/mcp` and `rm -rf ~/.plaud`.

## Start with the naming problem

The connection works on day one. What limits its usefulness is almost never the protocol, it is that `list_files` matches on recording names and half the archive is called "New Recording".

Name recordings the way you would search for them, with the counterpart and the subject, and the difference in what an agent can retrieve is immediate.

If you want meeting context to reach the customer record and the delivery queue rather than stopping at one person's client, [book a Kylon consultation](https://cal.com/forms/5bd983bd-70e5-4afa-afd7-098b78cde6c3).

Your first company harness. Where humans and agents run your business together.

[Get started](https://app.kylon.io/sign-up)

## Keep reading

[More in Integrations & connections](https://kylon.io/blog/topics/integrations)

[

### Kylon + Missive: Six Use Cases for Teams That Run on Email

Missive is where your team answers customers together. Connect it to Kylon and an agent reads the conversation, checks the records behind it, and leaves a draft, a note and a next step in Missive for a person to finish.

Kylon TeamOctober 26, 2026

](https://kylon.io/blog/kylon-missive-integration)[

### Better together: how Kylon connects your agents and your tools

Our launch post names a few hundred agents and tools in one sentence. Here are the four ways each of them connects to Kylon, and what happens when they meet in the same room.

Kylon TeamOctober 12, 2026

](https://kylon.io/blog/how-kylon-connects-agents-and-tools)[

### Kylon + Plaud: Six Use Cases for the Meetings That Happen in Person

Online calls get a notetaker bot. Site visits, client lunches and workshops get Plaud. Here are six ways to turn a Plaud recording from a meeting with no link into tasks, CRM updates and an approved follow-up in Kylon.

Kylon TeamOctober 3, 2026

](https://kylon.io/blog/kylon-plaud-integration)