Plaud MCP connector for AI agents

CALL ANY TOOL

List recordings and pull transcripts and notes with the signed-in user's own Plaud access, so transcription stays private to its owner.

plaudmcp_get_current_user

Get current user

Get details of the currently authenticated Plaud account.

Parameters

Name

Type

Required

Description

—

No parameters required

plaudmcp_get_file

Get file

plaudmcp_get_note

Get note

plaudmcp_get_transcript

Get transcript

plaudmcp_list_files

List files

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Plaud MCP tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["plaudmcp"], toolNames: [
    "plaudmcp_get_current_user",
    "plaudmcp_get_file",
    "plaudmcp_get_note"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Is the Salesforce sync healthy?" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["plaudmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which data sources are connected?" }],
  tools,
});

// Execute the tool call with the user's vaulted Plaud MCP credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["plaudmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Pull open Zendesk tickets created this week." }],
  tools,
});

// Tool call runs with the user's vaulted Plaud MCP credential
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["plaudmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "plaudmcp_agent",
  model: "gemini-2.5-pro",
  instruction: "Work with Plaud MCP for the signed-in user.",
  tools,
});

await agent.run("What auth does the Shopify connector need?");

Try these prompts

Paste any prompt into your agent to get started.

Recall

Copy the prompt

Copied

What did we commit to in yesterday's recording?

Copy the prompt

Copied

Summarise this transcript into action items.

Copy the prompt

Copied

Find the recording where we discussed pricing.

Notes

Copy the prompt

Copied

Get the note attached to this recording.

Copy the prompt

Copied

Turn this transcript into a follow-up email.

Copy the prompt

Copied

List my recordings from the last week.

Account

Copy the prompt

Copied

Who am I connected as?

Copy the prompt

Copied

Get the file details for this recording.

Copy the prompt

Copied

List the files available to me.

SEE HOW AUTH WORKS

Your users connect Plaud once. Their credentials stay vaulted, every call is scope checked, and every transcript read is logged.

1

Authorize

Your user connects

Plaud MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Plaud MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Plaud MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Plaud MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

GTM and RevOps Teams

Sales call prep agent

Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

People Ops and HR teams

Performance review collector

Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.

Test other agents

See the same per-user auth pattern across other connectors.

OPS

Meeting prep agent

Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.

SALES

Sales call prep agent

Read tomorrow's calls from Google Calendar, mine Granola notes and Attio history, and deliver each rep a prep brief in Slack.

SALES

Deal intelligence agent

Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.

PEOPLE OPS

Performance review collector agent

Collect review feedback from Airtable and Google Forms per manager, summarise each report in Notion, and DM the digest in Slack.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Plaud MCP token looks fine in a demo. In production every action looks like one service account, and you cannot tell who wired a source or ran a query. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Plaud MCP today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Can the agent read another person's recordings?

No. Plaud evaluates the user's own access at request time, so an agent can only reach recordings that user already owns.

What does OAuth 2.1 with DCR change here?

Your client registers dynamically rather than through a manual app setup, and the user consents once. Scalekit handles the registration and the refresh.

How many tools does this connector expose?

5: current user, files list, file, note, and transcript. Small surface, all read.

Is transcript text stored by Scalekit?

No. Scalekit brokers the authenticated call. The transcript flows to your agent, and the credential is never placed in LLM context.

How are credentials isolated across customers?

Per tenant and per user in an encrypted vault, resolved at request time.

Plaud MCP

Tools your agent reaches for on Plaud, scoped per user.