Connect your AI Agents to Plaud in minutes
Available tools
list_recordings
List the authenticated user's Plaud recordings. Optional input fields: page (default 1), page_size (default 20, min 10), query (case-insensitive name match), date_from/date_to (YYYY-MM-DD). When query or a date filter is set, all matches return and page/page_size are ignored. Returns items with id, name, created_at, start_at, and duration (ms). Use get_recording for full details.
get_recording
Get the full record for one Plaud recording by file_id: id, name, created_at, start_at, duration (milliseconds), presigned_url (audio download link that expires in 24 hours, re-fetch if stale), source_list (the transcript), and note_list (AI notes, summary as Markdown). Use list_recordings to find a file_id. Raises a not-found error if the file_id does not exist.
get_recording_notes
Get the AI-generated notes for a Plaud recording by file_id, usually the fastest way to get a summary or action items (prefer over the full transcript). Returns notes under 'notes'; the 'auto_sum_note' item holds the summary as Markdown in data_content. May be empty if no notes exist. Use list_recordings to find a file_id; a missing file_id raises a not-found error.
get_recording_transcript
Get the timestamped transcript for a Plaud recording by file_id. Use for verbatim dialogue or speaker attribution rather than a summary (larger than get_recording_notes; prefer notes when a summary suffices). Returns source items under 'sources'; the 'transaction' item's data_content is a JSON string of segments {start_time, end_time, content, speaker}. Use list_recordings to find a file_id.
get_current_user
Get the profile of the currently authenticated Plaud user: id, email, nickname, and avatar. Use to confirm who is signed in before listing or reading recordings. Raises an authentication error if the connection is missing or expired.
validate_credential
Validate the connected Plaud account by fetching the authenticated user. Returns an object with 'success' (bool) and 'message' (str). Use this to confirm the connection works before listing or reading recordings.
How to set up Merge Agent Handler
In an mcp.json file, add the configuration below, and restart Cursor.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5 "headers": {
6 "Authorization": "Bearer yMt*****"
7 }
8 }
9 }
10}
11Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.
Make sure Claude is using the Node v20+.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "yMt*****"
14 }
15 }
16 }
17}Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "<ah-production-access-key>"
14 }
15 }
16 }
17 }In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".
You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.
Learn more in the official documentation ↗
1{
2 "inputs": [
3 {
4 "type": "promptString",
5 "id": "agent-handler-auth",
6 "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7 "password": true
8 }
9 ],
10 "servers": {
11 "agent-handler": {
12 "type": "stdio",
13 "command": "npx",
14 "args": [
15 "-y",
16 "mcp-remote@latest",
17 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18 "--header",
19 "Authorization: Bearer ${input:agent-handler-auth}"
20 ]
21 }
22 }
23}FAQs on using Merge's Plaud MCP server
FAQs on using Merge's Plaud MCP server
What is a Plaud MCP?
It's an MCP server that connects your agents to a Plaud account through tools. Your agents can invoke them to search recordings, read speaker-labeled transcripts, pull AI-generated summaries, export documents from a recording, and more.
Plaud offers an official MCP server, but you can also use one from a third-party platform, like Merge Agent Handler.
How can I use the Plaud MCP server?
The use cases naturally depend on the agent you've built, but here are a few common ones:
- Post-call CRM updates: after a sales call is recorded in Plaud, an agent can pull the transcript, extract next steps and objections, and log them against the matching opportunity in your CRM
- Meeting summary distribution: an agent can take a recording's summary and send a recap with action items to attendees over email or Slack
- Research synthesis across calls: an agent can search a set of user-interview recordings for a theme and combine the relevant excerpts into a single findings document
- Transcript lookups on demand: a teammate can ask their AI what was decided in a specific meeting, and the agent retrieves the transcript and answers from it
What are popular tools for Plaud's MCP server?
Here are some of the most commonly used tools:
list_recordings: returns recordings filtered by date or label. Useful for agents that need to find the right session before acting on it
get_transcript: returns the full speaker-labeled transcript for a recording. Call this when an agent needs the verbatim contents of a conversation
get_summary: returns the AI-generated summary of a recording. Use this when an agent needs the gist rather than the full transcript
search_recordings: searches across recordings for a keyword or topic. Good for workflows that pull every conversation touching a given subject
export_document: generates a formatted document from a recording, such as meeting notes. Helpful when an agent produces a shareable artifact from a call
get_recording: returns metadata and audio details for a single recording. Useful for agents that need the context around a session before processing it
What makes Merge Agent Handler's Plaud MCP server better than alternative Plaud MCP servers?
Choosing Merge Agent Handler's Plaud MCP server over a self-built or community option comes down to a few things:
- Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Plaud, this means transcript contents and the personal information discussed in a meeting can be redacted before they ever reach the agent
- Managed authentication and credentials: Merge stores and refreshes Plaud credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or handle token rotation yourself
- Real-time observability and audit trail: Every tool call made against Plaud is logged with timestamp, tool name, input parameters, and response metadata. You can see exactly which recordings and transcripts an agent accessed without building logging yourself
- Tool Packs and controlled access: Tool Packs let you bundle specific Plaud tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more
How can I start using Merge Agent Handler's Plaud MCP server?
You can take the following steps:
1. Create or log into your Merge Agent Handler account.
2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.
3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.
4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Plaud and complete the auth flow. Merge stores and manages the credentials going forward.
5. Open a Claude Code session and start querying Plaud data directly. The first time you use a Plaud tool, a Magic Link may appear to complete connector authentication.
If you want to connect Merge Agent Handler's Plaud MCP with internal or customer-facing agentic products, you can follow the steps in our docs.
Can employees use Merge Agent Handler to connect their AI tools to Plaud?
Yes, Agent Handler for Employees lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Plaud without bypassing IT governance.
Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Agent Handler and gets individual credentials tied to their identity. A teammate can ask their AI to pull a call transcript, summarize a meeting, or draft notes from a recording, all within the permissions IT has defined.
IT also provisions access by role or group via SCIM. A sales rep, for example, gets Plaud access to pull call transcripts, Salesforce to log the conversation, and Gmail to send the follow-up; while a product manager gets Plaud access to review user-interview recordings, Linear to file feature requests, and Notion to write up the findings.
Every tool call an employee's AI makes to Plaud is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.
Ready to try it out?
Whether you're an engineer experimenting with agents or a product manager looking to add tools, you can get started for free now
