OtterAI MCP

CALL ANY TOOL

OAuth-scoped per user. Every transcript and action item access attributed to the authorizing team member.

otterai_recordings_search

Search recordings

Search the authorizing user's OtterAI recordings by keyword, date range, participant, or meeting title.

Parameters

Name

Type

Required

Description

query

string

Optional

Keyword or phrase to search in transcripts

from_date

string

Optional

Start date for recording search (ISO 8601)

to_date

string

Optional

End date for recording search (ISO 8601)

limit

integer

Optional

Max recordings to return

otterai_transcript_get

Get transcript

otterai_action_items_get

Get action items

otterai_summary_get

Get meeting summary

otterai_speakers_get

Get speakers

Build your Agent

Drop the toolkit in, point it at the authorized team member, and your agent can pull meeting transcripts and action items from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["assemblyaimcp"], toolNames: ["assemblyai_transcript_submit", "assemblyai_transcript_get", "assemblyai_transcripts_list"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["assemblyaimcp"], toolNames: ["assemblyai_transcript_submit", "assemblyai_transcript_get", "assemblyai_transcripts_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["assemblyaimcp"], toolNames: ["assemblyai_transcript_submit", "assemblyai_transcript_get", "assemblyai_transcripts_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/assemblyaimcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your meeting agent to start pulling transcripts and action items from OtterAI MCP.

Search & recall

Copy the prompt

Copied

List all meeting transcripts from this week with [customer or team name].

Copy the prompt

Copied

Get all action items from the [meeting name] transcript.

Copy the prompt

Copied

Search my transcripts for mentions of [topic or keyword].

Summarize & extract

Copy the prompt

Copied

Summarize the key decisions and next steps from the [meeting name] recording.

Copy the prompt

Copied

Extract all open action items assigned to [name] across last month's meetings.

Copy the prompt

Copied

Get the full transcript for meeting ID [meeting-id] and find any pricing discussions.

SEE HOW AUTH WORKS

Team members authorize OtterAI once. Their OAuth token stays vaulted, every call is scoped to their meetings, and every query is logged.

1

Authorize

Your user connects

OtterAI 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

OtterAI 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

OtterAI 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

OtterAI 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

Same per-user auth pattern across other meeting intelligence and transcription connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

One vault for every meeting tool. OtterAI today, Gong and Fathom tomorrow.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

OtterAI MCP today. Others 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

Does the agent access OtterAI recordings as the user or a shared account?

As the user. Each team member authorizes once via OAuth and Scalekit resolves their credential at request time. The agent only accesses recordings and transcripts that belong to the authorizing user's OtterAI account.

Where is the OtterAI OAuth token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM completions.

Can I prevent the agent from accessing sensitive meeting transcripts?

Yes. Use listScopedTools to allow action item retrieval but block full transcript access for specific users or roles. You can also gate access to recordings from specific meeting types like board or investor calls.

What happens when a user revokes OtterAI access?

The connection is invalidated on the next tool call for that user. Subsequent requests fail closed. Other users remain unaffected. The revocation event is logged for audit.

Can the agent create tasks from OtterAI action items in other tools like Jira or Linear?

Yes. A single agent can pull action items from OtterAI and create issues in Linear, Jira, or Asana in one workflow. Each connector resolves under the same user identity with its own vaulted credential.

Tools your meeting agent reaches for on OtterAI, scoped per team member.