Dovetail connector for AI agents

CALL ANY TOOL

Search insights and highlights, read projects and notes, and capture new findings, each call scoped to the authenticated researcher's workspace access.

dovetail_projects_list

List projects

List the research projects the authenticated user can access in the workspace.

Parameters

Name

Type

Required

Description

query

string

Optional

Filter projects by name or keyword

limit

integer

Optional

Max projects to return (default 50)

dovetail_project_get

Get project

dovetail_insights_search

Search insights

dovetail_insight_get

Get insight

dovetail_highlights_list

List highlights

dovetail_note_create

Create note

dovetail_data_search

Search data

Build your Agent

The same per-user auth pattern wires into every agent framework.

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

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["dovetailmcp"], toolNames: ["dovetail_insights_search", "dovetail_insight_get", "dovetail_highlights_list"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm: new ChatOpenAI({ model: "gpt-4o" }), tools });
await agent.invoke({ messages: [{ role: "user", content: "Summarise onboarding friction insights" }] });

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

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["dovetailmcp"], toolNames: ["dovetail_insights_search", "dovetail_insight_get", "dovetail_highlights_list"] },
  pageSize: 100,
});

const res = await openai.responses.create({
  model: "gpt-4o",
  input: "Search insights about onboarding friction",
  tools,
});

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

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["dovetailmcp"], toolNames: ["dovetail_insights_search", "dovetail_insight_get", "dovetail_highlights_list"] },
  pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 1024,
  tools,
  messages: [{ role: "user", content: "Pull highlights linked to the pricing insight" }],
});

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

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["dovetailmcp"], toolNames: ["dovetail_insights_search", "dovetail_insight_get", "dovetail_highlights_list"] },
  pageSize: 100,
});

const agent = new LlmAgent({ name: "dovetail_agent", model: "gemini-2.0-flash", tools });
await agent.run("List insights in the onboarding project");

Try these prompts

Paste any prompt into your agent to start working Dovetail research.

Search & synthesize

Copy the prompt

Copied

What are customers saying about onboarding friction this quarter?

Copy the prompt

Copied

Find insights tagged pricing across all my projects.

Copy the prompt

Copied

Summarise the top themes in the Q2 discovery project.

Investigate

Copy the prompt

Copied

Pull the highlights linked to the checkout confusion insight.

Copy the prompt

Copied

Show me raw transcript data that mentions slow first-value.

Copy the prompt

Copied

Which project has the most highlights about mobile bugs?

Capture & recall

Copy the prompt

Copied

Create a note in the onboarding project summarising this week's calls.

Copy the prompt

Copied

List all research projects I have access to.

Copy the prompt

Copied

How many insights are published in the retention study?

SEE HOW AUTH WORKS

The researcher authorises Dovetail once. Every later agent call uses their token with project scope enforced.

1

Authorize

Your user connects

Dovetail 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

Dovetail 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

Dovetail 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

Dovetail 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 analytics connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Research data needs real per-user attribution.

01.

Shared tokens break per-user analytics

A shared Dovetail token looks fine in a demo. In production every note and edit logs as one service account, so you lose track of which researcher acted. Scalekit resolves the real user's credential per call.

// shared token
create_note → research_bot

// scalekit
create_note → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Dovetail 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 Dovetail as the user or as a shared key?

As the user. Scalekit resolves the authenticated researcher's own Dovetail credential at request time, so every insight read, note, and edit is attributed to them in the workspace rather than a shared research bot.

Where is the Dovetail token stored?

In an AES-256 encrypted vault, namespaced per tenant. Tokens are fetched only at the moment of a tool call, refreshed automatically before expiry, and revocable from a single dashboard, never exposed to the model or the prompt.

Can I limit what the agent is allowed to do in Dovetail?

Yes. Pass a toolNames filter to listScopedTools to expose only the actions you want, for example read-only insight and highlight search without note creation. Scalekit also runs a scope check before each API call.

What happens when a user revokes Dovetail access?

The credential is invalidated at the next tool call, which fails closed rather than falling back to a shared token. Other users are unaffected, and the revocation is recorded in the audit trail.

Can the agent search raw transcripts, or only published insights?

That is your choice. Expose dovetail_insights_search and dovetail_highlights_list for a synthesis agent that reads finished insights, or add dovetail_data_search to let it query raw transcripts, tickets, and call notes. Each call is scoped per user, so a researcher can only reach data in projects they already own.

Dovetail MCP

Tools your research agent reaches for on Dovetail, scoped per user.