Gainsight MCP | OAuth 2.0 Gainsight connector for AI agents

Tools your CS agent reaches for on Gainsight, scoped per CSM.

CALL ANY TOOL

OAuth-scoped per CSM. Every health score query and activity log attributed to the authorizing user.

gainsight_company_query

Query company

Search and filter Gainsight company records by any field. Returns up to 5000 records per call.

Parameters

Name

Type

Required

Description

limit

integer

Optional

Maximum number of records to return per call (1–5000). Default: 100.

offset

integer

Optional

Number of records to skip, used for pagination. Default: 0.

orderBy

object

Optional

Sort specification as an object with field names as keys and 'asc' or 'desc' as values. Custom fields use '__gc' suffix; lookup fields use '__gr'.

select

array

Optional

Field names to return. Omit to get standard fields (Name, Gsid, Status, Stage, ARR, etc.).

where

object

Optional

Filter object with conditions array and expression string. Each condition uses name (field name), alias, value array, and operator.

gainsight_cta_create

Create cta

gainsight_cta_list

List cta

gainsight_cta_update

Update cta

gainsight_object_describe

Object Describe

gainsight_object_list

List object

gainsight_object_query

Query object

gainsight_query_company_person

Query Company Person

gainsight_query_relationships

Query Relationships

gainsight_query_scorecard

Query Scorecard

gainsight_resolve_user

Resolve User

gainsight_success_plan_list

List success plan

gainsight_success_plan_update

Update success plan

gainsight_task_create

Create task

gainsight_task_list

List task

gainsight_timeline_create

Create timeline

gainsight_timeline_query

Query timeline

gainsight_timeline_update

Update timeline

Build your Agent

Drop the toolkit in, point it at the authorized CSM, and your agent can query health scores and customer timelines from the first run.

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: ["gainsightmcp"], toolNames: ["gainsight_health_score_get", "gainsight_timeline_log", "gainsight_tasks_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 });

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: ["gainsightmcp"], toolNames: ["gainsight_health_score_get", "gainsight_timeline_log", "gainsight_tasks_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: ["gainsightmcp"], toolNames: ["gainsight_health_score_get", "gainsight_timeline_log", "gainsight_tasks_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 }],
});

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/gainsightmcp",
    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 CS agent to start pulling health scores and customer data from Gainsight.

Search & recall

Copy the prompt

Copied

Show health score trends for all accounts in the enterprise segment this quarter.

Copy the prompt

Copied

List all open CTAs for accounts at risk of churn in the next 60 days.

Copy the prompt

Copied

Get the latest timeline entries for [account name].

Action & updates

Copy the prompt

Copied

Log a success plan update for [account] with milestone: [milestone].

Copy the prompt

Copied

Create a CTA for [account] to schedule an EBR before renewal.

Copy the prompt

Copied

Update health score for [account] based on latest NPS and product usage data.

SEE HOW AUTH WORKS

CSMs authorize Gainsight once. Their OAuth token stays vaulted, every call is scoped to their permissions, and every action is logged.

Authorize

Your user connects

Gainsight

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

Store

Their

Gainsight

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

Resolve

When your agent calls a

Gainsight

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

Audit

Every

Gainsight

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 customer success and CRM connectors.

SALES

Deal intelligence agent

Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

One auth pattern for every CS tool. Gainsight today, Salesforce and Intercom 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.

Gainsight 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 Gainsight as the CSM or a shared service account?

As the CSM. Each customer success manager authorizes once via OAuth and Scalekit resolves their credential at request time. Activities logged by the agent appear under that CSM's identity in Gainsight, not a bot account.

Where is the Gainsight OAuth token stored?

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

Can I restrict the agent to read-only Gainsight access?

Yes. Pass a tool name filter to listScopedTools to allow health score reads and CTA queries but block timeline writes or success plan updates for specific users.

What happens when a CSM revokes Gainsight access?

The connection is invalidated on the next tool call for that user. Subsequent requests fail closed with a clear error. Other CSMs in the tenant remain unaffected. The event is logged.

Can the CS agent combine Gainsight data with Salesforce or Slack in one workflow?

Yes. A single agent can pull health scores from Gainsight and push a Slack alert or Salesforce activity in the same workflow. Each connector resolves under the same user identity with its own vaulted credential.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit