Sybill MCP connector for AI agents

CALL ANY TOOL

Access AI-generated call summaries, deal context, and account conversation history. Same toolkit, every framework, no auth plumbing.

sybill_calls_list

List calls

List recent sales calls with AI-generated summaries, next steps, and sentiment scores.

Parameters

Name

Type

Required

Description

account_name

string

Optional

Filter by account or company name

limit

integer

Optional

Max calls to return (default 10)

from_date

string

Optional

Start date (ISO 8601)

sybill_call_summary_get

Get call summary

sybill_magic_summary_get

Get magic summary

sybill_deals_get

Get deal context

sybill_accounts_get

Get account history

Build your Agent

Drop the toolkit in, point it at the user, and your agent can pull Sybill call summaries and deal context 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: ["sybillmcp"], toolNames: ["sybill_calls_list", "sybill_call_summary_get", "sybill_magic_summary_get"] },
  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: ["sybillmcp"], toolNames: ["sybill_calls_list", "sybill_call_summary_get", "sybill_magic_summary_get"] },
  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: ["sybillmcp"], toolNames: ["sybill_calls_list", "sybill_call_summary_get", "sybill_magic_summary_get"] },
  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/sybillmcp",
    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 revenue agent to start pulling sales intelligence from Sybill.

Search & recall

Copy the prompt

Copied

Summarize the last [N] calls with [account name].

Copy the prompt

Copied

What open commitments came out of my calls this week?

Copy the prompt

Copied

Get the magic summary for [call ID].

Deal intelligence

Copy the prompt

Copied

What is the deal health for [opportunity name]?

Copy the prompt

Copied

Show stakeholder sentiment across all calls with [account].

Copy the prompt

Copied

List all calls where pricing was discussed this quarter.

SEE HOW AUTH WORKS

Reps authorize Sybill once. Their credentials stay vaulted, every call summary is scoped to their account, and every access is logged.

1

Authorize

Your user connects

Sybill 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

Sybill 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

Sybill 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

Sybill 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 CRM and sales intelligence connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

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.

Sybill 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 Sybill as the rep or a shared account?

As the rep. Each sales rep authorizes once and Scalekit resolves their credential at request time. Call summaries and deal data are scoped to that rep's Sybill account.

Where is the Sybill OAuth token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Tokens never appear in prompts or LLM context.

Can I restrict the agent to specific call data?

Yes. Use listScopedTools to allow summary retrieval without granting deal health or account history access.

What happens when a rep revokes Sybill access?

The connection is invalidated on the next tool call. Subsequent requests fail closed. Other reps remain unaffected.

Can the agent combine Sybill summaries with CRM data in one workflow?

Yes. A single agent can pull Sybill summaries and Salesforce or HubSpot deal data in the same workflow, each using the same rep identity.

Sybill MCP

Tools your agent reaches for on Sybill MCP, scoped per user.