Attention

Live

API KEY

AI

Transcription

Every sales call, transcript, and AI insight your team captures lives in Attention. Attention MCP gives your agent authenticated access to call data scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Attention account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Attention
agent · Acme Q3
Run
Which deals had competitor mentions in the last 7 days and what objections came up?
S
attention_insights_search
88ms
Call intelligence agent
3 deals flagged with competitor mentions. Acme ($120K): pricing objection vs Globex. Initech ($85K): feature gap on SSO. Umbrella ($60K): timeline concerns.
Sources: 3 calls, 2 reps, Oct 24 to Oct 31
attentionmcp
3 calls
18:29
Message Claude...

Tools your call intelligence agent reaches for on Attention, scoped per user.

CALL ANY TOOL
Search calls and transcripts, surface insights, and pull AI summaries from sales conversations.
attention_ask_attention
Ask attention
Ask a natural-language question over one or more conversations within a deal and get back an AI-generated answer. Optionally include timestamped transcript excerpts that support the answer, or synthesize a single cross-conversation summary.
Parameters
Name
Type
Required
Description
conversations_ids
array
Required
List of conversation IDs to analyze. Pass an empty array to consider all conversations under the given deal.
deal_id
string
Required
Identifier of the CRM deal that provides context for this question.
prompt
string
Required
Natural-language question or instruction to run against the selected conversations.
include_timestamps
boolean
Optional
If true, includes timestamped transcript excerpts that support the answer.
summarize
boolean
Optional
If true, synthesizes all per-conversation outputs into a single combined response.
attention_calendar_events_list
List calendar events
attention_connection_report_get
Get connection report
attention_conversation_archive
Archive conversation
attention_conversation_get
Get conversation
attention_conversation_import
Import conversation
attention_conversation_media_download_url_get
Get conversation media download url
attention_conversation_privacy_update
Update conversation privacy
attention_conversation_update
Update conversation
attention_conversation_upload_url_get
Get conversation upload url
attention_conversations_list
List conversations
attention_deck_create
Create deck
attention_emails_list
List emails
attention_roles_list
List roles
attention_scorecard_result_create
Create scorecard result
attention_scorecards_list
List scorecards
attention_scorecards_summary_get
Get scorecards summary
attention_snippet_create
Create snippet
attention_team_create
Create team
attention_team_get
Get team
attention_team_members_list
List team members
attention_team_update
Update team
attention_teams_list
List teams
attention_usage_report_get
Get usage report
attention_user_create
Create user
attention_user_delete
Delete user
attention_user_update
Update user
attention_users_list
List users
Build your Agent
Drop the toolkit in, point it at the user, and your call intelligence agent can use Attention from the first run.
Python · LlamaIndex
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: ["attention"], toolNames: ["attention_calls_list", "attention_call_get", "attention_call_transcript"] },
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: ["attention"], toolNames: ["attention_calls_list", "attention_call_get", "attention_call_transcript"] },
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: ["attention"], toolNames: ["attention_calls_list", "attention_call_get", "attention_call_transcript"] },
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/attention",
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 agent to start using Attention.
Search & recall
Copy the prompt
Copied
Find all calls mentioning [competitor name].
Copy the prompt
Copied
List calls with [account name] this month.
Copy the prompt
Copied
Show me transcripts where [objection] came up.
Copy the prompt
Copied
Which deals had risk flags this week?
Insights & summaries
Copy the prompt
Copied
Summarize the last 5 calls with [account].
Copy the prompt
Copied
Get action items from [call name].
Copy the prompt
Copied
What objections appeared in calls this week?
Copy the prompt
Copied
Show coaching opportunities for [rep name].
Reporting & coaching
Copy the prompt
Copied
Compare win rates by objection type.
Copy the prompt
Copied
List reps with most competitor mentions.
Copy the prompt
Copied
Which calls scored highest on next-step clarity?
Copy the prompt
Copied
Show all calls where pricing came up.
SEE HOW AUTH WORKS
Users authorize Attention once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Attention
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
Attention
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
Attention
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
Attention
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 call intelligence agents and MCP connectors. Working code, live demos, fork what fits.
GTM and RevOps Teams
CRM AI agent
Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.
GTM and RevOps Teams
Sales call prep agent
Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.
GTM and RevOps Teams
Deal intelligence agent
Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.
GTM and RevOps Teams
Competitive intelligence briefing agent
Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.
Test other agents
Same per-user auth pattern across other call intelligence agents and MCP connectors. Working code, live demos, fork what fits.
SALES
Deal intelligence agent
Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.
SALES
Sales call prep agent
Read tomorrow's calls from Google Calendar, mine Granola notes and Attio history, and deliver each rep a prep brief in Slack.
GTM
CRM AI agent
Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.
GTM
Competitive intelligence briefing agent
Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Call insights attributed to a bot, not the rep
A shared Attention API key looks fine in a demo. In production, every call insight and coaching signal retrieved looks like it came from a service account. Rep-level attribution breaks. Scalekit resolves the actual user's token so every Attention action is attributed correctly.
// 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.
Attention today. Gong, Chorus, Fathom 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 Attention as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Attention api key stored?
In Scalekit's managed 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 limit what the agent is allowed to do in Attention?
Yes. Pass a tool name filter to listScopedTools so the call intelligence agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Attention.

What happens when a user revokes Attention access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Which calls can the agent surface insights for?
Only calls the authorizing user can see in Attention. Manager visibility scope surfaces team calls. IC-level access stays scoped to that rep's own calls. Cross-team data is denied at the source.

Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""attention"": {
""url"": ""https://mcp.scalekit.com/attention"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.attention]
url = ""https://mcp.scalekit.com/attention""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""attention"": {
""url"": ""https://mcp.scalekit.com/attention"",
""type"": ""http""
}
}
}