Claap MCP

Live

API KEY

MEETING RECORDINGS

Transcription

Claap MCP gives agents API key access to meeting recordings: search transcripts, read AI insight views, and connect calls to deals, contacts, and emails.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Claap MCP
agent · Acme Q3
Run
What objections came up in enterprise calls this month?
S
claapmcp_search_recording_transcripts
91ms
Claap agent
Found 11 mentions across 6 calls. Top objections: SSO gaps (4 calls), pricing tiers (3), migration effort (2). Latest: Acme call, Jul 2.
Sources: 6 recordings, Jun 10 to Jul 8
claapmcp
6 recordings
18:29
Message Claude...

Tools your revenue agent reaches for on Claap, scoped per user.

CALL ANY TOOL
Work meeting recordings end to end: query metadata, search transcripts, read insight views, and tie calls to deals, contacts, and emails.
claapmcp_get_recordings
Query recordings
Query the recording metadata database with filters and get recordings ordered by relevance and creation date.
Parameters
Name
Type
Required
Description
workspaceId
string
Required
The Claap workspace ID to query recordings from.
cursor
string
Optional
Opaque cursor returned as nextCursor by a previous call. Pass verbatim to fetch the next page.
filters
object
Optional
Filters to apply to the recording query.
limit
number
Optional
Maximum number of results per page (default 10, max 100).
sort
array
Optional
Sort dimensions. When omitted, results are ordered by relevance and creation date descending.
claapmcp_search_recording_transcripts
Search transcripts
claapmcp_get_recording_transcript
Get full transcript
claapmcp_list_recording_views
List insight views
claapmcp_get_recording_view
Read a view
claapmcp_search_deals
Search deals
claapmcp_search_contacts
Search contacts
claapmcp_search_emails
Search emails
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

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

// Claap tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["claapmcp"], toolNames: [
    "claapmcp_get_recordings",
    "claapmcp_search_recording_transcripts",
    "claapmcp_get_recording_view"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "What objections came up in enterprise calls this month?" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["claapmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Summarize the MEDDIC view for open enterprise deals." }],
  tools,
});

// Execute the tool call with the user's vaulted Claap credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["claapmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Pull the full transcript of yesterday's Acme demo." }],
  tools,
});

// Tool call runs with the user's vaulted Claap credential
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["claapmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "claap_revenue_agent",
  model: "gemini-2.5-pro",
  instruction: "Mine Claap recordings for the signed-in user.",
  tools,
});

await agent.run("Which deals had no follow-up email after the last call?");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Claap tool. Click to copy, paste into your agent, done.
Mine call transcripts
Copy the prompt
Copied
What objections came up in enterprise calls this month?
Copy the prompt
Copied
Pull the full transcript of yesterday's Acme demo.
Copy the prompt
Copied
Find every call where a prospect mentioned a competitor.
Qualification views
Copy the prompt
Copied
List the recording views configured in our workspace.
Copy the prompt
Copied
Summarize the MEDDIC view for open enterprise deals.
Copy the prompt
Copied
Which calls in the objection tracker are missing a champion?
Deals and follow-ups
Copy the prompt
Copied
Search deals in negotiation and list their latest recordings.
Copy the prompt
Copied
Which deals had no follow-up email after the last call?
Copy the prompt
Copied
Find the contact and email thread tied to the Globex renewal.
SEE HOW AUTH WORKS
Your users connect once. Their Claap credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
Claap 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
Claap 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
Claap 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
Claap 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 meeting connectors.
SALES
Sales call prep agent
Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.
SALES
Deal intelligence agent
Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with identity, scope enforcement, and audit. Connectors follow.
01.
Shared tokens break per-user analytics
A shared Claap key looks fine in a demo. In production every transcript search and deal lookup looks like one service account, and you cannot tell which rep's agent read which customer call. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Claap today. Ten connectors 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 Claap as the user or through a shared key?
As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every transcript search and deal lookup in your audit trail is attributed to a real user, not a shared service account.
Where is the Claap API key stored?
In an AES-256 encrypted vault with per-tenant namespacing. Keys are resolved at request time, never enter LLM context, and can be rotated or revoked from one dashboard.
Can I limit what the agent does in Claap?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example transcript search without email tools. Scalekit also enforces scope checks before every API call.
What happens when a user revokes access?
The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.
Our workspace has custom insight views like MEDDIC. Can the agent use them?
Yes. list_recording_views returns whatever views your workspace configured, including qualification frameworks, hiring rubrics, and objection trackers, and get_recording_view reads their AI-generated columns row by row. The agent prefers a view when one matches the question.
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"": {
""claapmcp"": {
""url"": ""https://mcp.scalekit.com/claapmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.claapmcp]
url = ""https://mcp.scalekit.com/claapmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""claapmcp"": {
""url"": ""https://mcp.scalekit.com/claapmcp"",
""type"": ""http""
}
}
}