Grain MCP

Live

API KEY

MEETING NOTES

Transcription

Every meeting recording, highlight clip, and transcript your team captures lives in Grain. Grain MCP gives your agent authenticated access to meeting intelligence scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Grain MCP 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.
Grain MCP
agent · Acme Q3
Run
Search all recordings from this week for mentions of competitor pricing and summarize what was said.
S
grain_search
91ms
Meeting intelligence agent
4 recordings with competitor pricing mentions. Acme call: 'Their pricing is 3x ours but we win on security.' Globex: 'Asked why we don't offer per-seat.' Initech: 'Compared us favorably on enterprise tier.' Umbrella: 'Budget tied up in existing contract.'
Sources: 4 recordings, this week
grainmcpmcp
4 recordings
18:29
Message Claude...

Tools your meeting intelligence agent reaches for on Grain MCP, scoped per user.

CALL ANY TOOL
List and search recordings, fetch transcripts, retrieve AI highlights, and surface key moments.
grainmcp_list_clips
List clips
Returns a paginated list of Grain clips you have access to, ordered by most recent. Clips are short segments from meeting recordings. If the list contains more than `limit` clips, the response will also contain a non-null `cursor` value that can be used to fetch the next page by calling the tool again. Only returns clips whose media has finished processing, so newly-created clips may take a few minutes to appear.
Parameters
Name
Type
Required
Description
cursor
string
Optional
Optional cursor value from a previous request in order to fetch the next page of results.
filters
object
Optional
Optional filters to narrow down the list of clips.
limit
integer
Optional
Number of results to return per request page. Value should be between 1 and 20. If not specified, the default is 10.
grainmcp_search_persons
Search persons
grainmcp_list_stories
List stories
grainmcp_search_companies
Search companies
grainmcp_list_meetings
List meetings
grainmcp_search_in_transcripts
Search in transcripts
grainmcp_list_projects
List projects
grainmcp_get_dossier_for_company
Get dossier for company
grainmcp_list_collections
List collections
grainmcp_create_clip
Create clip
grainmcp_list_all_deals
List all deals
grainmcp_create_story
Create story
grainmcp_list_open_deals
List open deals
grainmcp_create_project
Create project
grainmcp_list_smart_topics
List smart topics
grainmcp_create_collection
Create collection
grainmcp_list_workspace_users
List workspace users
grainmcp_create_smart_topic
Create smart topic
grainmcp_list_attended_meetings
List attended meetings
grainmcp_update_my_settings
Update my settings
grainmcp_list_coaching_feedback
List coaching feedback
grainmcp_add_clips_to_story
Add clips to story
grainmcp_update_project_share_state
Update project share state
grainmcp_add_recordings_to_project
Add recordings to project
grainmcp_update_collection_share_state
Update collection share state
grainmcp_add_recordings_to_collection
Add recordings to collection
grainmcp_myself
Myself
grainmcp_my_team
My team
grainmcp_fetch_deal
Fetch deal
grainmcp_my_settings
My settings
Build your Agent
Drop the toolkit in, point it at the user, and your meeting intelligence agent can use Grain MCP 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: ["grainmcp"], toolNames: ["grain_recordings_list", "grain_recording_get", "grain_transcript_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: ["grainmcp"], toolNames: ["grain_recordings_list", "grain_recording_get", "grain_transcript_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: ["grainmcp"], toolNames: ["grain_recordings_list", "grain_recording_get", "grain_transcript_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/grainmcp",
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 Grain MCP.
Search & recall
Copy the prompt
Copied
Find recordings mentioning [topic] this week.
Copy the prompt
Copied
Get the transcript for [recording name].
Copy the prompt
Copied
List all recordings with [person name].
Copy the prompt
Copied
Which meetings discussed [competitor]?
Highlights & summaries
Copy the prompt
Copied
List highlights from [recording name].
Copy the prompt
Copied
Summarize the key points from [call name].
Copy the prompt
Copied
Find moments where pricing was discussed.
Copy the prompt
Copied
Get action items from [recording].
Reporting & coaching
Copy the prompt
Copied
Which reps had the most calls this month?
Copy the prompt
Copied
Find recordings longer than 45 minutes.
Copy the prompt
Copied
List all calls with [account name] this quarter.
Copy the prompt
Copied
Summarize competitor mentions across this week's calls.
SEE HOW AUTH WORKS
Users authorize Grain MCP once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Grain 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
Grain 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
Grain 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
Grain 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 meeting 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 meeting 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.
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.
Grain 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 Grain MCP 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 Grain MCP 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 Grain MCP?
Yes. Pass a tool name filter to listScopedTools so the meeting intelligence agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Grain MCP.
What happens when a user revokes Grain MCP 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.
Can the agent access private recordings from other team members?
Only recordings the authorizing user owns or has been explicitly shared on. Grain workspace visibility rules apply. Private recordings from other team members stay inaccessible.
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"": {
""grainmcp"": {
""url"": ""https://mcp.scalekit.com/grainmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.grainmcp]
url = ""https://mcp.scalekit.com/grainmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""grainmcp"": {
""url"": ""https://mcp.scalekit.com/grainmcp"",
""type"": ""http""
}
}
}