Carta MCP

Live

OAUTH 2.0

EQUITY MANAGEMENT

Accounting & Finance

Every cap table entry, share class, and investor stake your agent needs lives in Carta. Carta MCP gives your equity agent per-user OAuth access scoped to the authorizing stakeholder, no shared service account, no credential sprawl.

  • Acts as the user: Every tool call runs under the authorizing stakeholder's Carta permissions.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail on every action.
Carta MCP
agent · Acme Q3
Run
What is the fully diluted share count by share class after our Series B closing?
S
carta_captable_get
134ms
Equity agent
Fully diluted: 28.4M shares. Common: 14.2M (50%), Series B Preferred: 8.1M (28.5%), Options pool: 4.7M (16.5%), Warrants: 1.4M (5%).
Sources: cap table, share classes
cartamcp
4
18:29
Message Claude...

Tools your equity agent reaches for on Carta, scoped per authorized stakeholder.

CALL ANY TOOL
OAuth-scoped per stakeholder. Every call runs under the authorizing user's Carta permissions.
cartamcp_cap_table_chart
Cap Table Chart
Show a visual cap table summary with ownership breakdown by share class.
Parameters
Name
Type
Required
Description
corporation_id
string
Required
Carta corporation ID of the company.
as_of_date
string
Optional
Date to use for the cap table snapshot in YYYY-MM-DD format.
company_name
string
Optional
Name of the company to look up.
cartamcp_discover
Discover
cartamcp_fetch
Fetch
cartamcp_get_current_user
Get Current User
cartamcp_list_accounts
List Accounts
cartamcp_list_contexts
List Contexts
cartamcp_mutate
Mutate
cartamcp_set_context
Set Context
cartamcp_view_remote
View Remote
cartamcp_view_static
View Static
cartamcp_welcome
Welcome
Build your Agent
Drop the toolkit in, point it at the authorized stakeholder, and your agent can query Carta cap table data 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: ["cartamcp"], toolNames: ["carta_captable_get", "carta_stakeholders_list", "carta_share_classes_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: ["cartamcp"], toolNames: ["carta_captable_get", "carta_stakeholders_list", "carta_share_classes_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: ["cartamcp"], toolNames: ["carta_captable_get", "carta_stakeholders_list", "carta_share_classes_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/cartamcp",
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 equity agent to start pulling cap table data from Carta.
Search & recall
Copy the prompt
Copied
Show fully diluted shares by class after the latest financing round.
Copy the prompt
Copied
List all option holders with unvested shares and cliff dates.
Copy the prompt
Copied
Get the current 409A valuation and effective date.
Action & updates
Copy the prompt
Copied
Fetch the latest board consent document.
Copy the prompt
Copied
Show all Series B preferred stakeholders and their liquidation preferences.
Copy the prompt
Copied
List recent equity plan grants for [team or department].
SEE HOW AUTH WORKS
Stakeholders authorize Carta once. Their OAuth token stays vaulted, every call is scoped to their permissions, and every action is logged.
1
Authorize
Your user connects
Carta 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
Carta 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
Carta 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
Carta 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 finance and equity management connectors.
GTM
CRM AI agent
Log calls, update opportunity stages, and surface stalled deals across HubSpot or Salesforce. No manual data entry.
SALES
Outbound prospecting agent
Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.
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.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
One auth pattern for every connector. Carta today, QuickBooks and Xero 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.
Carta 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 Carta as the user or a shared service account?
As the user. Each stakeholder authorizes once via OAuth and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the Carta OAuth token 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 Carta?
Yes. Pass a tool name filter to listScopedTools so the equity agent only sees cap table read operations, not share issuance or document signing. Pre-call scope checks block out-of-policy actions before they reach Carta.
What happens when a user revokes Carta 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.
Does the agent see confidential board-level data in Carta?
Only what the authorizing user's Carta role permits. Board-confidential documents and investor-side data remain gated by Carta's own permission model. Scalekit enforces but does not expand the user's access.
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"": {
""cartamcp"": {
""url"": ""https://mcp.scalekit.com/cartamcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.cartamcp]
url = ""https://mcp.scalekit.com/cartamcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""cartamcp"": {
""url"": ""https://mcp.scalekit.com/cartamcp"",
""type"": ""http""
}
}
}