Financial Datasets MCP

Live

OAUTH 2.1

MARKET DATA

Accounting & Finance

Financial Datasets MCP gives agents authenticated market data: stock prices, financial statements, SEC filings, insider trades, and stock screens on demand.

  • 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.
Financial Datasets MCP
agent · Acme Q3
Run
How did NVDA's last quarter compare to its revenue trend?
S
financialdatasetsmcp_get_income_statement
96ms
Research agent
NVDA Q3 revenue $35.1B, up 94% YoY, gross margin 74.6%. That is well above the 5-year trend; data center now drives 87% of total revenue.
Sources: 10-Q filing, 20 quarters of statements
financialdatasetsmcp
3 calls
18:29
Message Claude...

Tools your research agent reaches for on Financial Datasets, scoped per user.

CALL ANY TOOL
Pull market data across the research workflow: prices, statements, metrics, SEC filings, insider trades, earnings, and stock screens.
financialdatasetsmcp_get_stock_price
Get stock price
Retrieve current or historical stock price data for a single ticker.
Parameters
Name
Type
Required
Description
ticker
string
Required
The stock ticker symbol to retrieve price data for.
financialdatasetsmcp_get_income_statement
Get income statement
financialdatasetsmcp_get_balance_sheet
Get balance sheet
financialdatasetsmcp_get_financial_metrics_snapshot
Get metrics snapshot
financialdatasetsmcp_get_filings
List SEC filings
financialdatasetsmcp_get_earnings
Get earnings
financialdatasetsmcp_get_insider_trades
Get insider trades
financialdatasetsmcp_screen_stocks
Screen stocks
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);

// Financial Datasets tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["financialdatasetsmcp"], toolNames: [
    "financialdatasetsmcp_get_stock_price",
    "financialdatasetsmcp_get_income_statement",
    "financialdatasetsmcp_screen_stocks"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "How did NVDA's last quarter look?" }] });
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: ["financialdatasetsmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Screen for software companies with P/E under 20." }],
  tools,
});

// Execute the tool call with the user's vaulted 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: ["financialdatasetsmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Any insider selling at AAPL in the last 90 days?" }],
  tools,
});

// Tool call runs with the user's vaulted 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: ["financialdatasetsmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "equity_research_agent",
  model: "gemini-2.5-pro",
  instruction: "Answer equity research questions for the signed-in user.",
  tools,
});

await agent.run("Pull TSLA's balance sheet for the last 4 quarters.");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Financial Datasets tool. Click to copy, paste into your agent, done.
Company research
Copy the prompt
Copied
Pull NVDA's income statement for the last 4 quarters.
Copy the prompt
Copied
Show TSLA's balance sheet and current P/E ratio.
Copy the prompt
Copied
What are AAPL's key metrics right now: market cap, P/E, dividend yield?
Filings and signals
Copy the prompt
Copied
List MSFT's SEC filings from this year with links.
Copy the prompt
Copied
Any insider selling at AAPL in the last 90 days?
Copy the prompt
Copied
Show me the most recently filed earnings across all covered companies.
Screen and monitor
Copy the prompt
Copied
Screen for software companies with P/E under 20 and revenue growth over 15%.
Copy the prompt
Copied
Get current prices for NVDA, AMD, and INTC.
Copy the prompt
Copied
Which filters can I use in the stock screener?
SEE HOW AUTH WORKS
Your users connect once. Their Financial Datasets credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
Financial Datasets 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
Financial Datasets 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
Financial Datasets 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
Financial Datasets 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 market data 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 identity, scope enforcement, and audit. Connectors follow.
01.
Shared tokens break per-user analytics
A shared Financial Datasets token looks fine in a demo. In production every price pull and filing fetch looks like one service account, and you cannot tell whose research burned the rate limit. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Financial Datasets 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 Financial Datasets as the user or through a shared key?
As the user. Scalekit resolves the OAuth credential of the person who triggered the agent at request time, so every price pull and filing fetch in your audit trail is attributed to a real user, not a shared service account.
Where is the Financial Datasets token stored?
In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically, and can be revoked from one dashboard.
Can I limit what the agent does in Financial Datasets?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example statements and prices without the screener. 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.
Market data is read-only. Why does it need per-user auth?
Because entitlements, quotas, and compliance are per user. Each user's plan governs which of the 24 tools they can call and how often, and regulated teams need to show exactly who queried insider trades or filings. Scalekit binds every call to a real identity.
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"": {
""financialdatasetsmcp"": {
""url"": ""https://mcp.scalekit.com/financialdatasetsmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.financialdatasetsmcp]
url = ""https://mcp.scalekit.com/financialdatasetsmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""financialdatasetsmcp"": {
""url"": ""https://mcp.scalekit.com/financialdatasetsmcp"",
""type"": ""http""
}
}
}