FiscalAI MCP

CALL ANY TOOL

API key scoped per analyst. Every SEC and market data query attributed to the authorizing user.

fiscalai_sec_filings_search

Search SEC filings

Search and retrieve SEC EDGAR filings (10-K, 10-Q, 8-K) by ticker, CIK, or filing type with full text and structured data.

Parameters

Name

Type

Required

Description

ticker

string

Optional

Stock ticker symbol (e.g. NVDA)

filing_type

string

Optional

Filing type: 10-K, 10-Q, 8-K, DEF14A

limit

integer

Optional

Max filings to return

fiscalai_earnings_transcripts_get

Get earnings transcripts

fiscalai_stock_prices_get

Get stock prices

fiscalai_financials_get

Get financials

fiscalai_insider_transactions_get

Get insider transactions

Build your Agent

Drop the toolkit in, point it at the authorized analyst, and your agent can query SEC filings and market data from the first run.

Copied

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: ["fiscalaimcp"], toolNames: ["fiscalai_sec_filings_search", "fiscalai_earnings_transcripts_get", "fiscalai_stock_prices_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 });

Copied

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: ["fiscalaimcp"], toolNames: ["fiscalai_sec_filings_search", "fiscalai_earnings_transcripts_get", "fiscalai_stock_prices_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: ["fiscalaimcp"], toolNames: ["fiscalai_sec_filings_search", "fiscalai_earnings_transcripts_get", "fiscalai_stock_prices_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 }],
});

Copied

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/fiscalaimcp",
    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 financial research agent to start pulling SEC and market data from FiscalAI.

Search & recall

Copy the prompt

Copied

Get the latest 10-K filing for [ticker].

Copy the prompt

Copied

Pull earnings call transcripts for [company] from the last 4 quarters.

Copy the prompt

Copied

Show insider buying activity for [ticker] in the last 30 days.

Analysis

Copy the prompt

Copied

Compare revenue growth across [company1] and [company2] for the last 3 years.

Copy the prompt

Copied

Summarize guidance language from the last [company] earnings call.

Copy the prompt

Copied

Get XBRL-parsed income statement data for [ticker] Q3.

SEE HOW AUTH WORKS

Analysts authorize FiscalAI once. Their API key stays vaulted, every data query is scoped to their subscription tier, and every access is logged.

1

Authorize

Your user connects

FiscalAI 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

FiscalAI 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

FiscalAI 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

FiscalAI 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 financial data and analytics connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

One vault for every financial data connector. FiscalAI today, Bloomberg and Refinitiv 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.

FiscalAI 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 use a shared FiscalAI API key or per-user keys?

Per-user keys. Each analyst provisions their own FiscalAI API key and Scalekit vaults it under their identity. Queries are attributed to that analyst, not a team-wide credential.

Where is the FiscalAI API key stored?

In Scalekit's managed AES-256 vault, namespaced per tenant. Keys are resolved at request time and never appear in prompts, logs, or LLM context.

Can I limit which FiscalAI tools the agent can call?

Yes. Use listScopedTools with a name filter to restrict the agent to specific data types, for example, allow SEC filings but block real-time price feeds for non-licensed users.

What happens when an analyst's FiscalAI key is revoked?

The next tool call fails closed for that user with a clear error. Other analysts in the tenant continue unaffected. Revocation is logged with a timestamp.

Does this work with compliance requirements around MNPI handling?

Yes. Per-user scoping and a full 90-day audit trail support compliance workflows. You can restrict which users access which data types, and every query is logged with user identity for review.

Tools your financial research agent reaches for on FiscalAI, scoped per analyst.