Finnhub MCP server for AI agents

Live

API KEY

MARKET DATA

Accounting & Finance

Finnhub gives your agent read access to market data: stock quotes and price candles, company profiles and financials, earnings and IPO calendars, analyst ratings, insider transactions, SEC filings, and market news.

  • Per-user credentials: each call uses the actual user's API key, 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.
Finnhub
agent · Acme Q3
Run
Did NVIDIA beat EPS estimates in each of the last 4 quarters?
S
finnhub_get_earnings_surprises
88ms
Market research agent
NVIDIA beat the consensus EPS estimate in all 4 quarters. The largest surprise was 8.6% above the estimate.
Sources: Finnhub earnings surprises, 4 quarters
finnhub
4 quarters
18:29
Message Claude...

Tools your market research agent reaches for on Finnhub, scoped per user.

CALL ANY TOOL
30 tools for market data on Finnhub: stock, forex, and crypto candles, company profiles and financials, earnings, IPO, and economic calendars, analyst ratings, insider activity, SEC filings, and news.
finnhub_get_basic_financials
Get basic financials
Get a company's key financial metrics and ratio history. Returns metric, a map of current values such as peTTM, pbAnnual, epsTTM, dividendYieldIndicatedAnnual, beta, 52WeekHigh, 52WeekLow, 10DayAverageTradingVolume, grossMarginTTM and netProfitMarginTTM, plus series, annual and quarterly histories of ratios such as currentRatio, netMargin and salesPerShare. Use finnhub_get_basic_financials for valuation, margins and 52-week range. Use finnhub_get_financials_as_reported for full statements from SEC filings and finnhub_get_quote for the current price.
Parameters
Name
Type
Required
Description
symbol
string
Required
Ticker symbol of the company, as Finnhub lists it (US tickers are plain, e.g. AAPL; other markets use a suffix, e.g. BMW.DE). Use finnhub_search_symbols to find it.
metric
string
Optional
Metric group to return. Finnhub accepts all. Example: all. One of: `all`. Default: `all`.
finnhub_get_company_profile
Get company profile
finnhub_get_crypto_candles
Get crypto candles
finnhub_get_earnings_calendar
Get earnings calendar
finnhub_get_earnings_surprises
Get earnings surprises
finnhub_get_economic_calendar
Get economic calendar
finnhub_get_financials_as_reported
Get financials as reported
finnhub_get_forex_candles
Get forex candles
finnhub_get_forex_rates
Get forex rates
finnhub_get_insider_sentiment
Get insider sentiment
finnhub_get_ipo_calendar
Get ipo calendar
finnhub_get_market_holidays
Get market holidays
finnhub_get_market_status
Get market status
finnhub_get_peers
Get peers
finnhub_get_price_target
Get price target
finnhub_get_quote
Get quote
finnhub_get_recommendation_trends
Get recommendation trends
finnhub_get_stock_candles
Get stock candles
finnhub_list_company_news
List company news
finnhub_list_countries
List countries
finnhub_list_crypto_exchanges
List crypto exchanges
finnhub_list_crypto_symbols
List crypto symbols
finnhub_list_forex_exchanges
List forex exchanges
finnhub_list_forex_symbols
List forex symbols
finnhub_list_insider_transactions
List insider transactions
finnhub_list_market_news
List market news
finnhub_list_sec_filings
List sec filings
finnhub_list_stock_symbols
List stock symbols
finnhub_list_upgrades_downgrades
List upgrades downgrades
finnhub_search_symbols
Search symbols
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);

// Finnhub tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["finnhub"], toolNames: [
    "finnhub_get_quote",
    "finnhub_get_earnings_calendar",
    "finnhub_list_company_news"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Give me a pre-earnings brief on NVIDIA with the latest quote, report date, and recent news" }] });
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: ["finnhub"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Give me a pre-earnings brief on NVIDIA with the latest quote, report date, and recent news" }],
  tools,
});

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

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Give me a pre-earnings brief on NVIDIA with the latest quote, report date, and recent news" }],
  tools,
});

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

const agent = new Agent({
  name: "market_research_agent",
  model: "gemini-2.5-pro",
  instruction: "Finnhub tools scoped to this user",
  tools,
});

await agent.run("Give me a pre-earnings brief on NVIDIA with the latest quote, report date, and recent news");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Finnhub tool. Click to copy, paste into your agent, done.
Stocks
Copy the prompt
Copied
What is Apple's latest quote?
Copy the prompt
Copied
Show Microsoft's daily candles for the last 3 months.
Copy the prompt
Copied
Which companies are Tesla's peers?
Fundamentals and analysts
Copy the prompt
Copied
Get Amazon's key financial metrics and margins.
Copy the prompt
Copied
What is the analysts' consensus price target for AMD?
Copy the prompt
Copied
List analyst upgrades and downgrades for Netflix this month.
Calendars and news
Copy the prompt
Copied
Which companies report earnings next week?
Copy the prompt
Copied
List upcoming IPOs for the next 30 days.
Copy the prompt
Copied
Show this week's company news for Shopify.
SEE HOW AUTH WORKS
Each user connects their own Finnhub API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Finnhub
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
Finnhub
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
Finnhub
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
Finnhub
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 finance and market data connectors.
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.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
Test other agents
See the same per-user auth pattern across other finance and market data connectors.
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.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Finnhub API key looks fine in a demo. In production every quote and filing lookup looks like one service account, and you cannot tell which user triggered it. 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.
Finnhub 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 Finnhub as the user or through a shared API key?
As the user. Each user connects their own Finnhub API key once, and Scalekit sends it with every call. Audit logs attribute every market data request to that user, not a shared service account.
Where is the Finnhub API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Finnhub?
Yes. All 30 Finnhub tools are read-only: they look up quotes, fundamentals, calendars, filings, and news and never change anything. You can still filter by tool name in listScopedTools to expose a smaller set, for example only finnhub_get_quote and finnhub_get_company_profile. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Finnhub 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.
What news can the agent read from Finnhub?
finnhub_list_market_news returns the latest headlines in one category: general, forex, crypto, or merger. finnhub_list_company_news returns articles about one North American company published in a date range, with headline, summary, and source.
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"": {
""finnhub"": {
""url"": ""https://mcp.scalekit.com/finnhub"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.finnhub]
url = ""https://mcp.scalekit.com/finnhub""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""finnhub"": {
""url"": ""https://mcp.scalekit.com/finnhub"",
""type"": ""http""
}
}
}