Income statement, balance sheet and cash flow, already assembled from SEC filings. No API key.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Ticker Scout.
list_companiesEvery covered company with its latest fiscal period and next expected filing. Resolves a company name to a ticker.
get_companyIdentity and coverage manifest: name, CIK, exchange, SIC industry, fiscal period held, source accession.
get_key_figuresHeadline figures for the latest reported period, each with its year-over-year change, exact amount and source accession.
get_financialsIncome statement, balance sheet, cash flow, segment revenue, per-share figures.
get_narrativeBusiness, risk factors, MD&A, legal proceedings, subsequent events from the latest 10-K and 10-Q.
get_eventsMaterial 8-K filings over roughly the trailing five quarters.
Finished financial statements for US public companies, over the Model Context Protocol. The SEC publishes the numbers as data, but it does not publish them as statements. This serves them already assembled. No API key, no signup, no paywall.
It exposes the data published at tickerscout.ai (https://tickerscout.ai) as six tools: financial statements, annual and quarterly report summaries, and material event histories for a growing set of US public companies, all derived from their own filings with the SEC.
The difference between this and the EDGAR APIs is assembly, not availability. The SEC gives you facts. This gives you statements.
Claude Code
Claude on the web or desktop
Settings, then Connectors, then Add custom connector, and paste the URL.
Cursor, and any client with an mcpServers config
Clients that only speak stdio
| Tool | Arguments | Returns |
|---|---|---|
list_companies | query (optional) | Every covered company with its latest fiscal period and next expected filing. Resolves a company name to a ticker. |
get_company | ticker | Identity and coverage manifest: name, CIK, exchange, SIC industry, fiscal period held, source accession. |
get_key_figures | ticker | Headline figures for the latest reported period, each with its year-over-year change, exact amount and source accession. |
get_financials | ticker, sections (optional) | Income statement, balance sheet, cash flow, segment revenue, per-share figures. |
get_narrative | ticker, section (optional) | Business, risk factors, MD&A, legal proceedings, subsequent events from the latest 10-K and 10-Q. |
get_events | ticker, section (optional) | Material 8-K filings over roughly the trailing five quarters. |
Tickers are case-insensitive, and BRK.B and BRK-B both resolve.
This is the reason to use the server rather than fetching the files directly. financials.json averages 58KB and narrative.md averages 38KB, and a question usually needs one part of one of them.
get_narrative called without a section returns an index of the document's sections with a one-line summary of each, so an agent can pick one and fetch only that. Pass section: "all" for the whole thing.
get_financials called without sections returns the whole file, and available_sections in the response lists what that company has. Section names are not the same across companies: a bank carries different top-level keys from a semiconductor company, and an insurer from both. Ask for what is there rather than guessing.
Every get_financials response includes a meta header with the company's units, reporting currency and fiscal period, even when you ask for a single section. All money is in actual dollars, not millions, and all share counts are actual shares.
list_companies.Free to read and cite. Please attribute "Ticker Scout (tickerscout.ai)".
A stateless Cloudflare Worker using createMcpHandler from @modelcontextprotocol/server, speaking streamable HTTP at /mcp.
The server stores no data. Every tool call fetches the corresponding file from https://tickerscout.ai through the Cloudflare edge cache and shapes the response. There is no database, no snapshot and no fallback copy: if the upstream file cannot be fetched, the tool returns an error naming the URL and the status rather than serving something stale.
npm test covers the pure logic. test/smoke.mjs calls every tool against a running server for a deliberately shape-diverse set of companies plus three negative cases, and is the check that matters before shipping.
MIT. See LICENSE.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/ticker-scout-2)<a href="https://allmcps.com/mcp/ticker-scout-2"><img src="https://allmcps.com/api/badge/ticker-scout-2?style=directory" alt="Ticker Scout on AllMCPs" /></a>