OpenInsider MCP
Data for company research in an agent chat: Form 4 trades, SEC filings, short volume and quotes, with no scoring.
- 104 ★ on the repository
- Last commit
Minimal access
Why this level
- Requests go to open sites and public interfaces, and the server buys and sells nothing.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/openinsider-mcpDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- Requests go to open sites and public interfaces, and the server buys and sells nothing.
This is third-party code. Review the repository files before installing.
What it does
OpenInsider MCP gives an agent 16 tools over open data for investment research: Form 4 insider trades from OpenInsider, SEC EDGAR events and notices (8-K, 13D, S-3 and 424B5), short interest and daily short volume from FINRA and the SEC, and Yahoo Finance quotes. The server returns observations as they are, with no scores or composites: the model draws conclusions. Responses are cached in memory for 5 minutes and quotes for 60 seconds, and requests carry a `User-Agent` string changed through `OPENINSIDER_MCP_UA`.
Who it is for. Analysts and private investors who study company disclosures through an agent and match insider trades against SEC filings.
Good fit when
- Insider trades for a ticker over the last 90 days are needed through `search_by_ticker`.
- Cluster buys over the past week are searched with `cluster_buys`.
- After a sharp drop, 8-K filings and share offerings are checked through `recent_sec_filings` and `dilution_filings`.
- Short interest and its trend are assessed through `short_interest` and `failures_to_deliver`.
Not a fit when
- Buy or sell recommendations are needed; the server does not produce them.
- Data on issuers outside the United States is needed; SEC and FINRA disclosures cover American companies.
- Real-time exchange data with a latency guarantee is required; quotes come from Yahoo Finance.
Example request
Show NVDA insider trades for the last 90 days and find 8-K filings that might explain them.MCP
- Transport
- stdio
- Authentication
- not required
Environment variables
OPENINSIDER_MCP_UA- User-Agent string for requests to the open sources
Limitations
The server reads the open OpenInsider site and public SEC, FINRA and Yahoo Finance interfaces, so response format and availability depend on those sources. The data is reference material and does not replace investment advice. Nothing persists between sessions and there is no scheduler. Requests to public sources should be gentle: the 5-minute cache lowers load. Last commit in the repository: August 2026.
How to disable. Run `claude mcp remove openinsider` or delete the `openinsider` block from the client configuration. The server leaves no other data: its cache lives in process memory.
FAQ
Which sources does the server use?
OpenInsider, SEC EDGAR, FINRA together with the SEC, and Yahoo Finance. All four are free and public.
Does it give buy signals?
No. The server returns observations only and computes no scores; the model draws conclusions.
How do I connect it in Cursor or Codex?
The README has an install button for Cursor. For Codex use `codex mcp add openinsider -- npx -y openinsider-mcp`.
How do I change the User-Agent?
Set the `OPENINSIDER_MCP_UA` variable. Without it the server uses its own default string.
What happens when asking about a ticker situation?
The model usually calls several tools, for example `recent_sec_filings`, `dilution_filings` and `search_by_ticker`, and then correlates their answers.
Discussion
No questions or reviews yet.
Related
MCP serversAn MCP server for SEC EDGAR: US company filings, forms 10-K, 10-Q and 8-K, XBRL-parsed financials and insider trades
investor-agent gives an agent quotes, price history, options, an earnings calendar and a fear and greed index with no key.
MCP server that gives an agent Yahoo Finance data by ticker: price history, financial statements and option chains
The MCP server gives agents daily stock screens, relative-strength ratings, industry rankings and market breadth.
An MCP server for personal stock analysis: market data, technical indicators, screening and portfolio tracking, no keys for the core
Financial Datasets MCP
Financial Datasets MCP Server
An MCP server for the Financial Datasets API: company financials, stock and crypto prices and news for the agent
README in short
The server ships on npm and starts in stdio mode through `npx`. Tool descriptions include notes on data sources and pitfalls.