Server data from the Official MCP Registry
Give your AI deep fundamentals on US public companies — metrics, segments, peers. Free.
Give your AI deep fundamentals on US public companies — metrics, segments, peers. Free.
Remote endpoints: streamable-http: https://api.opencapital.sh/mcp
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
Endpoint verified · Requires authentication · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"sh-opencapital-mcp": {
"url": "https://api.opencapital.sh/mcp"
}
}
}From the project's GitHub README.
Every US public company, sourced from SEC filings — now available to your AI assistant.
OpenCapital is a hosted Model Context Protocol (MCP) server that gives Claude, ChatGPT, Cursor, Codex, and any other MCP-capable client read-only access to what every US public company actually reports — fundamentals, segment breakdowns, peer comparisons, and earnings for thousands of US-listed equities (common shares and ADRs), all derived directly from SEC filings.
You don't run anything. The server is hosted on OpenCapital's infrastructure. You add one URL to your client, sign in once, and start asking.
https://api.opencapital.sh/mcp
The data is free, the workflow is paid. Every metric, segment, quarter, and filing reference is free to query. OpenCapital is an independent project — not affiliated with the SEC.
Pick your client below, or see the full step-by-step guides at opencapital.sh/connect-ai.
OpenCapital, paste https://api.opencapital.sh/mcpFull guide: opencapital.sh/connect-ai/claude
claude mcp add --transport http opencapital https://api.opencapital.sh/mcp
Add --scope user to make it available in every project. Then run /mcp inside a session, select opencapital, and choose Authenticate.
Full guide: opencapital.sh/connect-ai/claude-code
OpenCapital, paste the URL, select OAuthFull guide: opencapital.sh/connect-ai/chatgpt
Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):
{
"mcpServers": {
"opencapital": {
"url": "https://api.opencapital.sh/mcp"
}
}
}
Then enable the server under Cursor Settings → Tools & MCP → Connect.
Full guide: opencapital.sh/connect-ai/cursor
codex mcp add opencapital --url https://api.opencapital.sh/mcp
codex mcp login opencapital
Or add to ~/.codex/config.toml:
[mcp_servers.opencapital]
url = "https://api.opencapital.sh/mcp"
Full guides: codex · codex-cli
Add a remote / custom MCP server over the Streamable HTTP transport, pointing at https://api.opencapital.sh/mcp. Most clients also accept the mcpServers JSON shape shown in the Cursor section above. The first call opens your browser to sign in and approve read-only access.
Full guide: opencapital.sh/connect-ai/other
The server ships with 13 read-only tools. You rarely call them by name — just ask in natural language and your client picks the right one.
| Tool | What it does |
|---|---|
stock_screener | Find and filter companies (sector, market cap, P/E, growth, FCF…). One row per company. |
stock_screener_filter_values | List valid values for a stock filter field (e.g. count of stocks per sector). |
metric_screener | Search financial metrics across companies. One row per (company × metric), with latest value, YoY/QoQ, and TTM change. |
metric_screener_filter_values | List valid values for a metric filter field. |
metric_detail | Definition, plain-language meaning, signal interpretation, parent/standard metric, and similar metrics across peers. |
metric_time_series | Full quarterly / annual / TTM history for one or more metrics on a single ticker. |
peer_time_series | One metric across up to 10 tickers — head-to-head peer comparisons. |
segment_time_series | Segment disaggregation (product, business, geography) for a line item, with history per segment. |
business_overview | What a company does, from its latest 10-K Item 1: segments, value chain, partnerships, named competitors. |
business_competitors | Ranked peer list — competitors named in filings, reverse mentions, and embedding-similar businesses. |
portfolio_holdings | Your linked brokerage holdings, aggregated by ticker with weights and P&L. (requires sign-in + linked account) |
get_watchlist | Your watchlist with company metadata and nearest earnings event. (requires sign-in) |
update_watchlist | Add or remove tickers from your watchlist. (requires sign-in) |
More in examples/prompts.md.
The OpenCapital MCP server only exposes read-only stock research data — fundamentals, segments, and earnings derived from public SEC filings. Your assistant cannot place trades or modify any account state. The watchlist tools are the only write surface, and they only edit your own OpenCapital watchlist.
OAuth grants your AI client read-only access to OpenCapital's public stock research index (and, if you choose, your own watchlist and linked-brokerage holdings). See the Terms of Service and Privacy Policy.
The configuration snippets and documentation in this repository are MIT-licensed.
The OpenCapital MCP service they connect to is a hosted service governed by its Terms of Service — your use of the service, including the free tier, is subject to those terms, not this license. This repository does not contain the server's source code.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.