oqro-mcpSAFE
OQRO MCP server for Claude, ChatGPT and Cursor: insider, Congress, 13F and federal contract filings for US stocks, each linked to its source.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Ask Claude, ChatGPT, Cursor or any MCP client about insider trades, Congress stock trades, hedge fund 13F moves and federal contracts for US-listed companies. Every answer comes with the official filing it was read from.
- Server (remote, Streamable HTTP):
https://oqro.io/api/mcp - Website and setup page:
- Protocol: MCP
2025-06-18 - Auth: OAuth 2.1 with PKCE and dynamic client registration (sign in with an OQRO account). The tool list is open; every tool call is checked against an active OQRO Pro subscription ($9.99 a month or $79.99 a year).
OQRO describes what was filed. It is not investment advice.
Connect
Claude Code
claude mcp add --transport http oqro https://oqro.io/api/mcp
Cursor (~/.cursor/mcp.json)
{ "mcpServers": { "oqro": { "url": "https://oqro.io/api/mcp" } } }Claude, ChatGPT and other clients: add a remote MCP server (custom connector) with the URL above, then sign in when asked. Step-by-step screens are on .
Tools (15)
e8a0fb714d5aOBSERVED · 2026-10-10Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
streamable-http
Gates applied: no_behavioural_pass.
e8a0fb714d5afull audit observations/trust-audit/mcp-server/ldws123__oqro-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | e8a0fb714d5a | SAFE | B | 89 | first audit |
Questions
What is the oqro-mcp MCP server?
OQRO MCP server for Claude, ChatGPT and Cursor: insider, Congress, 13F and federal contract filings for US stocks, each linked to its source.
Is oqro-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does oqro-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does oqro-mcp run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (e8a0fb714d5a), read on 2026-10-10. The repository is watched and re-audited when it changes.