VARRDSAFE
AI-powered trading research platform. Test any idea on stocks, futures, and crypto with event studies, backtesting, and statistical validation. MCP server with 8 tools. pip install varrd.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/augiemazza-varrd)
The governed live edge layer. Statistically validated market behaviors, monitored in real time.
Web App · MCP Endpoint · PyPI · varrd.com
Every edge shows exact entry, stop, target, and the full statistical methodology behind it.
Equity curves, Monte Carlo simulations, regime analysis, edge decay, and full audit trail.
Two ways to use VARRD
1. Tell your AI. Add the MCP config below, then ask: "What VARRD edges are firing right now?" or "What happens to gold when silver ETFs are making 100-day new lows?" Your AI browses the edge library, shows you what's actionable, and can test any idea you throw at it.
**2. Use
4979a9fc0899OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add varrd --env VARRD_API_KEY=${VARRD_API_KEY} -- uvx varrd{
"mcpServers": {
"varrd": {
"command": "uvx",
"args": [
"varrd"
],
"env": {
"VARRD_API_KEY": "${VARRD_API_KEY}"
}
}
}
}Trust 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 | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
assets/edge-library.png
Gates applied: no_behavioural_pass.
4979a9fc0899full audit observations/trust-audit/mcp-server/augiemazza__varrd.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 |
|---|---|---|---|---|---|
| 2026-10-09 | 4979a9fc0899 | SAFE | B | 89 | first audit |
Questions
What is the VARRD MCP server?
AI-powered trading research platform. Test any idea on stocks, futures, and crypto with event studies, backtesting, and statistical validation. MCP server with 8 tools. pip install varrd.
Is VARRD 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 VARRD need?
It reads VARRD_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does VARRD run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as varrd.
How current is this page?
The grade is for one exact copy of the source (4979a9fc0899), read on 2026-10-09. The repository is watched and re-audited when it changes.