openthomasSAFE
A self-improving weather forecasting & trading agent, in public.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/openthomas/) [](https://github.com/PredictionMarketTrader/openthomas/actions) [](LICENSE) [](https://pypi.org/project/openthomas/)
An autonomous AI agent that trades weather markets on Kalshi and Polymarket. It knows the exact NWS station each market settles on, builds a probability for every strike from a seven-model forecast consensus, learns each station's systematic bias from months of leak-free hindcasts, lets an LLM adjust — within hard bounds — for what the statistics can't see, and sizes every position with fractional Kelly under risk limits no model can override. It learns from every settled degree.
pip install openthomas openthomas init --bankroll 1000 --risk conservative openthomas hindcast # teach the baseline each station's bias — before the first trade openthomas run # paper trading on live market prices — the default
No wallet, no exchange API keys needed to start: paper mode simulates fills against real Polymarket + Kalshi order books. You only connect real money after you've watched it trade.
⚠️ Prediction market trading can lose all the money you allocate. OpenThomas ships with paper trading as the default, hard position limits, and a drawdown kill-switch — but no software makes trading safe. Roughly 70% of Polymarket addresses have lost money. This is not financial advice.
Why another trading bot? Because the LLM is not the edge.
The Prediction Arena benchmark gave six frontier AI models $10,000 eac
2637e0f85d6dOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add openthomas --env HF_TOKEN=${HF_TOKEN} --env KALSHI_API_KEY_ID=${KALSHI_API_KEY_ID} --env KALSHI_PRIVATE_KEY_PATH=${KALSHI_PRIVATE_KEY_PATH} -- uvx openthomas{
"mcpServers": {
"openthomas": {
"command": "uvx",
"args": [
"openthomas"
],
"env": {
"HF_TOKEN": "${HF_TOKEN}",
"KALSHI_API_KEY_ID": "${KALSHI_API_KEY_ID}",
"KALSHI_PRIVATE_KEY_PATH": "${KALSHI_PRIVATE_KEY_PATH}"
}
}
}
}Exposed tools (8)
6 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
forecast_market | write | Run OpenThomas |
get_market | read | Fetch one market |
performance_report | read | Track record: PnL, win rate, Brier score, calibration table, per-category stats. |
portfolio_status | destructive | Current account value, cash, open positions, and kill-switch state. |
propose_trade | read | Propose a trade from YOUR probability estimate that YES resolves true. |
research_news | read | Retrieve recent news headlines for a market question (GDELT + Google News, |
scan_markets | read | Scan live Polymarket + Kalshi markets through OpenThomas |
weather_brief | read | Settlement station, strike, multi-model NWP guidance, and today |
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 | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (8)
portfolio_status
return hashlib.sha1(f"{self.config.model}|{prompt}".encode()).hexdigest()[:16]monkeypatch.setenv("http_proxy", "http://127.0.0.1:3128")monkeypatch.setenv("https_proxy", "http://127.0.0.1:3128")provider="openai", model="glm-5.2", base_url="http://10.0.0.7:8000/v1",
base_url="http://127.0.0.1:8081/v1")))
assert _pool(client, "http://10.0.0.7:8000/v1/chat/completions") == "ConnectionPool"
docs/2604.07355v1.pdf
Gates applied: no_behavioural_pass.
2637e0f85d6dfull audit observations/trust-audit/mcp-server/predictionmarkettrader__openthomas.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 |
|---|---|---|---|---|---|
| 2026-10-11 | 2637e0f85d6d | SAFE | B | 89 | first audit |
Questions
What is the openthomas MCP server?
A self-improving weather forecasting & trading agent, in public.
What tools does openthomas expose?
8 in total: 6 read-only, 1 that write, and 1 that can delete or overwrite (portfolio_status). Every one is listed on this page with its risk.
Is openthomas 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. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does openthomas need?
It reads HF_TOKEN, KALSHI_API_KEY_ID and KALSHI_PRIVATE_KEY_PATH 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 current is this page?
The grade is for one exact copy of the source (2637e0f85d6d), read on 2026-10-11. The repository is watched and re-audited when it changes.