polymarket-paper-traderCAUTION
Paper trading simulator for Polymarket
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/polymarket-paper-trader/) [](https://github.com/agent-next/polymarket-paper-trader/actions/workflows/test.yml) [](https://clawhub.com/robotlearning123/polymarket-paper-trader) [](https://github.com/agent-next/polymarket-paper-trader/blob/main/LICENSE)
A zero-risk gym for AI agents on real prediction markets — real order books, official fees, verified fill fidelity. Practice, evaluate, and benchmark decision intelligence.
Agents make probability judgments all day. Polymarket is the world's largest prediction market, and its order books are the honest scoreboard: real money, real prices, real outcomes. But you cannot hand an agent a wallet to learn with. So this project gives every agent what SWE-bench gave coders — a faithful environment where judgment has consequences and gets scored:
- Practice — your agent trades $10k of paper money against live Polymarket order books, with the same fee model and fill mechanics as the real exchange
- Evaluate — the
polymarket-benchmarkharness in this repository (installed separately) scores any model on prediction-market decision sets (Brier score, calibration, alpha) - Compare — multi-account battles and leaderboards rank agents against each other
- Compete — Forecast Arena: the live public leaderboard where AI models and simple baselines forecast the same Polymarket questions daily and are scored by real outcomes (Brier score). Runs from this repo (enter your model · workflow · raw data).
Part of
97003f168e78OBSERVED · 2026-10-01Connect
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 polymarket-paper-trader -- None polymarket-paper-trader==0.4.5
Trust audit
CAUTIONgrade B · trust 81/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (1 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- found
Findings (14)
pm_trader/_skill/SKILL.md
return getattr(importlib.import_module(module_path), func_name)
async with streamable_http_client(f"http://127.0.0.1:{port}/mcp") as (r, w, *_):secret = "ghp_very-secret-token"
@pytest.mark.parametrize("bad", ["a/../../evil", "A", "-x", "a b", ".x", "a.json"])result = _invoke(runner, ["accounts", "create", "../../escaped"], data_dir)
result = _invoke(runner, ["--account", "../../etc", "init"], data_dir)
result = _parse(init_account(account="../../etc"))
f"https://static.cloudflareinsights.com/beacon.min.js/ '{_IMPORTMAP_SRI}'; "f"https://static.cloudflareinsights.com/beacon.min.js/ 'sha384-{digest}'; "model="openai/x", api_base="http://127.0.0.1:9/v1", num_retries=1
url = f"http://127.0.0.1:{port}/mcp"API key, token, or `.env` file; load credentials from the environment.
Gates applied: no_behavioural_pass.
97003f168e78full audit observations/trust-audit/mcp-server/agent-next__polymarket-paper-trader.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 |
|---|---|---|---|---|---|
| 2026-10-01 | 97003f168e78 | CAUTION | B | 81 | first audit |
Questions
What is the polymarket-paper-trader MCP server?
Paper trading simulator for Polymarket
Is polymarket-paper-trader safe to connect to an agent?
With care. The audit graded it B (81/100) and found 14 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does polymarket-paper-trader need?
It reads JEV_API_KEY and OPENCODE_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 polymarket-paper-trader run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as polymarket-paper-trader.
How current is this page?
The grade is for one exact copy of the source (97003f168e78), read on 2026-10-01. The repository is watched and re-audited when it changes.