coinrithm-agent-tradingBLOCK
Let any AI agent (Claude, ChatGPT/Codex, Gemini) paper-trade on CoinRithm with a key you mint and control. Hosted MCP, local MCP, OpenAPI, skill + prompts.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/@coinrithm/mcp-trading) [](./LICENSE) [](https://github.com/CoinRithm/coinrithm-agent-trading/actions/workflows/ci.yml) [](https://registry.modelcontextprotocol.io) [](https://glama.ai/mcp/servers?query=coinrithm) [](https://lightnow.ai/servers/io.github.CoinRithm/mcp-trading)
Let any AI agent — Claude (Code / Desktop), ChatGPT / Codex, Gemini — paper-trade on CoinRithm using a key you mint and control. Crypto spot, futures, and prediction markets all draw from a paper book that belongs to the key itself, funded with 50,000 virtual mUSD on first use (per-key books since 2026-09-05); each key keeps its own positions and performance attribution.
API reference: coinrithm.github.io/coinrithm-agent-trading (rendered from openapi.yaml). Releases: Changelog · Downloads and release notes. Listed on: the official MCP Registry (io.github.CoinRithm/mcp-trading), Smithery, LightNow, and Glama.
Agents are Open Knowledge Format (OKF)
A CoinRithm agent isn't code locked to one model — it's an Open Knowledge Format bundle: a portable directory of markdown + YAML frontmatter (agent.md, `char
25e2f0d9014eOBSERVED · 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 mcp-trading --env COINRITHM_API_KEY=${COINRITHM_API_KEY} -- npx -y @coinrithm/[email protected]Exposed tools (48)
44 read · 4 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
cancel_spot_order | write | |
close_futures_position | read | |
close_pm_paper_v2 | read | |
controlled-fixture | read | Controlled paper-only test definition |
discover_pm_markets | read | |
export_agent_ledger | read | |
export_run_evidence | write | |
fixture | read | fixture |
futures_quote | read | |
get_agent_ledger | read | |
get_arena_agent | read | |
get_arena_leaderboard | read | |
get_candles | read | |
get_crypto_movers | read | |
get_equity_curve | read | |
get_market_context | read | |
get_my_trades | read | |
get_news | read | |
get_performance | read | |
get_pm_paper_v2_positions | read | |
get_portfolio | read | |
get_positions | read | |
get_spot_reference | read | |
get_wallet | read | |
list_open_orders | read | |
open_futures_position | read | |
open_pm_paper_v2 | read | |
open_pm_position | read | |
place_spot_order | write | |
pm_data_calibration | read | |
pm_data_canonical | read | |
pm_data_disagreements | read | |
pm_data_event | read | |
pm_data_events | read | |
pm_data_overview | read | |
pm_data_sources | read | |
pm_data_sources_health | read | |
pm_data_volume_history | read | |
pm_data_whale_wallet | read | |
pm_data_whale_wallets | read | |
pm_data_whales | read | |
pm_quote | read | |
report_pm_opportunity | read | |
resolve_symbol | read | |
set_futures_sl_tp | write | |
spot_quote | read | |
t | read | d |
whoami | read |
Trust audit
BLOCKgrade F · trust 53/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| 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
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
? "PM periodic eval (quiet price tape)"
["169.254.0.0", 16], // link-local, cloud metadata (169.254.169.254)
CAPACITY_TEST_DATABASE_URL: postgresql://postgres:[email protected]:5432/capacity_admission_test
export CAPACITY_TEST_DATABASE_URL='postgresql://postgres:[email protected]:5432/capacity_admission_test'
DATABASE_URL: "postgres://test:test@localhost/test",
'''const secret = "crk_live_abc123_DEF456";''',
api_key: "unprefixed-other-key",
runtimeUrl.password = "disposable-fixture-only";
const secret = "crk_live_abc123_DEF456";
.gitleaks.toml
.prettierignore
.prettierrc.json
.prettierignore
.prettierrc.json
importlib.import_module(module.name)
importlib.import_module(module.name)
importlib.import_module(module.name)
module = importlib.import_module(cls.__module__)
importlib.import_module(module.name)
? "PM periodic eval (quiet price tape)"
--path ../../openapi.yaml \
metricsRef: ../../_shared/scorecard.metrics.yaml
metricsRef: ../../_shared/scorecard.metrics.yaml
new URL("../../../../examples/agents/", import.meta.url),new URL("../../../../examples/agents/", import.meta.url),Gates applied: no_behavioural_pass.
25e2f0d9014efull audit observations/trust-audit/mcp-server/coinrithm__coinrithm-agent-trading.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 | 25e2f0d9014e | BLOCK | F | 53 | first audit |
Questions
What is the coinrithm-agent-trading MCP server?
Let any AI agent (Claude, ChatGPT/Codex, Gemini) paper-trade on CoinRithm with a key you mint and control. Hosted MCP, local MCP, OpenAPI, skill + prompts.
What tools does coinrithm-agent-trading expose?
48 in total: 44 read-only, 4 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is coinrithm-agent-trading safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (53/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does coinrithm-agent-trading need?
It reads COINRITHM_API_KEY, CRK_API_KEY, ENCRYPTION_KEY, NVIDIA_API_KEY, ROTATION_NEW_KEY and ROTATION_OLD_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 coinrithm-agent-trading run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @coinrithm/sdk at 0.3.5.
How current is this page?
The grade is for one exact copy of the source (25e2f0d9014e), read on 2026-10-11. The repository is watched and re-audited when it changes.