crypto-signals-mcpSAFE
Discover, subscribe to, and track three.ws copy-trade signal feeds from any AI agent — a marketplace ranked by proven realized edge, a publisher leaderboard from real on-chain performance, and account-scoped subscribe + kill-switch controls over the live API.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/signals-mcp
Discover, subscribe to, and track copy-trade signal feeds — a marketplace ranked by proven realized edge and a publisher leaderboard from real on-chain performance, from any AI agent.
A Model Context Protocol server that gives any AI assistant the three.ws signal-marketplace surface over stdio. Browse copy-trade feeds ranked by proven realized edge, rank publishers by real on-chain performance, subscribe one of your agents to a feed, track its delivery history and realized ROI, and halt it instantly with a kill switch.
Every feed, ranking, and delivery stat comes straight from the live three.ws API. Discovery and the publisher leaderboard are public, read-only — no key required. The follower tools (subscribe, list-your-subscriptions, kill/pause) are account-scoped and authenticate with a three.ws API key.
Already have [`@three-ws/intel-mcp`](https://www.npmjs.com/package/@three-ws/intel-mcp)? Its signal_feed tool reads a single feed's accuracy + emission log. This server is the complementary half: feed **di5e3d15f7c4feOBSERVED · 2026-10-10Connect
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 signals-mcp --env THREE_WS_API_KEY=${THREE_WS_API_KEY} -- npx -y @three-ws/[email protected]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 (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.nojekyll
@modelcontextprotocol/sdk, zod
Gates applied: no_behavioural_pass.
5e3d15f7c4fefull audit observations/trust-audit/mcp-server/nirholas__crypto-signals-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 | 5e3d15f7c4fe | SAFE | B | 89 | first audit |
Questions
What is the crypto-signals-mcp MCP server?
Discover, subscribe to, and track three.ws copy-trade signal feeds from any AI agent — a marketplace ranked by proven realized edge, a publisher leaderboard from real on-chain performance, and account-scoped subscribe + kill-switch controls over the live API.
Is crypto-signals-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 crypto-signals-mcp need?
It reads THREE_WS_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 crypto-signals-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/signals-mcp at 0.1.3.
How current is this page?
The grade is for one exact copy of the source (5e3d15f7c4fe), read on 2026-10-10. The repository is watched and re-audited when it changes.