crypto-portfolio-mcpSAFE
An AI agent's own trading state over MCP — portfolio summary, value history, live wallet balances, the public closed-trade PnL feed, and one real write: a signed on-chain Solana transfer. Powered by three.ws.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/portfolio-mcp
An AI agent's own trading state over MCP — portfolio value, PnL, live balances, the public trade feed, and one real write: a signed on-chain Solana transfer.
A Model Context Protocol server that gives an AI agent programmatic access to its own trading state over stdio: what it holds, how that value moves over time, a single token's position with live market data, the platform-wide feed of closed trades and their realized PnL, live on-chain balances for any wallet — and one real write, a signed Solana transfer of SOL or any SPL token.
Reads hit the live three.ws API and Solana RPC — nothing is mocked. The account-scoped reads run against the agent wallets you own (resolved from your three.ws session). The one write, send_transfer, signs locally with your own key and moves real funds on mainnet.
Install
npm install @three-ws/portfolio-mcp
Or run with npx (no install):
npx @three-ws/portfolio-mcp
Quick start
Claude Code, one line:
claude mcp add portfol
73a1e6352255OBSERVED · 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 portfolio-mcp --env THREE_WS_SESSION=${THREE_WS_SESSION} --env SOLANA_SECRET_KEY=${SOLANA_SECRET_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, @solana/spl-token, @solana/web3.js, bs58, zod
Gates applied: no_behavioural_pass.
73a1e6352255full audit observations/trust-audit/mcp-server/nirholas__crypto-portfolio-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 | 73a1e6352255 | SAFE | B | 89 | first audit |
Questions
What is the crypto-portfolio-mcp MCP server?
An AI agent's own trading state over MCP — portfolio summary, value history, live wallet balances, the public closed-trade PnL feed, and one real write: a signed on-chain Solana transfer. Powered by three.ws.
Is crypto-portfolio-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-portfolio-mcp need?
It reads SOLANA_SECRET_KEY and THREE_WS_SESSION 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-portfolio-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/portfolio-mcp at 0.1.2.
How current is this page?
The grade is for one exact copy of the source (73a1e6352255), read on 2026-10-10. The repository is watched and re-audited when it changes.