solana-vanity-mcpSAFE
Read the three.ws vanity-address grind-bounty market and proof-of-grind rarity gallery from any AI agent. Quote a pattern's difficulty + USDC price, appraise any address's rarity, and browse the bounty board, claimable queue, stats, leaderboard, config, and gallery. Read-only — no key, no signer, no
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/vanity-mcp
Read the three.ws vanity-address grind-bounty market + rarity gallery from any AI agent.
A Model Context Protocol server that gives any AI assistant the read/discovery surface of the three.ws vanity-address grind-bounty market over stdio. Quote how hard a Solana vanity pattern is and what to escrow for it, appraise the rarity of any address, and browse the live bounty board, claimable queue, stats, leaderboard, config, and the proof-of-grind gallery.
The market is secret-blind: a requester escrows a USDC bounty for a pattern, a fleet of independent workers grinds it in parallel, and the first to submit a verified key matching the pattern is paid on-chain — yet the found secret is sealed to the requester, so the worker earns the bounty without ever seeing the wallet. Posting a bounty and claiming one are the x402-paid write paths on the HTTP API; this MCP exposes the read/discovery + rarity surface. No API key, no signer, no payment — every call hits the public /api/vanity endpoints.
Install
npm install @three-ws/v
30f05359156aOBSERVED · 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.
claude mcp add vanity-mcp -- 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.
30f05359156afull audit observations/trust-audit/mcp-server/nirholas__solana-vanity-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 | 30f05359156a | SAFE | B | 89 | first audit |
Questions
What is the solana-vanity-mcp MCP server?
Read the three.ws vanity-address grind-bounty market and proof-of-grind rarity gallery from any AI agent. Quote a pattern's difficulty + USDC price, appraise any address's rarity, and browse the bounty board, claimable queue, stats, leaderboard, config, and gallery. Read-only — no key, no signer, no
Is solana-vanity-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 solana-vanity-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does solana-vanity-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/vanity-mcp at 0.1.3.
How current is this page?
The grade is for one exact copy of the source (30f05359156a), read on 2026-10-10. The repository is watched and re-audited when it changes.