three-token-mcpSAFE
The first MCP server whose actions burn a token. Let any AI agent price, hold, and burn $THREE on-chain — every burn splits to the incinerator + treasury via the live three.ws token rail, with Jupiter USD pricing. Deflation as an agent primitive.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/three-token-mcp
The first MCP server whose actions burn a token — let any AI agent price, hold, and burn $THREE on Solana.
Install · Quick start · Tools · Requirements · three.ws
A Model Context Protocol server that gives any AI assistant three $THREE primitives over stdio: read the live USD price, read a wallet's balance, and burn $THREE on-chain — split between the incinerator and the three.ws treasury, priced live via Jupiter. Deflation as an agent primitive: every three_burn call is a real, verifiable Solana transaction that permanently removes $THREE from supply and funds the treasury.$THREE is the only coin this server touches. Contract address (mainnet SPL): `FeMbDoX7R1Psc4GEcvJdsbNbZA3
840d8b7ed2c4OBSERVED · 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 three-token-mcp --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 (5)
.nojekyll
@modelcontextprotocol/sdk, @solana/spl-token, @solana/web3.js, bs58, zod
- **Report a bug** with the [bug form](https://github.com/nirholas/three-token-mcp/issues/new?template=bug.yml). Include the version, your Node version and the smallest reproduction you can.
Know someone who would use it? [Post on X](https://twitter.com/intent/tweet?text=three-token-mcp%3A%20The%20first%20MCP%20server%20whose%20actions%20burn%20a%20token&url=https%3A%2F%2Fgithub.com%2Fnir
Gates applied: no_behavioural_pass.
840d8b7ed2c4full audit observations/trust-audit/mcp-server/nirholas__three-token-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 | 840d8b7ed2c4 | SAFE | B | 89 | first audit |
Questions
What is the three-token-mcp MCP server?
The first MCP server whose actions burn a token. Let any AI agent price, hold, and burn $THREE on-chain — every burn splits to the incinerator + treasury via the live three.ws token rail, with Jupiter USD pricing. Deflation as an agent primitive.
Is three-token-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 three-token-mcp need?
It reads SOLANA_SECRET_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 three-token-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/three-token-mcp at 1.1.3.
How current is this page?
The grade is for one exact copy of the source (840d8b7ed2c4), read on 2026-10-10. The repository is watched and re-audited when it changes.