jamhimself-robinxSAFE
RobinX MCP — Robinhood Chain (4663) caller accuracy + deployer reputation + token intel, graded vs real price since genesis. x402-paid.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Robinhood Chain MCP server for AI agents and trading bots: rug checks, deployer reputation, insider-flow detection, measured X callers and live call signals for Robinhood Chain (chain 4663) tokens, built from complete on-chain history. Gives any MCP agent (Claude Desktop, Cursor, ...) a one-hop answer to "who launched this token and should I trust it?" — even seconds after launch, because it scores the deployer, not just the contract.
Remote, no install: add https://api.robinx.io/mcp as a custom connector in Claude, ChatGPT or any MCP client. Local: npx -y robinx-mcp (below).
RobinX measures who is actually right about Robinhood Chain — callers and deployers graded against real price since chain genesis.
Paid tools settle $0.01–0.05 USDC per call on Base via the x402 protocol. Configure a funded wallet key and the agent pays automatically; leave it out and paid tools return the price instead of data. All 28 tools are read-only (readOnlyHint) against the external RobinX API (openWorldHint).
Tools
669dbfc8c832OBSERVED · 2026-10-13Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add robinx-mcp --env ROBINX_WALLET_KEY=${ROBINX_WALLET_KEY} -- npx -y [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 (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
@modelcontextprotocol/sdk, @x402/fetch, @x402/evm, viem
Every paid tool still works as a price probe: it returns `PAYMENT REQUIRED ($0.0X USDC)` plus the x402 requirements, so an agent can decide whether to pay. The free tools (`robinx_stats`, `robinx_sear
Gates applied: no_behavioural_pass.
669dbfc8c832full audit observations/trust-audit/mcp-server/jamhimself__robinx-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 |
|---|---|---|---|---|---|
| 2026-10-13 | 669dbfc8c832 | SAFE | B | 89 | first audit |
Questions
What is the jamhimself-robinx MCP server?
RobinX MCP — Robinhood Chain (4663) caller accuracy + deployer reputation + token intel, graded vs real price since genesis. x402-paid.
Is jamhimself-robinx 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 jamhimself-robinx need?
It reads ROBINX_WALLET_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 jamhimself-robinx run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as robinx-mcp at 0.6.2.
How current is this page?
The grade is for one exact copy of the source (669dbfc8c832), read on 2026-10-13. The repository is watched and re-audited when it changes.