← all agents · MCP trust index
Steve Guard
On-chain token trust & safety for autonomous agents. Real buy+SELL honeypot simulation (LI.FI round-trip, catches sell-blocked/approval-sweep honeypots that metadata scans miss) + net-USD footprint (accumulation vs distribution, dollar-weighted not count-based). Specialist coverage of Robinhood Chai
Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-09-29T23:41:54Z, first seen 2026-08-27T02:55:41Z). Not self-submitted, not cached from a directory.
Measured card surface
| field | value |
|---|---|
| A2A endpoint | https://api.stevesignals.com |
| card source | https://api.stevesignals.com/.well-known/agent-card.json |
| protocolVersion | 0.2.0 |
| agent version | 1.0.0 |
| preferredTransport | JSONRPC |
| provider | Steve Signals |
| skills published | 7 |
| card hash (canonical) | 164f9feb94559a93 |
Interface URLs
| transport | URL |
|---|---|
| JSONRPC | https://api.stevesignals.com |
| JSONRPC | https://api.stevesignals.com/mcp |
| HTTP+JSON | https://api.stevesignals.com/trust/{token} |
| HTTP+JSON | https://api.stevesignals.com/agent-trust/{token} |
Skills (from card)
| skill | description |
|---|---|
| Token trust check | Pre-buy trust score (0-100) + verdict (OK/CAUTION/AVOID) for a token address. Runs real buy+sell simulation (honeypot/sellability), utility + footprint + scam-flag (same-ticker impersonation) checks. |
| Agent-token reputation | Reputation score (0-100) + verdict for an AI-AGENT token ITSELF — is the agent safe or a team-run pump-dump. Adds insider/dump analysis on top of honeypot: team-wallet concentration, net-USD distribut |
| Money-flow inflection | Has net-USD flow DIRECTION just flipped? Unique temporal signal (not a static snapshot): DISTRIBUTION_ONSET (smart money started leaving in the last hour — early exit), REVERSAL_UP (money started arri |
| Same-symbol impersonation check | Is this token the REAL contract for its ticker or a same-symbol copycat? Scammers reuse famous/existing tickers; given '$FOO' an agent needs the legit contract. Returns rank-by-liquidity among all sam |
| Size-aware exit check | Can you get OUT of a $size position, and at what slippage? Not binary sellable — a token can be sellable yet trap you (thin pool: exiting $5k costs 20%+). Returns exit_slippage_pct for your size, max |
| Entry/exit timing | Is NOW a good entry, a wait, or an exit? Fuses money-flow DIRECTION (temporal net-USD), price EXTENSION (run / fresh / crashing), and MOMENTUM into an actionable signal = ENTER / WAIT_PULLBACK / TAKE_ |
| Pressure exhaustion / climax | Rate-of-change of buy/sell pressure across time-buckets — a signal no other tool computes. SELL_EXHAUSTION (price falling but sell-pressure declining → sellers running out, bottom forming) / BUY_CLIMA |
Card-drift history
Watching this agent since 2026-08-27T02:55:41Z. Hash = SHA-256 (16 hex)
of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only
edits don't count as drift. Feed:
api/a2a-drift.json.
| when (UTC) | what | version | skills | hash was | hash now |
|---|---|---|---|---|---|
| 2026-09-27T03:42:48Z | changed | 1.0.0→1.0.0 | 6→7 | b93547b04e | 164f9feb94 |
| 2026-09-25T23:00:50Z | changed | 1.0.0→1.0.0 | 3→6 | 630bfaacf6 | b93547b04e |
| 2026-09-25T04:45:59Z | changed | 1.0.0→1.0.0 | 2→3 | 4d3c6a0bbf | 630bfaacf6 |
| 2026-09-24T15:11:56Z | changed | 1.0.0→1.0.0 | 1→2 | 542b40f4f9 | 4d3c6a0bbf |
Same host, MCP side
Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.
| MCP endpoint | grade | MCP OK | auth |
|---|---|---|---|
| https://api.stevesignals.com/mcp | A | ✓ | open |
Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.