← all agents · MCP trust index

AgentForge

Production-grade AI services for autonomous agents. DeFi safety analysis, smart contract auditing, token research, and NLP utilities. Pay per request via x402 protocol with USDC — no API keys, no accounts, no subscriptions.

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:20:03Z, first seen 2026-08-26T05:54:17Z). Not self-submitted, not cached from a directory.

Measured card surface

fieldvalue
A2A endpointhttps://agentforge-taupe.vercel.app
card sourcehttps://agentforge-taupe.vercel.app/.well-known/agent.json
protocolVersion
agent version1.5.0
preferredTransport
providerAgentForge
skills published19
card hash (canonical)9eafdb18a57fdd8a

Interface URLs

transportURL
unspecifiedhttps://agentforge-taupe.vercel.app

Skills (from card)

skilldescription
Token IntelligenceToken metadata enrichment with market data and AI risk assessment for any EVM or Solana token.
Smart Contract Code ReviewSecurity analysis with gas optimization and diff review mode. Supports Solidity, Rust, Move, TypeScript.
Multi-Source Token ResearchAggregates CoinGecko, DeFiLlama, Etherscan, Polymarket data with AI risk assessment.
Contract DocumentationHuman-readable smart contract documentation with function descriptions, risk flags, and security posture.
Contract Activity MonitorMonitors recent admin activity: ownership transfers, upgrades, pause state changes.
Token ComparisonCompare a primary token against up to 3 competitors with AI comparative analysis.
Transaction DecoderDecode any EVM transaction: function call, parameters, token transfers, and plain-English explanation.
Approval ScannerScan a wallet for risky token approvals. On EVM chains: identifies unlimited ERC-20 approvals and unverified spenders. On Solana: scans SPL token delegate authorities. Returns risk assessment.
Wallet Safety CheckComprehensive wallet safety check: scans approvals, analyzes recent transaction activity for suspicious patterns, and assesses target contract risk. Returns composite risk score (0-100). Supports EVM
Sentiment AnalysisAI sentiment analysis for crypto, finance, and social media text. Returns score, confidence, label, reasoning.
Text SummarizationAI text summarization with configurable length, format, and optional topic focus.
TranslationAI translation with tone control and auto source language detection. Preserves formatting.
Gas Price OracleCurrent gas prices (slow/standard/fast) for any EVM chain with trend analysis.
DeFi Pool SnapshotCached snapshot of top 500 DeFi liquidity pools. Filter by protocol, chain, or token. Returns TVL, APY, volume, IL risk, and registry enrichment.
Token Risk MetricsQuantitative risk metrics for any ERC-20 token: holder concentration, contract permissions (mint/burn/pause/blacklist), liquidity depth, deployer history, and composite risk score (0-100).
Payment VerificationLiveness check with x402 payment verification. Test that wallet and payment flow work correctly.

showing first 16 of 19 published skills — full list in the linked card.json

Card-drift history

Watching this agent since 2026-08-26T05:54:17Z. 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.

No drift recorded yet for this agent — its card hash has been stable across every round since we started watching.

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 endpointgradeMCP OKauth
https://agentforge-taupe.vercel.app/mcpD?

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.