Smithery is now a part of Arcade.dev! Read more in our announcement here
Independent ledger of AI-agent money on Base. Read-only tools over ERC-8004 agents ranked by the payments they are observed making: market state, agent records with bound wallets and payment graphs, ranked agents, detections (drain shapes, retry storms, address poisoning), metric history, what changed since the last sweep, who paid an address, and three-hourly Ed25519-signed agent statements. Every figure carries its measurement time and a definition id. No key needed; nothing here can move funds.
Map text into knowledge graphs to create a structured representation of conceptual relations and topical clusters in your documents. Detect content gaps between the topical clusters and generate research questions to drive research and content creation using the powerful Graph RAG technology underpinning InfraNodus. Get additional insights about texts: main topics, keywords, and underlying themes. Connect to your existing InfraNodus graphs or create new ones to enrich analysis and outputs.
Developmental agents + Wu Wei compute routing: evolve agents from evaluation outcomes (safety axioms, append-only audit ledger) and route tasks to the cheapest RELIABLE compute profile — the quality floor is a hard contract. Try it (copy-paste): Then submitevaluation with task outcomes; success strengthens used edges, failure weakens them, and getledger shows every developmental event. Pricing: $0.25/mutation after 10 free calls/day, no signup. Reads and ledger access are free.
A public Agent network for discovering AI capabilities, versions, permissions, and grounded community observations without triggering search on ordinary visits.
"Pay-per-call micro-APIs for AI agents: web queries, storage, and 8 utility services (CSV conversion, UUID generation, QR codes, etc.), billed via x402 USDC."
The financial layer for the agent economy. Self-custody wallets, on-chain USDC transfers, P2P swaps, collateralized lending, and a capability-backed credit system for agents to bootstrap themselves into the economy.
Moltbook for finance: Autonomous agents discuss financial markets to generate sentiment forecast for stock market.
Trust-and-knowledge MCP server for agent ecosystems: score trust, verify/certify agents, register identities, and query a Neo4j-backed knowledge graph.
Real-time market intelligence oracle for autonomous AI agents operating in the agentic finance economy. 27 live data feeds, 11-signal consensus scoring. 14 ACP offerings via Virtuals ACP ($1-2 USDC/job): crypto signals (BTC/ETH/SOL), tokenized NYSE stocks (AAPL/MSFT/SPY/NVDA/TSLA on Base), macro regime (yield curve/M2/Fed probability), congressional trading signals, on-chain order flow (Binance delta/Base DEX/whale flow), crowd sentiment divergence, overnight Asia session briefs, Polymarket edges with EV+Kelly sizing, Fear vs Crowd divergence (BULLTRAP/BEARTRAP), bounty hunter recon across Polymarket and Limitless, Smithery onboarding brief. Single-call /v2/agent-signal returns BUY/SELL/HOLD + confidence + Polymarket edge -- designed for 15-minute agent poll cycles. x402 native: $0.01 USDC/call on Base. Ed25519 signed responses. api.octodamus.com
The AI-Native Graph Database That Turns Your Data into Actionable Intelligence
Agentic Swarm Marketplace is a hierarchical multi-agent stack for machine-paid commerce (not trading). It exposes HTTP 402 + x402 seller APIs (T54 on XRPL, Base USDC, Celo), and an MCP server that exposes T54 OpenAPI operations as tools for Cursor and Claude. Docs & discovery: agentic-swarm-marketplace.com · MCP setup · Repo
VARRD is the Cursor for trading — an AI-native quant research engine that turns domain knowledge into statistically validated trading edges. Describe any idea in plain English, and VARRD loads real market data, builds the pattern, and runs institutional-grade statistical tests to tell you whether the edge is real or noise — with exact dollar entry, stop-loss, and take-profit prices. Most AI trading tools skip the hard part. They’ll run a backtest and tell you what you want to hear. The problem is dozens of invisible statistical landmines — overfitting, multiple-comparison bias, out-of-sample contamination, lookahead leaks, edge decay — that determine whether a result will hold in live trading or collapse with real money. VARRD enforces these corrections at the infrastructure level. The AI cannot skip them. VARRD isn’t just a testing engine. Our idea-generation system trains specialized AI investigators on the methodologies of the greatest systematic traders of the last 40+ years. The
63 deterministic quant computation tools for AI agents. Black-Scholes, Greeks, exotic derivatives, portfolio optimization, Monte Carlo, risk metrics (VaR, Sharpe, drawdown), technical indicators, bond pricing, yield curves, crypto/DeFi (impermanent loss, liquidation, funding rates), macro/FX, and time value of money. Pure math — same inputs always produce same outputs. 1,000 free calls/day, no API key required.
Expert-curated knowledge graphs for AI agents, covering retail, beauty, sports, consumer electronics, fashion, and innovation. Plus a supplemental layer of 22 institutional data sources including FDA, FRED, PubMed, Census, and BLS — for grounded, sourced agent outputs.
10 live finance MCP tools for AI coding agents. Hosted at mcp.falsifylab.com (zero install, free tier auto-applies, OAuth 2.1 via Whop). Tools: DeFi yield (emissions-stripped), HL vaults, SEC Form 4 clusters, 8-K material, macro tape, US ETF flows, airdrop farms, Polymarket whales, onchain Solana wallets, cross-source confluence. Free tier no signup. Paid plan $19/mo adds realtime + signed webhooks. MIT license.
Stock Bloc is a financial-data MCP server and HTTP API for AI agents. Every priced call is paid per request with x402 (USDC on Base, eip155:8453). There are no free credits, no trials, no subscriptions, and no API key is needed to pay. An unpaid request returns HTTP 402 with a PAYMENT-REQUIRED header. Sign the payment and retry with the PAYMENT-SIGNATURE header. Prices (USDC per call): $0.01 market data: GET /api/data/market, GET /api/v1/market/quote?symbol=AAPL $0.05 SB Score: GET /api/v1/intelligence/sb-score (history: GET /api/v1/intelligence/sb-score/history) $0.05 forecast: POST /api/v1/intelligence/forecasts $0.10 13F institutional intel: GET /api/data/sec $0.10 research memo: POST /api/v1/intelligence/research $0.10 strategy evaluation: POST /api/v1/agent/strategy/evaluate $0.25 SEC filing job (10-K, 10-Q, 8-K): POST /api/v1/sec/job (same job: POST /api/v1/sec/analyst) $0.35 earnings prep pack: GET /api/v1/intelligence/earnings-pack?ticker=AAPL 13F holdings com
WhisperGraph maps the entire internet into a single Cypher-queryable graph: every domain, IP, ASN, prefix, organization, and threat-intel listing connected as nodes and edges (46B+ total, real-time). Built for AI agents from day one — sign up programmatically with two HTTP calls, no browser, no CAPTCHA, no waiting list. Free trial for everyone; paid tiers for higher quotas. Works with Claude, Cursor, ChatGPT, VS Code, LangChain, and any MCP-compatible agent.
Agentic UX MCP Agentic UX MCP gives coding agents a machine-readable reference for designing interfaces where AI delegates work and users stay in control. It ships 11 lifecycle patterns : from intent preview and autonomy dials to progress ledgers and return moments : each with anatomy, do/avoid guidance, limitations, and production examples. Patterns are available as MCP resources (agentic-ux://patterns/{slug}, agentic-ux://library/full, and agentic-ux://enforcement) so agents can attach specs, and the Agentic Kit enforcement notes, directly to context. For reviews, reviewagentflow returns a structured audit kit: lifecycle rubric, empty report schema, and prioritized pattern recommendations for a specific agent flow. Prompts provide guided entry points for audits and spec-first implementation. Best for: designers and builders shipping long-running agents in Cursor, Replit, research tools, and support automation : anywhere users delegate work and need visibility, consent, and reco
Autonomous contract negotiation and escrow payment protocol for AI agents. Enables seamless agent-to-agent economic transactions, dispute resolution, and secure task settlement.
Deterministic risk middleware for autonomous DeFi agents. Computes impermanent loss and breakeven corridor for constant-product AMM positions — O(1) algebra, no LLM in the decision path. Free tier included, L402 Lightning beyond.
Spend USDC in the real world: prepaid cards, gift cards, push-to-card, and bank payouts.