"Creating a Local Knowledge Base" matching MCP connectors:
GET /v1/connectors — MCP directory API referenceMatching Connector Tools:
Rug pull risk and on-chain forensics for tokens on Solana, Ethereum, Base and Robinhood.
UI Verify is visual regression testing built for coding agents. Connect the MCP server and your agent (Claude Code, Cursor, Codex) pulls a pull request's UI changes into the conversation, views each visual diff, reads the AI judge's verdict of regression vs intended change, and accepts the intended baselines - all over MCP.
Build a real 3D website by chatting: pages, models and text in space, published to a live URL.
Receipt checks for expense and bookkeeping agents: normalize receipt text or structured extraction and review arithmetic, confidence and duplicate indicators. Free fixed synthetic example. Caller-supplied analysis: 0.25 USDC on Base via owner-approved x402. No image OCR or automatic bookkeeping.
Read-only discovery and bounded access to a finite market briefing with evidence boundaries.
290+ quality-scored API capabilities for AI agents across 27 countries via MCP.
Aggregator wrapping paywalled Coinbase x402 APIs as Model Context Protocol (MCP) tools, settling USDC micropayments on the Base network with integrated cashflow ledgering.
Smart contract security screening for Base. Check any contract or token for risk before interacting with it: Solidity source verification, upgradeable proxies and admin or mint powers, holder concentration, dangerous selectors, and B20 issuer powers. It surfaces the usual rug pull and scam indicators. The free tool needs no wallet and no API key; the paid Flash Audit (3.49 USDC over x402) returns a report with an anchored SHA-256. Payment is the only gate.
Never let your agent repeat a bug or linger on a known issue. Search 385+ failure lessons to skip known errors instantly.
Measured share of answer for 24 crypto and Web3 brands. An open dataset, not an audit of your site.
Measured share of answer for 20 SaaS brands. An open dataset, not an audit of your site.
Browser support for web features, live from caniuse. From which version, and is it safe to ship?
31Pay-per-call agent superpowers: media/video gen, product demos, research, GTM, scraping, compute.
Domain security reconnaissance tools for AI agents via Model Context Protocol. 13 security tools — DNS, SSL, HTTP headers, email auth, port scan, propagation, reverse DNS, ASN/BGP, RDAP/WHOIS, subnet calc, and comprehensive security scan — callable from Claude Desktop and any MCP-compatible AI agent. Part of DechoNet. Every tool here is also a free web tool at dechonet.com — no sign-up, no API key — backed by error-fix guides. This package brings the same checks to AI agents.
Production-safety audits for AI-generated code, with a fix for every finding. Scan for committed secrets and known vulnerable dependencies free with no key; a full audit returns a verdict with security, privacy, reliability and architecture findings, priced per audit and quoted before it runs.
Verified fixes, professional reviews, and evidence-led apparel over MCP.
Verifies which domain officially belongs to a software product, AI tool, or company, so the agent stops handing users lookalike download sites. Ownership only, never safety. Every verdict is backed by reproducible evidence. Tools: get_official_url(name), verify_url(url). No auth required.
Hosted, no-auth endpoint of feldspar-scan: free deterministic security scan of a public git repository (OSV.dev vulnerable dependencies, secret patterns, config lint) as structured JSON. Tools: scan_repository(url), audit_pricing(). Stateless streamable-HTTP JSON-RPC, rate-limited. Source: https://github.com/project-feldspar-resources/feldspar-scan (MIT). Operated by Feldspar, an autonomous AI agent (Project Feldspar).
A public bounty board where AI agents do paid work. USDC on Base, paid on accepted delivery.
Look up a guitar chord by name and get a text chord diagram. 12,708 standard-tuning names.
