55Trust score 55 of 100, Fair
Transactional write gate for coding agents: plan, canonical manifest, checks, two-phase apply.
Registry
Loading the directory
Loading the directory
Every published server in the catalog, ordered by trust score. Each one has a single canonical page with its score explained.
Transactional write gate for coding agents: plan, canonical manifest, checks, two-phase apply.
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Live jobs from company Greenhouse, Lever and Ashby boards with age, long-open and repost signals.
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
Base-vs-head CI differ: which PR failures are introduced, pre-existing, external, or fixed.
Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
FAOSTAT data for 245 countries: crops, trade, food security, and emissions via 23 MCP tools.
Unknown author
Generate referentially intact, distribution-realistic PostgreSQL synthetic data from AI assistants.
Contabilidad española con IA: facturas, gastos por OCR, conciliación bancaria e impuestos AEAT.
GİB e-Fatura/e-Arşiv/e-İrsaliye belgelerini GİB'in XSD ve şematron kurallarıyla yerelde denetler
PostgreSQL schema intelligence from a committed snapshot. No connection, no credentials.
An MCP server whose confirmation cannot be replayed against a different call.
Webhooks for AI agents: send events, manage endpoints, inspect and retry deliveries.
Unknown author
Price a Claude, GPT, Gemini or Grok call before you send it. Runs locally.
Create PDFs from your CastPDF templates or HTML, issue EU e-invoices, and look up documents.
Git-friendly memory for AI coding: a tree of thread summaries with inherited context
Paid-per-call market data for agents: trading calendars, futures, macro, contract specs (x402)
Universal trust attestation for AI agents: create, verify, and negotiate Shuka trust proofs.
Local structured analysis of deployed EVM runtime bytecode
Drive Adobe After Effects from any MCP client: compositions, layers, animation and rendering.
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Compact agent context verbatim, offline: cut spent tool outputs, recall them by hash.
Check whether a URL or IP is safe before an AI agent fetches or opens it.
Manage addy.io email aliases, recipients, domains, rules and blocklist.