Merge pull request #8874 from meloliva14/add-verity-mcp

Add verity-mcp — fail-closed verify-before-you-act trust gate (Security) 🤖🤖🤖

README.md

@@ -3441,6 +3441,7 @@ Tools for conducting research, surveys, interviews, and data collection.
 - [askalf/truecopy](https://github.com/askalf/truecopy) [![askalf/truecopy MCP server](https://glama.ai/mcp/servers/askalf/truecopy/badges/score.svg)](https://glama.ai/mcp/servers/askalf/truecopy) 📇 🏠 🍎 🪟 🐧 - Supply-chain gate for agent skills and MCP servers — scans tool definitions for poisoned instructions, pins vetted servers by content hash in a committed lock, and verifies drift in CI; the bundled truecopy-mcp proxy exposes only pinned, unmodified tools from a live server.
 - [jamesdfinance-dev/lazaretto-mcp](https://github.com/jamesdfinance-dev/lazaretto-mcp) [![jamesdfinance-dev/lazaretto-mcp MCP server](https://glama.ai/mcp/servers/jamesdfinance-dev/lazaretto-mcp/badges/score.svg)](https://glama.ai/mcp/servers/jamesdfinance-dev/lazaretto-mcp) 📇 ☁️ 🏠 - Check whether anything you depend on is known malware, before an agent installs it. `check_lockfile` takes a package-lock.json, yarn.lock or pnpm-lock.yaml and matches every pinned version against published malicious-package advisories in one call, free and with no API key, catching compromised releases like chalk@5.6.1 while leaving their clean releases alone. `scan_artifact` adds deterministic behavioral analysis (no LLM in the serving path) for credential theft, exfiltration, obfuscation, prompt injection and install-time droppers, with the file, line and evidence that triggered it; verdicts are SHA-256-bound so you can re-verify what landed on disk. Paid scans settle at $0.03 USDC on Base (x402) or prepaid credits. `npx lazaretto-mcp`
 - [RoscoNL/intodns-mcp-server](https://github.com/RoscoNL/intodns-mcp-server) [![RoscoNL/intodns-mcp-server MCP server](https://glama.ai/mcp/servers/RoscoNL/intodns-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/RoscoNL/intodns-mcp-server) 📇 ☁️ 🏠 🍎 🪟 🐧 - Free DNS and email security scanner for AI assistants. DNS, SPF, DKIM, DMARC, DNSSEC, MTA-STS, BIMI, TLS/STARTTLS, FCrDNS, CAA, TLSA/DANE, blacklist and full-deliverability checks, plus security-header/CSP analysis and bookmarkable report snapshots, via the IntoDNS.ai API. No signup or API key. `npx intodns-mcp`
+- [meloliva14/verity-mcp](https://github.com/meloliva14/verity-mcp) [![meloliva14/verity-mcp MCP server](https://glama.ai/mcp/servers/meloliva14/verity-mcp/badges/score.svg)](https://glama.ai/mcp/servers/meloliva14/verity-mcp) 🐍 ☁️ - Fail-closed "verify before you act" trust gate for AI agents: fact-check (catch hallucinations), prompt-injection detection, content moderation, PII/secret detection, and a pre-action guardrail (allow/review/block). Independent, keyless, pay-per-call via x402. `pip install verity-mcp`
 - [astafford8488/agentaegis-mcp](https://github.com/astafford8488/agentaegis-mcp) [![astafford8488/agentaegis-mcp MCP server](https://glama.ai/mcp/servers/astafford8488/agentaegis-mcp/badges/score.svg)](https://glama.ai/mcp/servers/astafford8488/agentaegis-mcp) 📇 ☁️ - Security & trust layer for AI agents. Scan an MCP server or skill *before* you install it (`scan_mcp_plugin`, `scan_skill`) — flags exfiltration, prompt-injection sinks, dangerous capabilities, install hooks and obfuscation → PROCEED/CAUTION/BLOCK. Plus `vet_endpoint` (endpoint safety verdict before an agent calls or pays it) and 25 more tools: vuln scans, threat intel, compliance (SOC 2/ISO 27001/HIPAA), code security (SAST/secret/dependency), identity — 28 total. Per-call billing via API key or x402 USDC on Base; free discovery tier.
 - [Fronesis-Labs/dcl-webhook](https://github.com/Fronesis-Labs/dcl-webhook) [![dcl-webhook MCP server](https://glama.ai/mcp/servers/Fronesis-Labs/dcl-webhook/badges/score.svg)](https://glama.ai/mcp/servers/Fronesis-Labs/dcl-webhook) 🐍 ☁️ - Deterministic AI audit layer: evaluates LLM/agent outputs against configurable policies (jailbreak, safety, quality, wallet, trade, MEV compliance) and writes every verdict to a tamper-evident SHA-256 hash chain — metadata only, never raw content. 17 tools including a full crypto-trading compliance suite. Pay-per-call via x402 (USDC on Base), from $0.01. `mcp.fronesislabs.com/mcp`
 - [hernaninverso/eleion-scanner-mcp](https://github.com/hernaninverso/eleion-scanner-mcp) [![hernaninverso/eleion-scanner-mcp MCP server](https://glama.ai/mcp/servers/hernaninverso/eleion-scanner-mcp/badges/score.svg)](https://glama.ai/mcp/servers/hernaninverso/eleion-scanner-mcp) 📇 ☁️ - Register/verify your domains, queue security scans (headers, TLS, DNS, ports, CVEs + AI-specific checks) and read findings, for AI agents. Install with `npx -y eleion-scanner-mcp`.