MCP server

Assay A2A, MCP & x402 Pre-Flight Verifier & Observatory

dev.agentdiet/assay

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

Live behavioral security verifier, schema auditor, and trust oracle for A2A, MCP & x402 agents.

Working at last checkVerified publisher: agentdiet.devAbout 1,761 tokens per request once connected4 tools

https://assay.agentdiet.dev/mcp

At a glance

Type: MCP server
Publisher: agentdiet.dev (verified by the MCP Registry)
Status: Working at last check
Tools: 4
Token cost: About 1,761 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 25 Oct 2026, 20:29 UTC

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http assay https://assay.agentdiet.dev/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.assay]
url = "https://assay.agentdiet.dev/mcp"

Gemini CLI

{"mcpServers":{"assay":{"httpUrl":"https://assay.agentdiet.dev/mcp"}}}

Cursor

{"mcpServers":{"assay":{"url":"https://assay.agentdiet.dev/mcp"}}}

VS Code

{"servers":{"assay":{"type":"http","url":"https://assay.agentdiet.dev/mcp"}}}

Antigravity

agy mcp add assay https://assay.agentdiet.dev/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"assay","server_url":"https://assay.agentdiet.dev/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"assay","server_url":"https://assay.agentdiet.dev/mcp"}

assay_get_ledger_policy ~442 tokens
Retrieve historical conformance observations and manage pinned SHA-256 tools/list policy hashes in the Assay ledger for a target endpoint. When expected_tools_hash is provided, it pins that 64-hex digest as the target's baseline policy and compares it against the latest stored observation; when omit
assay_preflight ~449 tokens
Gate a remote MCP, A2A, or x402 endpoint before calling or paying it by probing live JSON-RPC reachability, hashing tools/list (SHA-256), and scanning for prompt-injection poisoning. When expected_tools_hash is provided, any mismatch against the live tools/list digest forces verdict='deny' to block
assay_probe ~372 tokens
Register a new remote MCP, A2A, or x402 endpoint or refresh its public Assay Observatory dossier by running a live HTTP, agent-card, and JSON-RPC tools/list inspection without policy gating. Target must be a public HTTPS origin (private IPs are rejected with a 400 error); each call appends a timesta
assay_verify_delivery ~498 tokens
Audit a paid x402 or A2A provider after payment to confirm delivery or prove an SLA breach with an HMAC-SHA256 signed receipt. Passing status_code >= 500 forces verdict='sla_breach_confirmed' even if the live re-probe succeeds, while passing tx_hash cryptographically binds your Base or Solana paymen

aaaa-nexus — Formally Verified AI Safety APIs
Formally verified AI safety APIs. Pay-per-call via USDC (x402). 75+ endpoints, no signup.
Dominionobservatory Observatory
Runtime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.
Litmus
Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only.
StealthGuard 402
Stealth web extraction, Polymarket alpha, and on-chain pre-trade gating via x402 on Base.
Robinsaige Verifier
MCP tool observatory: do registry servers answer, and are their answers true? No key.
X402 Endpoints
x402 paid API tools for AI agents on Base: EU/global registries, crypto, wallet & agent trust.
AgentsToolsHub
156 paid-per-call JSON APIs for AI agents over x402: calculators, live data, crypto, security, dev.
Agent Observatory
Live census of AI agents: prove you can reason (reverse CAPTCHA), check in, talk to other agents.

[![AptLynx](https://aptlynx.net/badge/dev.agentdiet/assay.svg)](https://aptlynx.net/servers/dev.agentdiet/assay)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents