the-prospector

multi-agent-trust-verifier

The #1 ranked OWASP ASI01 risk is Agent Goal Hijack — when an agent gets manipulated into doing something it was never hired to do. This service is your external policy engine. It compares every proposed action against the agent's original goal, enforces spend limits, detects goal drift, and blocks unauthorized agent-to-agent transactions before they execute. $0.004/verification via x402 on Base. MCP tool name: verify_agent_trust

token-squeezer

Compresses large blocks of text, code, or conversation history into hyper-dense Reasoning Maps optimized for LLM context windows. Saves agents 80%+ on token costs. Stateless. Pay $0.001 USDC per compression via x402 on Base network.

format-converter

Converts data between JSON, CSV, XML, YAML, Markdown, HTML and TOML instantly. Handles nested JSON flattening with dot-notation. Pure math, zero dependencies. Pay $0.001 USDC per conversion via x402 on Base network.

loop-gate

Stateless circuit breaker that detects recursive agent loops in MCP tool calls. Uses Bloom filter to identify repeated calls within 30 seconds. Pay $0.005 USDC via x402 on Base network to reset context and break the loop.

rate-limit-manager

Prevents your agent from hitting API rate limits mid-task. Submit a request and this service tells you instantly whether to proceed or how long to wait — with smart exponential backoff built in. No more failed runs, no more crashed workflows. Keeps your agent moving smoothly across any external API. $0.001/request via x402 on Base. No accounts. MCP tool name: check_rate_limit

permission-guard

Permission Guard — validates an agent's requested action against its defined scope before execution. Detects out-of-scope access, privilege escalation, and flags dangerous operations like delete, execute, admin, and deploy even when technically permitted. Stops agents from doing more than they're supposed to. $0.002/req via x402 on Base.

NodeAPI

Machine-native GIS processing API for AI agents and developers. Convert, reproject, validate, repair, buffer, clip, dissolve, and tile vector geodata across 25 endpoints. Pay-per-use USDC on Solana Mainnet ($0.01/op). No accounts, no API keys. Remote MCP SSE.

astllm-mcp

An MCP server for efficient code indexing and symbol retrieval using tree-sitter AST parsing to fetch specific functions or classes without loading entire files. It significantly reduces AI token costs by providing O(1) byte-offset access to code components across multiple programming languages.

Openterms-mcp

Cryptographic proof of consent for AI agents. Sign before you act. Policy engine enforces spending caps, action whitelists, and escalation rules. Independently verifiable by anyone.

Aegis-ZK

On-chain trust verification for AI agent tools. Agents query skill attestations, audit levels, and risk scores before running third-party MCP servers, so you know what's safe before you execute.

HiveAgent — The Agentzon

498 MCP tools across 12 industry verticals. Marketplace, escrow, DeFi, legal, healthcare, insurance, construction, and trades. USDC payments on Base L2.

NutriBalance

Calculate TDEE & macro targets, look up food nutrition data, generate meal plans, fix nutrient deficiencies, and score a day's eating from 0–100. Free nutrition tools for AI assistants.