Maiat Protocol MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add --transport http maiat-protocol https://app.maiat.io/api/mcp
README.md

The trust layer for agentic commerce.

Maiat Protocol

The trust layer for agentic commerce. Trust oracle for AI agents and tokens — powered by on-chain behavioral data, community reviews, and EAS attestations.

Live App · API Docs · ACP Agent #18281


Architecture

┌──────────────────────────────────────────────────────────────────────┐
│                          maiat-protocol                             │
├──────────┬──────────┬──────────┬─────────────────────────────────────┤
│ Web App  │ API      │Contracts │ Packages                            │
│ Next.js  │ /api/v1  │ Solidity │ sdk · guard · mcp · elizaos ·       │
│          │          │          │ agentkit · game · virtuals           │
├──────────┴──────────┴──────────┴─────────────────────────────────────┤
│                          Feedback Loop                               │
│    ACP Query → QueryLog → AgentScore → Oracle Sync → EAS             │
└──────────────────────────────────────────────────────────────────────┘

Connect in 30 Seconds

MCP (Claude Desktop, Cursor, any MCP-compatible agent):

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "maiat": {
      "url": "https://app.maiat.io/api/mcp"
    }
  }
}

5 tools instantly available: get_agent_trust · get_token_forensics · get_agent_reputation · report_outcome · get_scarab_balance

REST API (any agent, any LLM):

# Agent trust score
curl https://app.maiat.io/api/v1/agent/0x5facebd66d78a69b400dc702049374b95745fbc5

# Token rug risk
curl https://app.maiat.io/api/v1/token/0xYourToken/forensics

# skill.md (for LLM agents)
Read https://app.maiat.io/skill.md and follow the instructions

What It Does

Use Case Endpoint Fee
Token honeypot check GET /api/v1/token/:address Free
Agent trust score GET /api/v1/agent/:address Free
Deep agent analysis GET /api/v1/agent/:address/deep Free
Rug prediction GET /api/v1/agent/:address/rug-prediction Free
Trust-gated swap quote POST /api/v1/swap/quote Free
Browse 35K+ agents GET /api/v1/agents Free
Submit review POST /api/v1/review 2 Scarab
Trust Passport GET /api/v1/wallet/:address/passport Free

Web App Pages

Live at app.maiat.io

Route Description
/monitor Tactical dashboard — real-time agent activity feed, ACP job stream, oracle sync status
/explore Browse 35K+ indexed agents with trust scores, colored risk indicators (green/amber/red)
/leaderboard Top agents ranked by trust score, completion rate, and job volume
/agent/[name] Agent detail — behavioral insights, score breakdown, review history, deep analysis
/passport/[address] Trust Passport — wallet's cross-agent reputation, EAS receipt history (Phase 2)
/review/[address] Submit on-chain review — weighted by tx history (3x) and EAS receipts (5x), burns Scarab
/swap Trust-gated swap UI — checks oracle before surfacing Uniswap quote; blocks unsafe tokens
/markets Prediction markets for AI agent performance outcomes
/dashboard Personal dashboard — your agents, reviews submitted, trust score history
/docs API reference, SDK guides, contract ABIs, integration examples

ACP Offerings (Virtuals Protocol)

Wallet: 0xE6ac05D2b50cd525F793024D75BB6f519a52Af5D

Offering Fee Description
token_check $0.01 Honeypot detection, tax analysis, risk flags
agent_trust $0.02 Behavioral trust score + deep analysis (percentile, risk flags, tier)
`token_forensi

Tools (5)

get_agent_trustRetrieves the behavioral trust score and deep analysis for a specific AI agent.
get_token_forensicsPerforms a forensic analysis on a token to check for rug risks and honeypot indicators.
get_agent_reputationFetches the reputation data for an AI agent based on on-chain history.
report_outcomeSubmits an outcome report for an agent interaction.
get_scarab_balanceChecks the current Scarab balance for the user.

Configuration

claude_desktop_config.json
{"mcpServers": {"maiat": {"url": "https://app.maiat.io/api/mcp"}}}

Try it

Check the trust score for the AI agent at address 0x5facebd66d78a69b400dc702049374b95745fbc5.
Perform a forensic analysis on the token at 0xYourToken to see if it is a honeypot.
What is the current reputation and risk profile for this agent?
Get my current Scarab balance.

Frequently Asked Questions

What are the key features of Maiat Protocol?

Real-time trust oracle for AI agents and tokens. On-chain behavioral data and EAS attestation integration. Rug prediction and honeypot detection for tokens. Agent reputation tracking and deep behavioral analysis. Trust-gated swap quotes and market performance monitoring.

What can I use Maiat Protocol for?

Verifying the trustworthiness of an AI agent before interacting with it. Performing due diligence on new tokens to avoid rug pulls. Monitoring agent performance and job completion rates. Submitting on-chain reviews for AI agents to contribute to the trust ecosystem.

How do I install Maiat Protocol?

Install Maiat Protocol by running: Add to ~/Library/Application Support/Claude/claude_desktop_config.json

What MCP clients work with Maiat Protocol?

Maiat Protocol works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Maiat Protocol docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare