// SCAN REPORT

Maiat Protocol

11 tools. 5 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

5 can modify or destroy data

6 read-only

11 tools total

Community server · catalogue entry verified 29/06/2026

How to control Maiat Protocol ↓

TOOL MAP

What Maiat Protocol exposes to your agents

Read (6) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Maiat Protocol tools

Financial · Critical trust_swap This tool retrieves a swap quote along with calldata for executing a token swap on Uniswap, a decentralized exchange. Write · High register_passport This tool creates and registers new digital identity artifacts (ENS name, ERC-8004 token, wallet, Scarab balance) and is reversible in principle. Write · Medium submit_review This is a Write operation because it creates/stores new review records and modifies token balances reversibly. Write · Medium vote_review This tool creates or modifies data (review votes and associated Scarab token rewards) in a reversible manner.

5 of Maiat Protocol's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Maiat Protocol

PolicyLayer is an MCP gateway — it sits between your AI agents and Maiat Protocol, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "trust_swap": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations

{
  "register_passport": {
    "limits": [
      {
        "counter": "register_passport_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "deep_analysis": {
    "limits": [
      {
        "counter": "deep_analysis_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Maiat Protocol — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MAIAT PROTOCOL →

Instant setup, no code required.

FULL CATALOGUE

All 11 Maiat Protocol tools

FINANCIAL 1 tools

Financial trust_swap Get a trust-verified swap quote with calldata. Checks both tokens for safety before returning a Uniswap quote.

WRITE 4 tools

Write register_passport Register for a Maiat Passport — get a free ENS name (yourname.maiat.eth), on-chain ERC-8004 identity, KYA veri Write report_outcome Report the outcome of an interaction with an agent after using their service. This feeds the Maiat oracle feed Write submit_review Submit a review for an on-chain entity (agent, token, protocol). Use after completing a job, swap, or interact Write vote_review Upvote or downvote a review. Only vote when you have firsthand experience with the reviewed entity. Upvotes re

READ 6 tools

Read deep_analysis Get deep trust analysis for an ACP agent address. Returns detailed breakdown with percentile rankings, risk si Read get_agent_reputation Get community reputation for an ACP agent — reviews, average rating, sentiment analysis, and market consensus. Read get_agent_trust Get the behavioral trust score for an AI agent wallet address. Returns a 0-100 score, verdict (proceed/caution Read get_scarab_balance Check the Scarab reputation points balance for a wallet address. Scarab is Maiat Read get_token_forensics Analyze a token contract for rug pull risk and safety signals. Returns honeypot detection, liquidity lock stat Read list_agents Browse indexed agents with their trust scores. Returns a paginated list of all known ACP agents.

FAQ

Questions about Maiat Protocol

Can an AI agent move money through the Maiat Protocol MCP server? +

Yes. The Maiat Protocol server exposes 1 financial tools including trust_swap. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through Maiat Protocol? +

The Maiat Protocol server has 4 write tools including register_passport, report_outcome, submit_review. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Maiat Protocol.

How many tools does the Maiat Protocol MCP server expose? +

11 tools across 2 categories: Read, Write. 6 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Maiat Protocol? +

Register the Maiat Protocol MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Maiat Protocol tool call.

Deterministic rules across all 11 Maiat Protocol tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MAIAT PROTOCOL →

Instant setup, no code required.

11 Maiat Protocol tools catalogued and risk-classified — across an index of 43,000+ MCP servers.