TrustLayer

goatgaucho/trust-layer

You'd reach for this when you need to assess whether an AI agent or wallet address can be trusted before interacting with it. It exposes reputation scoring and Sybil detection across a network of 133K+ agents, pulling from cross-chain identity data to flag suspicious patterns. The streamable HTTP transport means you can query trust scores in real time from the TrustLayer API without managing local state. Useful for building agent marketplaces, autonomous transaction systems, or any multi-agent environment where you need to filter out bad actors before they can do damage. Think of it as a credit score system, but for autonomous agents operating across different blockchains.

tools: 6
transport: HTTP
last updated: Apr 4, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://api.thetrustlayer.xyz/mcp --name trust-layer

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http trust-layer https://api.thetrustlayer.xyz/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 6 tools

Verified live against the running server on Nov 6, 2026.

get_trust_reportFull trust forensics for an AI agent: Sybil risk, reviewer quality, cross-chain identity, anomaly flags, risk level, and recommended max exposure. Covers every ERC-8004 registry chain plus Solana.1 params

Full trust forensics for an AI agent: Sybil risk, reviewer quality, cross-chain identity, anomaly flags, risk level, and recommended max exposure. Covers every ERC-8004 registry chain plus Solana.

Parameters* required

agentId*string

Agent ID in chain:id format. Chains: base, ethereum, bsc, celo, gnosis, optimism, arbitrum, avalanche, polygon, monad, mantle, scroll, linea, metis, taiko, solana-mainnet. Example: base:1378

get_trust_scoreBasic trust score (0-100) for an AI agent with component breakdown.1 params

Basic trust score (0-100) for an AI agent with component breakdown.

Parameters* required

agentId*string

Agent ID in chain:id format. Example: base:1378

get_reviewer_profileQuality score and review history for a wallet that has left ERC-8004 feedback. High-quality reviewers are rare — most score below 50.1 params

Quality score and review history for a wallet that has left ERC-8004 feedback. High-quality reviewers are rare — most score below 50.

Parameters* required

address*string

Reviewer wallet address (0x...). Example: 0x1234...abcd

get_owner_portfolioAll agents owned by a wallet across all chains, with cross-chain group info and risk assessment.1 params

All agents owned by a wallet across all chains, with cross-chain group info and risk assessment.

Parameters* required

address*string

Owner wallet address (EVM 0x... or Solana)

get_score_historyFull score time-series for an agent: daily snapshots, 7d/30d trajectory, volatility over reputation lifetime.1 params

Full score time-series for an agent: daily snapshots, 7d/30d trajectory, volatility over reputation lifetime.

Parameters* required

agentId*string

Agent ID in chain:id format. Example: base:1378

get_network_statsLive network stats: total agents, chain breakdown, Sybil flags, reviewers scored, cross-chain groups.

Live network stats: total agents, chain breakdown, Sybil flags, reviewers scored, cross-chain groups.

No parameters. Call it with no arguments.

Readme

Details

Repository: github.com/goatgaucho/trust-layer
Category: AI & LLM Tools
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related AI & LLM Tools MCP servers

View all

Intelligence Mcpgoodmeta/intelligence-mcpAgent payments ecosystem intelligence. Scans GitHub/HN/npm across AP2, ACP, x402, MPP, UCP.0stars

Gsep Mcpgsepcore/gsep-mcpAI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.0stars

DrinkedIn — licensed bar dataio.github.haim-barad/drinkedinLicensed bar data from public registers, x402. Agent-bar tools deprecated. No real alcohol.0stars

Foresea Forecastingpareelamre/analyzing-llm-rationaleForecast future events and scan prediction-market edges.0stars

Pentagonal Mcppentagonal-ai/pentagonalAI smart contract forge — 8-agent security audits, generation, and compilation across 8 chains0stars

AgentTwinagenttwin/agenttwin-agent-toolsTest AI agent workflows against service twins with injected faults. Runs locally; no source upload.0stars