mcpField
A
Assay Protocol Ai Agent Trust

Assay Protocol Ai Agent Trust

Local
assaylabs.xyzAI & Agents0Updated 23w ago
RepositoryVisit website

About Assay Protocol Ai Agent Trust

Assay’s MCP server lets AI tools look up agents, search the Assay Discovery index, and inspect ecosystem statistics. It is intended for MCP clients querying Assay’s trust infrastructure.

Key features

  1. 01Check an agent’s trust assessment
  2. 02Search ranked agents by query
  3. 03Filter results by minimum score
  4. 04Retrieve ecosystem statistics

Use cases

  1. 01Review an agent’s trust data
  2. 02Find agents by capability description
  3. 03Check ecosystem-level trust metrics

MCP support

Exposes Assay agent lookup, semantic search, and ecosystem statistics as tools over MCP stdio. It can be used from clients such as Claude Desktop and Cursor.

#ai-agents#trust#erc-8004#base#blockchain#web3

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "grandionn": {
      "command": "npx",
      "args": [
        "-y",
        "@assaylabs/mcp-server"
      ]
    }
  }
}
Run commandnpx -y @assaylabs/mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@assaylabs/mcp-server

Tools

3

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
addressstringYesAgent wallet address or indexed synthetic address such as erc8004-35

Details

From the project README

@assaylabs/mcp-server

MCP server for Assay Discovery and trust infrastructure tools.

This server exposes Assay agent lookup, semantic search, and ecosystem stats over standard MCP stdio transport so tools like Claude Desktop and Cursor can query the Assay ecosystem directly.

Install

npm install @assaylabs/mcp-server

Or run it directly with npx:

npx @assaylabs/mcp-server

Environment

The server reads the Discovery API base URL from:

  • ASSAY_API_URL
  • fallback: VITE_API_URL
  • default: https://assay-discovery-api.onrender.com

Example:

ASSAY_API_URL=https://assay-discovery-api.onrender.com npx @assaylabs/mcp-server

Tools

check_agent_trust

Input:

{
  "address": "erc8004-35"
}

Returns:

  • name
  • trustAssessment
  • assayScore
  • stake
  • erc8004AgentId
  • capability
search_agents

Input:

{
  "query": "smart contract security agent",
  "minScore": 60
}

Returns the top 5 ranked results from Assay Discovery, optionally filtered by minimum trustAssessment.

get_ecosystem_stats

No input.

Returns:

  • total indexed agents
  • average trust assessment
  • 75+ trust count
  • 60+ trust count
  • full metadata count
  • top agents

Claude Desktop

Add this to your Claude Desktop MCP config.

Installed package:

{
  "mcpServers": {
    "assay": {
      "command": "npx",
      "args": ["-y", "@assaylabs/mcp-server"],
      "env": {
        "ASSAY_API_URL": "https://assay-discovery-api.onrender.com"
      }
    }
  }
}

Local repo checkout:

{
  "mcpServers": {
    "assay": {
      "command": "node",
      "args": ["C:/ASSAY/assay-protocol/mcp-server/dist/index.js"],
      "env": {
        "ASSAY_API_URL": "https://assay-discovery-api.onrender.com"
      }
    }
  }
}

Cursor

Add this to your Cursor MCP configuration.

Installed package:

{
  "mcpServers": {
    "assay": {
      "command": "npx",
      "args": ["-y", "@assaylabs/mcp-server"],
      "env": {
        "ASSAY_API_URL": "https://assay-discovery-api.onrender.com"
      }
    }
  }
}

Local repo checkout:

{
  "mcpServers": {
    "assay": {
      "command": "node",
      "args": ["C:/ASSAY/assay-protocol/mcp-server/dist/index.js"],
      "env": {
        "ASSAY_API_URL": "https://assay-discovery-api.onrender.com"
      }
    }
  }
}

Notes

  • Transport: stdio
  • Package name: @assaylabs/mcp-server
  • License: MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.