Skip to main content
The AgentScore MCP server exposes trust lookups as tools that AI agents and coding assistants can call directly. This lets agents check wallet reputation before transacting, without writing custom API integration code.

​
Install for Claude

​
Claude Code (CLI)

claude mcp add agentscore -e AGENTSCORE_API_KEY=as_live_your_key_here -- npx -y @agentscore/mcp
This registers the AgentScore MCP server. Restart Claude Code to pick up the new tools.

​
Claude Desktop

Add to your Claude Desktop config file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "agentscore": {
      "command": "npx",
      "args": ["-y", "@agentscore/mcp"],
      "env": {
        "AGENTSCORE_API_KEY": "as_live_your_key_here"
      }
    }
  }
}
Restart Claude Desktop after saving.

​
Install for Cursor

Add to .cursor/mcp.json in your project root (or ~/.cursor/mcp.json globally): 
{
  "mcpServers": {
    "agentscore": {
      "command": "npx",
      "args": ["-y", "@agentscore/mcp"],
      "env": {
        "AGENTSCORE_API_KEY": "as_live_your_key_here"
      }
    }
  }
}
Restart Cursor after saving. The tools will appear in Cursor’s agent mode.

​
Available tools

​
check_wallet_reputation

Look up a wallet’s trust score and reputation. Free tier.
ParameterTypeRequiredDescription
addressstringYesEVM wallet address
chainstringNoChain to query (default: base)
> Check the reputation of 0xdb5aa553feeb2c3e3d03e8360b36fb0f7e480671

​
assess_wallet

On-the-fly trust assessment with policy evaluation. Paid tier.
ParameterTypeRequiredDescription
addressstringYesEVM wallet address
min_gradestringNoMinimum grade threshold (A-F)
min_scorenumberNoMinimum score (0-100)
require_verified_payment_activitybooleanNoRequire verified payments

​
browse_agents

Browse ERC-8004 registered agents with filters. Free tier.
ParameterTypeRequiredDescription
chainstringNoFilter by chain
limitnumberNoMax results to return
min_scorenumberNoMinimum score filter
gradestringNoFilter by grade

​
get_ecosystem_stats

Get ecosystem-wide statistics (agent counts, score distributions). Free tier. No parameters.

​
Use cases

Agent-to-agent trust — An AI agent verifies the reputation of another agent’s wallet before initiating a transaction. Gateway pre-screening — An agent acting as a gateway screens incoming requests by wallet reputation before routing them. Batch pre-filtering — An agent managing a marketplace filters a list of applicant wallets against a minimum trust threshold.

​
Running locally

For development and testing: 
AGENTSCORE_API_KEY=as_live_your_key_here npx @agentscore/mcp
The server communicates over stdio using the MCP protocol. Connect any MCP-compatible client to test tool calls interactively.