Vetagent MCP server
{
"mcpServers": {
"vetagent": {
"type": "http",
"url": "https://vetagent.dev/mcp"
}
}
}{
"mcpServers": {
"vetagent": {
"type": "http",
"url": "https://vetagent.dev/mcp"
}
}
}{
"mcpServers": {
"vetagent": {
"type": "http",
"url": "https://vetagent.dev/mcp"
}
}
}{
"servers": {
"vetagent": {
"type": "http",
"url": "https://vetagent.dev/mcp"
}
}
}{
"mcpServers": {
"vetagent": {
"type": "http",
"url": "https://vetagent.dev/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 0.2.0
What it does
VetAgent exposes token safety checks for AI agents before trading. It analyzes honeypot risk, liquidity, pair age, holder concentration, and contract permissions, returning a risk level (low/medium/high/unknown) with specific signals and a recommendation rather than raw data.
- Check a token's risk profile before an agent buys or recommends it to users.
- Look up liquidity depth and pair status for tokens to detect upstream failures versus genuine zero-liquidity cases.
- Discover new or trending pools on a chain for exploration purposes (with an explicit note this is not a safety endorsement).
Tools this server exposes
| Tool | Does |
|---|---|
| assess_token_risk | Returns a risk level (low/medium/high/unknown) with confidence, risk score, and specific signals covering sellability, liquidity, pair age, holder distribution, |
| get_token_liquidity | Returns liquidity snapshot for a token's primary pair with an explicit status to distinguish upstream failures from zero-liquidity cases. |
| find_new_hot_pools | Lists newest or hottest pools on a chain; marked as discovery only and not a safety endorsement. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.