VerdictSwarm

Provides token risk analysis and on-chain security insights via a 6-agent MCP consensus for quick, shareable token risk assessments.

typescript

0

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "vswarm-ai-verdictswarm-mcp": {
      "command": "verdictswarm-mcp",
      "args": [],
      "env": {
        "VS_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

VerdictSwarm MCP Server enables any MCP-compatible client to delegate token risk analysis to VerdictSwarm’s 6-agent consensus system, providing fast, on-chain security insights and human-readable reports without needing a blockchain node. It acts as a lightweight wrapper around the core VerdictSwarm API, so you can install, run, and connect your client to the MCP server for quick token risk assessments.

How to use

You connect an MCP-compatible client to this server to perform token risk analyses. Choose a local stdio setup for quick testing or a remote HTTP setup if you host a server you manage. Each option uses the same underlying API and tools to run scans, fetch fast cached scores, or generate detailed markdown reports.

Typical usage flow after you have the MCP server running: set your API key in the environment, start the server, then configure your MCP client to reference the server. Use the client’s built-in commands to run a full token scan, fetch a quick score, or generate a report. All responses are provided by VerdictSwarm’s API and cached for sub-second retrieval.

How to install

Prerequisites: Python and pip, or an MCP-capable runtime such as uvx for zero-install usage.

# Install from GitHub
pip install git+https://github.com/vswarm-ai/verdictswarm.git#subdirectory=mcp-server
VS_API_KEY=your_key verdictswarm-mcp

# Or with uvx (zero-install)
VS_API_KEY=your_key uvx git+https://github.com/vswarm-ai/verdictswarm.git#subdirectory=mcp-server

# Or clone and run
git clone https://github.com/vswarm-ai/verdictswarm.git
cd verdictswarm/mcp-server
uv run verdictswarm-mcp

Configuration and usage notes

Environment variables shown in examples include the API key required to access VerdictSwarm services.

If you prefer a local one-command start, you can also run the MCP server directly after cloning and changing into the mcp-server directory, then launching the MCP runner as shown above.

Available tools

scan_token

Full 6-agent consensus analysis for in-depth token risk evaluation

get_quick_score

Fast cached score lookup (0-100) for quick checks before buying

check_rug_risk

Focused security and rug-pull risk assessment

get_trending_risky

Identify trending high-risk tokens (coming soon)

get_token_report

Generate a formatted markdown report of the analysis