VerdictSwarm MCP Server provides AI-powered token security analysis using 6 adversarial AI agents to detect rug pulls, scams, and risks in crypto tokens across multiple blockchains (Solana, Ethereum, Base, BSC).
scan_token — Comprehensive 6-agent consensus analysis with configurable depth (basic, full, debate), returning detailed risk scores and security findings
get_quick_score — Fast cached risk score (0–100, A–F grade) with basic token metadata for rapid pre-trade checks
check_rug_risk — Focused rug-pull assessment evaluating mint/freeze authority, liquidity lock/burn, honeypot behavior, holder concentration, and bundle/sniper activity — returns a SAFE/CAUTION/DANGER verdict
get_token_report — Generates a human-readable markdown report summarizing score, risk level, red flags, and security checks
get_trending_risky — Query trending high-risk tokens by chain and minimum risk level (currently in development)
get_pricing — Retrieve the USDC micropayment pricing table, payment wallet address, and instructions for autonomous agents
verify_payment — Confirm a Solana USDC micropayment was received before invoking paid endpoints
Works with MCP-compatible clients (Claude Desktop, Cursor, Codex, Windsurf, etc.), requires no blockchain nodes (cloud API with sub-second cached responses), and supports free-tier access (10 lifetime scans) or paid access via API key or USDC micropayments.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@VerdictSwarm MCP Server Check if this token is safe: DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263 on Solana"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
VerdictSwarm is a pre-trade security layer for agents that touch crypto. This MCP server exposes the Verdict API v2 as a small set of read-only tools for token checks, size-aware exit screening, and live pricing discovery.
No account setup is required. If VS_API_KEY is absent, the server mints a free key on the first API-backed tool call and saves it in the platform user config directory.
uvx verdictswarm-mcpThen ask your MCP client: “Check DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263 on Solana at fast level.”
To supply an existing free or credits-backed key:
VS_API_KEY=vs1_your_key uvx verdictswarm-mcpUse this server entry (the env block is optional):
{
"mcpServers": {
"verdictswarm": {
"command": "uvx",
"args": ["verdictswarm-mcp"],
"env": {
"VS_API_KEY": "vs1_your_key"
}
}
}
}Without VS_API_KEY, the self-provisioned key is stored at:
macOS: ~/Library/Application Support/VerdictSwarm/config.json
Linux: ${XDG_CONFIG_HOME:-~/.config}/verdictswarm/config.json
Windows: %APPDATA%\VerdictSwarm\config.json
The file is created with user-only permissions where the operating system supports them. Set VS_CONFIG_DIR to override the directory.
Related MCP server: aegis-defi
Tool | Description |
| Calls |
| Requests |
| Reads live pricing, levels, limits, and supported chains from |
The 0.1.x tools scan_token, get_quick_score, check_rug_risk, get_token_report, and verify_payment remain callable for migration safety, but return a deprecation response and make no legacy pay-lane request.
Free keys have per-level daily limits advertised by the API. If a limit is exhausted, the tool response says when the quota resets and preserves the complete x402 challenge. To continue immediately, set VS_API_KEY to a credits-backed key or use the returned x402 payment instructions.
The MCP client sends these attribution headers on API requests:
X-VS-Integration: mcp
X-VS-SDK-Version: 0.2.0
Environment variable | Default | Description |
| unset | Optional free or credits-backed v2 API key. |
|
| VerdictSwarm API base URL. |
|
| HTTP request timeout in seconds. |
| platform user config dir | Directory for the self-provisioned key. |
|
| MCP transport. Use |
|
| HTTP bind host. |
|
| HTTP bind port. |
For HTTP transport:
VS_TRANSPORT=streamable-http HOST=0.0.0.0 PORT=8000 uvx verdictswarm-mcpimport asyncio
from verdictswarm_mcp import VerdictSwarmApiClient
async def main():
client = VerdictSwarmApiClient()
verdict = await client.check_token("TOKEN_ADDRESS", "solana", "fast")
print(verdict["verdict"]["action"], verdict["verdict"]["score"])
asyncio.run(main())git clone https://github.com/sentien-labs/verdictswarm-mcp.git
cd verdictswarm-mcp
uv sync --extra dev
uv run --extra dev python -m pytest -qThe server supports Python 3.10–3.13 and both stdio and HTTP transports.
MIT licensed. See LICENSE.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
Rug-check & launch radar for trading agents: composite honeypot score, EVM+Solana, keyless x402.
AI-powered threat intelligence, smart contract auditing, and cybersecurity OSINT.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sentien-labs/verdictswarm-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server