# bitfence Risk Oracle MCP server

Pre-transaction token risk checks for autonomous agents on six chains. Read-only; paid via x402.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-bitfenceai-bitfence
- Repository: https://github.com/bitfenceai/bitfence
- Website: https://www.bitfence.ai

## Install
- Endpoint: https://api.bitfence.ai/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://api.bitfence.ai/mcp

## Tools
- analyze_token - Full risk assessment for a token. Returns risk score (0-100), risk level, confidence, recommendation (PROCEED/REQUIRE_HUMAN_APPROVAL/BLOCK), reasoning, and flags triggered. Equivalent to GET /v1/risk/{chain}/{address}. Endpoint: https://api.bitfence.ai/mcp
- contextual_risk - Position-aware contextual risk assessment. Returns the full risk assessment plus position context: estimated slippage, effective cost, max safe position, portfolio concentration, and MEV exposure. Equivalent to POST /v1/risk/contextual. Endpoint: https://api.bitfence.ai/mcp
- quick_check - Lightweight go/no-go check for a token. Returns only risk_score, risk_level, recommendation, and cached flag. Use this when you just need a quick pass/fail without the full signal breakdown. Endpoint: https://api.bitfence.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.bitfenceai
- Version: 0.7.7
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 21, 2026
- Source: https://registry.modelcontextprotocol.io