{
  "markdown": "# bitfence\n\n**The risk layer agents can't skip.**\n\nbitfence is a pre-transaction token risk oracle for autonomous AI agents\noperating on Solana, Base, Ethereum, Arbitrum, BSC, and HyperEVM. Before an\nagent\nswaps, transfers, or interacts with a token, bitfence returns a structured\nrisk assessment in under a second: a composite score, confidence value,\naction recommendation, and any active circuit-breaker flags.\n\n- **Live on Solana, Base, Ethereum, Arbitrum, BSC, and HyperEVM**\n- **HTTP API · MCP server · Rig (Rust) — Coinbase AgentKit coming soon**\n- **$0.10 per risk query in USDC on Base via x402 — no API keys**\n\n🔗 [bitfence.ai](https://bitfence.ai) · 📄 [Whitepaper](./WHITEPAPER.pdf) · 𝕏 [@bitfenceai](https://x.com/bitfenceai)\n\n---\n\n## Why this exists\n\nAutonomous agents now hold keys, read mandates, and broadcast transactions\nwithout a human in the loop. The agent frameworks shipping today expose swap\nand transfer actions with no systematic pre-transaction safety check. The\nrisk-assessment tooling that exists was built for a human reading a wallet\npop-up — not a machine routing on structured fields.\n\nbitfence fills the gap: a pre-intent token risk layer designed for machine\nconsumption. Neutral, transparent, agent-native, per-call priced. It is\ncomplementary to existing wallet-grade tools, not competitive with them.\n\n## What it scores\n\nRisk is decomposed into six categories — each a distinct mechanism by which\na holder's position is destroyed — and assembled into a 0–100 composite with\nmaturity-aware scoring and structured circuit-breaker overrides.\n\n| Category                | What it covers                                                                |\n| ----------------------- | ----------------------------------------------------------------------------- |\n| **Exit Integrity**      | Honeypot behaviour (measured by bitfence's own transaction simulation on EVM chains), sell/transfer taxes and their modifiability, freeze authority, transfer blocking |\n| **Supply Integrity**    | Mint authority, hidden ownership, owner-editable balances, permanent delegates, upgradeable proxies, selfdestruct, metadata mutability |\n| **Liquidity Integrity** | LP lock and burn status, unlock schedule, pool depth, deployer-held LP, pool age |\n| **Holder & Insider Risk** | Top-holder share, deployer share, holder count, sniper/insider/bundler cohorts, holder wallet ages |\n| **Provenance**          | Deployer track record, observed prior rugs, vendor scam verdicts, launchpad lifecycle, verification registries |\n| **Market Integrity**    | Wash-trade ratios, old-wallet flow share, price/volume divergence             |\n\nCircuit breakers override the composite: measured threats (honeypot,\nconfiscatory sell tax, selfdestruct) block even trusted tokens; heuristic\nflags floor the score for any token outside the curated trusted-token\nregistry. The reported confidence value reflects only the data sources\nactually consulted, with cross-source disagreements excluded.\n\nThe full methodology is in the [whitepaper](./WHITEPAPER.pdf).\n\n## Integration surfaces\n\nThe same scoring engine is exposed through four interfaces. Each returns the\nsame `RiskAssessment` structure.\n\n- **HTTP/JSON API** — for any caller that speaks HTTP\n- **MCP server** — for tool-calling LLM agents (Claude Desktop, MCP-enabled IDEs)\n- **Coinbase AgentKit** — ActionProvider coming soon\n- **Rig (Rust)** — typed in-process tool binding for Rust-native agents\n\nFor integration details, contact `info@bitfence.ai`.\n\n## Pricing and access\n\n- **$0.10 per risk query, $0.20 per contextual query** in USDC on Base via [x402](https://github.com/coinbase/x402)\n- Implemented against the Coinbase CDP facilitator\n- No accounts, no API keys, no signups\n- Listed on the Coinbase x402 Bazaar\n\n## Open-source posture\n\nDocumentation, whitepaper, and integration surfaces are open under Apache\n2.0. The scoring engine source remains closed for security reasons:\npublishing exact circuit-breaker thresholds, signal weights, and maturity\nlogic would let adversarial token deployers engineer tokens that sit\nimmediately below the trigger points, defeating the protection bitfence\nprovides to agents downstream. This trade-off is discussed in the\n[whitepaper](./WHITEPAPER.pdf).\n\nA publishable methodology document — one useful to other Ethereum security\nteams without exposing trigger logic to deployers — is in active\ndevelopment.\n\n## Security\n\nSee [SECURITY.md](./SECURITY.md) for vulnerability disclosure.\n\n## License\n\n[Apache License 2.0](./LICENSE)\n",
  "bytes": 4535,
  "sha": "a284e21d4672d2b8dc53680494d54894079c7bfb6b88509105836ffa18adb7bd",
  "repo_slug": "bitfenceai/bitfence",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_bitfenceai_bitfence_879473c9/readme"
}