{
  "markdown": "# 3ilm MCP Server\n\nMCP server exposing **3ilm** — a curated knowledge base of 1,032 smart contract vulnerability findings from 10 fully-reconciled [Sherlock](https://audits.sherlock.xyz) audit contests.\n\nBuilt for AI agents, security researchers, and audit tools that need structured data on which bug classes get paid, at what rates, and why.\n\n## What it is\n\n3ilm (Arabic: علم, \"knowledge\") contains:\n\n- **1,032 verified findings** from 10 Sherlock contests (fully reconciled against contest outcomes)\n- **12 vulnerability pattern categories** with real acceptance rates, not estimates\n- **Accepted and rejected examples** per category — learn what passes triage\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `search_vulnerabilities` | Keyword search across all 12 categories. Returns matching patterns with acceptance rates and examples. |\n| `get_pattern_details` | Full stats table for one specific pattern: totals, acceptance rate, Sherlock-specific note, examples. |\n| `list_patterns` | All 12 patterns ranked by volume with 🟢🟡🔴 acceptance indicators. |\n\n## Install\n\n```bash\nnpx 3ilm-mcp\n```\n\n## Add to Claude / Cursor\n\n**Claude Desktop** — add to `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"3ilm\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"3ilm-mcp\"]\n    }\n  }\n}\n```\n\n**Cursor** — add to `.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"3ilm\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"3ilm-mcp\"]\n    }\n  }\n}\n```\n\n## Example queries\n\nAsk your AI assistant:\n\n- \"What is the acceptance rate for oracle manipulation findings on Sherlock?\"\n- \"Show me all vulnerability patterns and their payout rates\"\n- \"Search for reentrancy vulnerabilities — what percentage get accepted?\"\n- \"What does a accepted flash loan finding look like vs a rejected one?\"\n\n## Data source\n\nSame underlying dataset as [`vulnerability-acceptance-rates.json`](https://github.com/holistis/bug-bounty-intelligence-mcp/blob/main/vulnerability-acceptance-rates.json) — CC0, downloadable directly, no server required. That file is the canonical, publicly reproducible source; the numbers here are copied from it, not independently computed. Findings are reconciled against actual contest outcomes — no scraping, no estimates. See [METHODOLOGY.md](https://github.com/holistis/bug-bounty-intelligence-mcp/blob/main/METHODOLOGY.md) for the exact reconciliation method.\n\nThe 12 patterns: `fee-miscalculation`, `dos-griefing`, `reentrancy`, `trusted-actor`, `overflow`, `staleness`, `rounding`, `access-control`, `oracle-manipulation`, `mev-slippage`, `liquidation`, `flash-loan`.\n\n## How this relates to bug-bounty-intelligence-mcp\n\nBoth MCP servers read the same verified data — they differ in scope:\n\n| | 3ilm-mcp (this repo) | [bug-bounty-intelligence-mcp](https://github.com/holistis/bug-bounty-intelligence-mcp) |\n|---|---|---|\n| Pattern search / acceptance rates | Free | Free (`list_vulnerability_patterns`) |\n| Full-repo contract scan | Not offered | $5 USDC via x402 (`scan_contract`) |\n| Cost | Always free, no paid tier | Free tools + one paid tool |\n| Best for | Just want the pattern data via MCP, nothing else | Also want an actual scan of your own contracts |\n\nIf you only need to query acceptance rates, either server works identically for that. Use 3ilm-mcp if you want the smaller, free-only package; use bug-bounty-intelligence-mcp if you also want the paid full-repo scan tool.\n\n## Related\n\n- HTTP API (pay-per-query, USDC on Base): `https://wazir-x402.duckdns.org/api/vuln-search?q=oracle`\n- x402 Tollbooth: all endpoints listed at `/api/status`\n\n## License\n\nMIT\n",
  "bytes": 3603,
  "sha": "2d8574ad9baa0b6dc0303c8f3a71c850624e8cb32244d955a17df946e22fe9ec",
  "repo_slug": "holistis/3ilm-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_holistis_3ilm_mcp_44b2d45a/readme"
}