3ilm Mcp

io.github.holistis由 GitHub 账号 holistis 发布v1.0.1更新于 Nov 3, 2026

Search 1,032 verified smart contract vulnerability findings from Sherlock audits by pattern.

已验证STDIO仅桌面知识与记忆安全与监控

概览

AI 生成的概览

本地 MCP 服务器,让助手按模式检索 1,032 条来自 Sherlock 审计竞赛的已验证智能合约漏洞发现。

可以做什么
  • 按关键词在 12 个漏洞模式类别中搜索发现,返回接受率与示例
  • 查看单个模式的完整统计:总数、接受率、Sherlock 相关说明及被接受与被拒绝的示例
  • 列出全部 12 个模式,按数量排序并附接受度标识
适用场景
适合研究智能合约漏洞类型、审计发现的分类结果与接受率,或需要让助手获取关于哪些漏洞模式在 Sherlock 上能获得奖励的结构化参考数据时使用。
运行要求
通过 npx 从 npm 包 3ilm-mcp 在本地运行,需要 Node.js 以及下载该包的网络访问。未声明任何认证、环境变量或请求头。
安装前请注意
仅对内置数据集做只读查询,不涉及凭据或付款。README 说明这些数字复制自另一份公开数据集而非独立计算,并提到相关服务器提供付费合约扫描,本服务器不提供该功能。

安装

在 SourceWeft 中

  1. 打开 控制台中的 3ilm Mcp,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

3ilm MCP Server

MCP server exposing 3ilm, a curated knowledge base of 1,032 smart contract vulnerability findings from 10 fully-reconciled Sherlock audit contests.

Built for AI agents, security researchers, and audit tools that need structured data on which bug classes get paid, at what rates, and why.

What it is

3ilm (Arabic: علم, "knowledge") contains:

  • 1,032 verified findings from 10 Sherlock contests (fully reconciled against contest outcomes)
  • 12 vulnerability pattern categories with real acceptance rates, not estimates
  • Accepted and rejected examples per category, to learn what passes triage

Tools

ToolDescription
search_vulnerabilitiesKeyword search across all 12 categories. Returns matching patterns with acceptance rates and examples.
get_pattern_detailsFull stats table for one specific pattern: totals, acceptance rate, Sherlock-specific note, examples.
list_patternsAll 12 patterns ranked by volume with 🟢🟡🔴 acceptance indicators.

Install

bash
npx 3ilm-mcp

Add to Claude / Cursor

Claude Desktop (add to claude_desktop_config.json):

json
{  "mcpServers": {    "3ilm": {      "command": "npx",      "args": ["-y", "3ilm-mcp"]    }  }}

Cursor (add to .cursor/mcp.json):

json
{  "mcpServers": {    "3ilm": {      "command": "npx",      "args": ["-y", "3ilm-mcp"]    }  }}

Example queries

Ask your AI assistant:

  • "What is the acceptance rate for oracle manipulation findings on Sherlock?"
  • "Show me all vulnerability patterns and their payout rates"
  • "Search for reentrancy vulnerabilities: what percentage get accepted?"
  • "What does a accepted flash loan finding look like vs a rejected one?"

Data source

Same underlying dataset as 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 for the exact reconciliation method.

The 12 patterns: fee-miscalculation, dos-griefing, reentrancy, trusted-actor, overflow, staleness, rounding, access-control, oracle-manipulation, mev-slippage, liquidation, flash-loan.

How this relates to bug-bounty-intelligence-mcp

Both MCP servers read the same verified data. They differ in scope:

3ilm-mcp (this repo)bug-bounty-intelligence-mcp
Pattern search / acceptance ratesFreeFree (list_vulnerability_patterns)
Full-repo contract scanNot offered$5 USDC via x402 (scan_contract)
CostAlways free, no paid tierFree tools + one paid tool
Best forJust want the pattern data via MCP, nothing elseAlso want an actual scan of your own contracts

If 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.

Related

  • HTTP API (pay-per-query, USDC on Base): https://wazir-x402.duckdns.org/api/vuln-search?q=oracle
  • x402 Tollbooth: all endpoints listed at /api/status

License

MIT

来源:README.md,提交 7ecf9b2

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.0.1最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分