经 AI Skill Hub 精选评估,Recon 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
Recon 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Recon 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/blisspixel/recon
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"recon": {
"command": "npx",
"args": ["-y", "recon"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Recon 执行以下任务... Claude: [自动调用 Recon MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"recon": {
"command": "npx",
"args": ["-y", "recon"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Passive domain intelligence from public sources. Queries DNS records, Microsoft/Google identity endpoints, and certificate transparency logs to build a picture of an organization's technology stack: no credentials, no API keys, no active scanning.
Drop in a domain, get an evidence-backed read on its identity stack, email posture, and cloud footprint in seconds, with the uncertainty widened when the public channel is sparse.
Defensive use only. recon is designed for legitimate security posture assessment, IT architecture review, vendor due diligence, and defensive hardening. It performs zero active scanning and zero credentialed access. See docs/legal.md for the full intended-use policy.
recon contoso.com
Contoso Ltd
contoso.com
──────────────────────────────────────────────────────────────────────────────
Provider Microsoft 365 (primary) via Proofpoint gateway + Google Workspace (secondary)
Tenant a1b2c3d4-e5f6-7890-abcd-ef1234567890 • NA
Auth Federated (Entra ID + Google Workspace)
Confidence ●●● High (4 sources)
Services
Email Microsoft 365, Google Workspace, Proofpoint, DMARC, DKIM,
SPF: strict (-all), BIMI
Identity Okta, Google Workspace (managed identity)
Cloud Cloudflare (CDN), AWS Route 53 (DNS)
Security Wiz, CAA: 3 issuers restricted
Collaboration Slack, Atlassian (Jira/Confluence)
High-signal related domains
api.contoso.com, login.contoso.com, portal.contoso.com, sso.contoso.com,
admin.contoso.com, status.contoso.com, support.contoso.com
(57 total, 50 more, use --full to see all)
Insights
Federated identity indicators observed (likely Okta, enterprise SSO)
Email security 4/5: DMARC reject, DKIM, SPF strict, BIMI
Email gateway: Proofpoint in front of Exchange
Dual provider: Google + Microsoft coexistence
Examples use Microsoft's fictional company names (Contoso, Northwind Traders, Fabrikam). Tenant IDs, services, and domains are fabricated. No real company is depicted.
Works for Microsoft 365, Google Workspace, or any provider. Also runs as an MCP server for AI agents; the default pip install recon-tool includes MCP support.
Jump to: Install · Usage · How it works · AI agents and MCP · Automation and JSON · Limitations · Docs index
Requires Python 3.11+.
pip install recon-tool # includes MCP server
pip install -U recon-tool # upgrade
recon doctor # verify connectivity
recon contoso.com # default panel
recon contoso.com --explain # full reasoning + provenance DAG
recon contoso.com --full # everything (services + domains + posture)
recon contoso.com --profile fintech # apply a posture lens
recon contoso.com --confidence-mode strict # drop hedging on dense-evidence targets (current)
recon contoso.com --direct-probes # opt in to direct CSE / BIMI-VMC probes (off by default)
recon contoso.com --json # structured JSON for piping
recon batch domains.txt --json # batch (cross-domain token clustering)
cat domains.txt | recon batch - --json # batch reading domains from stdin
recon batch domains.txt --json --include-ecosystem # add v1.8 ecosystem hypergraph
recon batch domains.txt --summary # one aggregate-only cohort summary (panel)
recon batch domains.txt --summary --json # the same, as JSON for downstream tooling
recon contoso.com --chain --depth 2 # follow related-domain breadcrumbs
recon delta contoso.com # diff against last cached snapshot
recon mcp # start MCP server (stdio)
Built-in profiles: fintech, healthcare, saas-b2b, high-value-target, public-sector, higher-ed. Custom profiles live in ~/.recon/profiles/*.yaml.
Shell completion. recon ships tab-completion for the command tree and flags (via Typer). Install it for your current shell, or print the script to wire it up yourself:
recon --install-completion # add completion to your shell config
recon --show-completion # print the completion script (bash/zsh/fish/powershell)
After --install-completion, start a new shell for it to take effect.
See docs/README.md for the organized documentation index.
高质量的MCP工具,易于使用
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:Recon 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | recon |
| Topics | domain-intelligenceemail-securitym365mcpmicrosoft365python |
| GitHub | https://github.com/blisspixel/recon |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-10 · 更新时间:2026-06-10 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端