enterprise-scout-mcp
Imports warehouse parquet data—including enterprise entities and equity relationships—into Neo4j, with dry-run support for graph storage and relationship analysis.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@enterprise-scout-mcpcollect 小米's business registration and equity info"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
enterprise-scout-mcp
企业工商/穿透情报 MCP 服务。Python 编排层(人设、风控路由、行为配额)+ 多通道采集,输出到 EnterpriseLake G:/enterprise_lake/。
与 enterprise-mcp-server(Handaas 单源 API)互补:工商主路径只走 ENScan_GO;Handaas 为可选付费补源。
MCP 工具
工具 | 说明 |
| 按关键词采集(平台 / 深度 / fields / persona) |
| 轻量搜索(depth=0) |
| 批量采集(支持 checkpoint) |
| 查看统一 cookie 注册表(GSXT / 爱企查 / ENScan) |
| 把本地 cookie 写入 ENScan config |
| 重跑 |
| 检查 ENScan / Handaas / 人设(可 probe sidecar) |
| 探活 ENScan / proxy_pool |
| warehouse parquet → Neo4j(默认 dry_run) |
Related MCP server: Enterprise Operation Insight MCP Server
快速启动
cd E:\Project\enterprise-scout-mcp
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -e ".[dev,warehouse]"
# 浏览器回退(可选): pip install -e ".[browser]"
copy config.example.yaml config.yaml
enterprise-scout-mcp # stdio(Cursor / Hermes 默认)
enterprise-scout-mcp streamable-http # HTTP :8000Cursor / Hermes 配置
stdio(推荐本地):
{
"mcpServers": {
"enterprise-scout-mcp": {
"command": "enterprise-scout-mcp",
"args": [],
"cwd": "E:/Project/enterprise-scout-mcp"
}
}
}streamable-http:
{
"mcpServers": {
"enterprise-scout-mcp": {
"type": "streamableHttp",
"url": "http://127.0.0.1:8000/mcp"
}
}
}开发 CLI
编排层调试(非 MCP 面):
escout doctor
escout personas
escout collect 小米 -p aiqicha
escout collect-batch --file keywords.txt -p aiqicha --checkpoint .state/batch.json
escout import-neo4j --dry-run # 统计 warehouse 行数
escout import-neo4j # 写入 Neo4j(需 pip install -e ".[graph]")
escout sessions list # 统一查看 cookie 路径与就绪状态
escout sessions import gsxt --from-file cookies.json
escout sessions import aiqicha --from-file ./secrets/aiqicha_cookies.txt
escout sessions warmup gsxt # 无头浏览器刷新 JSL+CT(需 .[browser])
escout sync-cookies --from-file ./secrets/aiqicha_cookies.txt # 兼容别名 → sessions import aiqicha
escout register-hermes # 写入 ~/.hermes/config.yaml
escout doctor --probe # 含 ENScan / proxy_pool 探活 + sessions
escout smoke-sidecars # 仅 sidecar 探活(CI/脚本用)
escout smoke-collect 小米 # 实机采集冒烟(需 ENScan 运行)
escout sync-gsxt-session --from-file cookies.json # 兼容别名 → sessions import gsxt
escout sync-gsxt-session --warmup # 兼容别名 → sessions warmup gsxt
escout collect 苏州挚途 --dims registry --prefer-tier l1 -p gsxt
escout smoke-registry-l1 苏州挚途 # L1 registry 穿通验收
escout drain-retry --dry-run # 列出 retry_queue 待重跑任务
escout drain-retry --limit 20 # 重跑 captcha 队列(成功 → .archive)采集策略(三级源): 默认 ensan_only — 爱企查 / 天眼查等走 ENScan L2。L1 官方工商:escout collect 关键词 --dims registry --prefer-tier l1 -p gsxt(需先在 shiming.gsxt.gov.cn 个人登录并 sync-gsxt-session 导入 cookie)。routing.l1_fallback_to_l2: true 时 L1 失败自动降级 ENScan(degraded=true);L1/L2 字段不一致写入 warehouse/conflicts/part.parquet。ENScan 不可用时 L2 直接报错。
默认 fields:enterprise_info,partner,holds,invest,branch(写入实体 + 股权边)。可用 -f / MCP fields 覆盖。
state_persist: true 时,日配额与路由成功率写入 state_dir(默认 ./.state/)。collect-batch --checkpoint 断点续跑:仅 ok/partial 记为 done,error/captcha/blocked 下次会重试。
neo4j.enabled + neo4j.auto_import: true 时,单采 / 批采结束 / drain 成功后会自动 merge warehouse → Neo4j(需 pip install -e ".[graph]")。
Warehouse 输出
output.parquet_enabled: true 时写入 EnterpriseLake:
路径 | 内容 |
| 企业实体行 |
| 股权/投资/分支边(partner/holds/invest/branch) |
| partial / captcha 分级 JSON |
列定义见 docs/warehouse-schema.md(与 EnterpriseLake layout 对齐)。
架构
MCP (enterprise-scout-mcp)
└─ CollectorScheduler
├─ TierAwareRouter ← L1 GSXT / L2 ENScan (when --prefer-tier)
├─ RiskAwareRouter ← ensan_only default for aiqicha/tyc
├─ GsxtOfficialChannel ← L1 registry (personal session)
├─ EnsanGoChannel ← L2 ENScan :31000
└─ HandaasChannel ← optional paid APISidecar
docker compose up -d proxy_pool
# ENScan: cd ..\ENScan_GO && .\enscan.exe -api测试
pytest -qCI: GitHub Actions workflow .github/workflows/test.yml runs the same suite on push/PR.
This server cannot be deployed
Maintenance
Related MCP Connectors
Russian company lookup (EGRUL/INN), Cyrillic search, RU page to Markdown. Pay per call in USDC.
CompanyLens is a remote MCP server giving AI agents instant access to official company registry data across 19 jurisdictions in Europe, the Americas, and Asia-Pacific. Eighteen read-only tools let you search companies and people, look up officers and beneficial owners, map corporate networks through shared directors, screen names against the UK disqualified directors register, find every company at a registered address, and pull filing history — all from a single connector. Visit our website: https://companylens.io
Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.
64 individually paid Chinese company data tools at 0.011 USDC per tool call via remote MCP and x402 on Base. 68 MCP tools total, including the schema helper and legacy tools. Selected registration, shareholder, risk, IP, legal, tax, website and other records; consult each live tool schema. Legacy Basic (3 modules) and Full (9 modules) remain 0.032 / 0.093 USDC, not bundles of the new tools. Discovery is free; data queries require a funded USDC wallet and x402 spending approval. Plain MCP clients do not pay automatically. Start with an exact Chinese legal name or company_id in company_detail; most company tools need its returned company_id. Record-detail tools use record_id from a matching separately paid parent list. New paged lists return the first page only, at most 5 rows; legacy lists at most 10. No automatic pagination, complete-history, factory or supplier-safety guarantee. Empty data is not no risk; statistics/trends are not detailed records. The old resolver is a capability notice, not a free lookup; native MPP is paused. Upstream checks passed for the 64 new tools; real-wallet payment-to-delivery acceptance and commercial redistribution/overseas delivery permission review remain pending. Guide: https://yangchunhong3000.github.io/cn-evidence-public-docs/v3-tools.html
Related MCP Servers
- FlicenseNot gradedqualityFmaintenanceEnables querying Chinese enterprise business data including company profiles, shareholder information, investments, branch offices, and key personnel through fuzzy search and detailed lookups.3-
- FlicenseNot gradedqualityDmaintenanceProvides comprehensive data insights into enterprise operations, including company trends, financing history, market rankings, and sentiment analysis. It enables users to perform keyword-based searches and evaluate business scale, tax qualifications, and competitive project profiles.3-
- AlicenseBqualityBmaintenanceAggregates multiple cyberspace search engines (FOFA, Quake, Hunter, ZoomEye) into a unified MCP server, enabling asset search, pagination, statistics, and account info retrieval.26MIT

CNBizAPI MCP Serverofficial
AlicenseNot gradedqualityDmaintenanceEnables AI agents to query detailed information on 77M+ Chinese companies, including basic data, shareholders, legal risks, and more, through a pay-per-query MCP server.1MIT