enterprise-scout-mcp
Enterprise-scout-mcp is an MCP service for collecting Chinese enterprise registry/equity intelligence and managing related session and warehouse workflows.
Collect or search enterprise data by keyword with configurable platform, depth, fields, persona, and preferred tier (e.g., aiqicha/GSXT/ENScan).
Run batch collections with optional checkpointing and stop-on-blocked behavior.
Inspect and sync cookie/session registries for GSXT, aiqicha, and ENScan.
Diagnose ENScan/Handaas/persona availability and live-probe ENScan/proxy_pool sidecars.
Re-run failed or captcha retry-queue jobs and archive successful retries.
Import warehouse parquet data into Neo4j, with dry-run row counting.
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-mcp collect 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);股权请用 |
| 轻量搜索(depth=0) |
| 批量采集(支持 checkpoint) |
| 从湖边表本地 BFS 组穿透树(只读) |
| 按需用 aiqicha 迭代补采缺失法人邻居(拒绝 tyc) |
| 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 cdp-hint # GSXT 瑞数:真实 Chrome CDP 接管步骤
escout sessions warmup gsxt # nodriver 刷新 cookie(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)
escout corpus init # 创建语料目录 + 示例 JSONL
escout corpus status # L3 / judicial 语料目录状态语料格式见 docs/corpus-schema.md。
采集策略(三级源): 默认 ensan_only — 爱企查 / 天眼查等走 ENScan L2。L1 官方工商默认 integrations.gsxt.search_mode: browser:在真实浏览器页面环境内调用搜索 API(绕过瑞数 CT/瑞数对 httpx 的拦截),不要对 412/405 盲目重试或换 IP。
模式 | 配置 | 说明 |
CDP 接管(推荐) |
| 真实 Chrome → Playwright |
nodriver 自建 |
| 持久 profile + 有头浏览器;NWAF 仍可能拦截自动化指纹 |
httpx API |
| 仅 JSL 可过;瑞数 Environment Checking 会 412 — 勿对 521/412 换 IP 硬刚 |
pip install -e ".[browser]"
escout sessions cdp-hint # 打印 Chrome 启动命令与步骤
# 1) 按 hint 启动 Chrome,打开 gsxt.gov.cn 并完成验证
# 2) config.yaml: browser_cdp_port: 9222
escout sessions import gsxt --from-file .state/gsxt_browser_export.json
escout smoke-registry-l1 苏州挚途VPN/Clash:proxy_url: http://127.0.0.1:7897 或 $env:HTTPS_PROXY=...(改善连通性,不能单独绕过瑞数环境检测)。routing.l1_fallback_to_l2: true 时 L1 仍失败则降级 ENScan(degraded=true)。
默认 fields:enterprise_info,partner,holds,invest,branch(写入实体 + 股权边)。可用 -f / MCP fields 覆盖。可选加 supplier(供给边 relation=supply)。
股权穿透(本地树,非天眼查计费):
escout collect 示例公司 -p aiqicha
escout equity-tree 示例公司 --depth 2
escout equity-expand 示例公司 --depth 2 --min-ratio 20 # 强制 aqc;勿并行树读 warehouse/edges/equity/part.parquet 做 BFS;expand 只补从未作为 query_keyword 采集过的法人邻居(跳过自然人与分支)。边写入按 (src,dst,relation) 去重。
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
├─ PersonaEngine ← 人设 UA / locale / tz / OS
├─ RiskAwareRouter ← ensan_only default for aiqicha/tyc
├─ TierAwareRouter ← L1 GSXT / L2 ENScan (--prefer-tier)
├─ BehaviorOrchestrator ← 配额 / 冷却 / 延迟
├─ EnvironmentValidator ← UA/TLS/locale/语言/geo/时区/OS
├─ disguise egress ← curl_cffi [transport] · Camoufox [camoufox]
├─ CaptchaHandler ← rotate_ip | CapSolver API | OpenCV 滑块 [captcha]
├─ GsxtOfficialChannel ← L1 registry (CDP / nodriver)
├─ EnsanGoChannel ← L2 ENScan :31000
└─ HandaasChannel ← optional paid API维度路由(--dims / MCP dims):registry(L1 GSXT / L2 ENScan)、equity(股东/投资/分支 → ENScan)、digital/ip(备案/小程序等 → ENScan)、credit(Handaas 凭证可用时走付费 API)/judicial(本地 corpus 或 stub)/prefer-tier l3(corpus/l3 JSON/JSONL)、prefer-tier l3(academic stub)。多维度一次采集会自动合并 payload。
模块落地状态见 escout doctor → architecture / tiers。
Neo4j:
escout doctor # warehouse.counts + neo4j.connectivity(enabled 时)
escout import-neo4j --dry-run
escout import-neo4j # Company / HOLDS / Supplement / ConflictPhase 3 — Fine UI(参考 E:/Project/fine-2.7.2/README_images:设置 + 爱企查 + 多 Tab):
# 首次(或 venv 损坏时)
.\setup-venv.ps1 -Ui
# 推荐:不依赖 PATH 里的 escout
.\serve-ui.ps1 # 自动 build ui/dist + API :8790
.\serve-ui-dev.ps1 # API :8790 + Vite :5179 热更新
# 或手动
.\.venv\Scripts\escout serve
cd ui && npm run dev # :5179,/api 代理到 8790页面:设置(warehouse / Neo4j / 通道)、爱企查(查询 + 股东/投资/分支 Tab)、状态(verify checklist)。
验收:
escout verify --summary
pytest -q可选依赖:
pip install -e ".[transport]" # curl_cffi TLS 伪装
pip install -e ".[camoufox]" # Camoufox 浏览器出口
pip install -e ".[captcha]" # OpenCV 滑块定位Sidecar
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.
Available Tools
10 toolsenterprise_collectC
Collect enterprise info. L1: prefer_tier=l1 + platform gsxt (needs GSXT session).
Inputs: keyword (required), dims, depth, fields, +3 more. Returns: result
enterprise_collect_batchC
Collect multiple company keywords (comma or newline separated).
Inputs: keywords (required), depth, fields, platform, +3 more. Returns: result
enterprise_searchC
Lightweight search — collect with depth=0 (same default equity fields).
Inputs: keyword (required), fields, platform. Returns: result
scout_doctorC
Report availability of ENScan_GO, Handaas, personas; optional live sidecar probe.
Inputs: probe_sidecars. Returns: result
scout_drain_retryC
Re-run captcha/failed jobs from raw/retry_queue; archive on success.
Inputs: limit, dry_run, include_partial. Returns: result
scout_import_neo4jC
Import warehouse parquet into Neo4j (dry_run=True counts rows only).
Inputs: dry_run. Returns: result
scout_sessionsB
List unified session/cookie registry (GSXT L1, aiqicha L2, ENScan mirror).
Inputs: no named parameters. Returns: result
scout_sidecarsB
Live-probe ENScan_GO and proxy_pool sidecars.
Inputs: no named parameters. Returns: result
sync_enscan_cookiesC
Import aiqicha cookie and sync into ENScan_GO config.yaml.
Inputs: cookie_file. Returns: result
sync_gsxt_sessionB
Import GSXT personal-login cookies after browser login at shiming.gsxt.gov.cn.
Inputs: cookie_file (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
enterprise_collect, enterprise_collect_batch, and enterprise_search overlap significantly — search is explicitly described as 'collect with depth=0', so an agent may struggle to pick the right entry point. scout_doctor and scout_sidecars also both probe sidecar availability with unclear boundaries, while the sync_* tools are distinct.
Two inconsistent prefixes (enterprise_* vs scout_*) are mixed with two verb styles: action-oriented names (enterprise_collect, sync_gsxt_session) coexist with noun-style names (scout_sessions, scout_doctor, scout_sidecars). Still readable, but no single predictable pattern.
Ten tools is a reasonable, well-scoped set for an enterprise collection pipeline covering collection, sessions, diagnostics, and export. Slightly heavy given that collect/search/batch and doctor/sidecars duplicate intent.
The surface covers collection, batch, search, session management, diagnostics, Neo4j import, and retry/drain, forming a coherent pipeline. Minor gaps exist around inspecting or deleting already-collected warehouse data and no explicit export/reporting operation.
Maintenance
Related MCP Connectors
Chinese company registry, litigation, IP and credit data for AI agents. Read-only remote MCP server.
15sos-entities — state business-entity registries in one normalised shape (fleet #2867).
454 OSINT recon tools + server-side entity correlation & person sweeps. Keyless.
B2B company domain discovery, web SERP footprint & firmographic enrichment API for AI agents.
1
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables querying Chinese enterprise business data including company profiles, shareholder information, investments, branch offices, and key personnel through fuzzy search and detailed lookups.4-
- FlicenseNot gradedqualityCmaintenanceProvides 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-

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- AlicenseAqualityBmaintenanceExposes 29 official business-registry actors as MCP tools for KYC/AML, beneficial-owner (UBO), credit-risk and adverse-media workflows across 11 jurisdictions (EU, US, UAE). Sourced via Apify; pay-per-result.387MIT