GxP MDM MCP Server
GxP MDM MCP Server - 面向 Claude / ChatGPT / Cursor 的 Cypher 工具
该 MCP 服务器通过 Cypher 查询,将您的计算机化系统清单构建为知识图谱。任何 Claude/ChatGPT 代理现在都可以查询 GxP 主数据,而不会产生幻觉。
架构
Claude / ChatGPT / Cursor
|
| MCP (stdio)
v
mcp_server.py (14 tools)
|
| Cypher queries
v
Neo4j (or MOCK mode: NetworkX + JSON) <- your MDM golden record为什么选择 Cypher?
影响范围(Blast radius) 是一种图遍历:
MATCH (start)-[:SENDS_VIA*1..3]->(downstream)— 这在 SQL 中无法实现用于 ALCOA+ 调查的数据血缘
法规真值 — 代理只能引用 Cypher 返回的条款,从而防止幻觉
Related MCP server: NOMIK
提供的 14 个工具
工具 | Cypher | 功能说明 |
| 自定义 Cypher | 用于探索的安全只读 Cypher |
|
| 完整清单 - 审计员会首先询问这个 |
| 完整子图 | 系统 + 功能 + 电子记录 + 供应商 + 接口 |
|
| 杀手级应用:变更会影响到哪些下游 GxP 系统? |
| 反向遍历 | 数据来自哪里? |
|
| 防幻觉:只能引用这些条款 |
|
| 带 GxP 标志的 API/文件/手动接口 |
|
| 未验证的 GxP Direct 系统 |
|
| 逾期的定期评审 |
|
| 电子签名、批放行、效价(高风险功能) |
|
| 供应商审计状态、SOC2 |
|
| 针对某类记录的数据血缘 |
|
| GxP Direct 清单 |
| 综合查询 | 编排 3 组 Cypher 查询,并按 GAMP 5 / CSA 生成影响评估 |
快速开始(无需 Neo4j - 模拟模式)
cd gxp_mdm_mcp_server
pip install -r requirements.txt
# Mock mode: uses JSON + NetworkX, no Neo4j required
python scripts/test_tools.py
# Should show:
# - List 4 systems
# - Veeva QMS details with downstream SAP
# - Blast radius: Veeva -> SAP
# - REJECT for audit trail purge
# - Minor for version upgrade模拟模式非常适合 POC 和 Claude Desktop 测试。
使用 Neo4j 的生产模式
# .env - set Neo4j creds
cp .env.example .env
# Edit .env with your Neo4j URI
# Start Neo4j
docker-compose up -d neo4j
# Load sample data + schema
python scripts/load_sample_data.py
# Test with Neo4j
python scripts/test_tools.py
# Start API harness (optional)
uvicorn src.api_server:app --reload --port 8000
# http://localhost:8000/cypher/list_all_systems
# http://localhost:8000/cypher/blast_radius?system_id=SYS-VEEVA-QMS-001Claude Desktop 配置
找到您的 Claude 配置文件:
~/Library/Application Support/Claude/claude_desktop_config.json(Mac)或%APPDATA%/Claude/claude_desktop_config.json(Win)添加以下内容(请使用绝对路径):
{
"mcpServers": {
"gxp-mdm-cypher": {
"command": "python",
"args": ["/absolute/path/to/gxp_mdm_mcp_server/src/mcp_server.py"],
"env": {
"NEO4J_URI": "",
"NEO4J_USERNAME": "neo4j",
"NEO4J_PASSWORD": "password"
}
}
}
}模拟模式下请将 NEO4J_URI 留空。使用 Neo4j 时,请设置为 bolt://localhost:7687。
重新启动 Claude Desktop。您应该会在 🔌 下看到 14 个工具。
尝试以下提示:
List all GxP Direct systems in my inventory
> calls list_all_systems(gxp_impact="Direct")
What happens if I change Veeva QMS? Show blast radius
> calls get_blast_radius(system_id="SYS-VEEVA-QMS-001")
Assess this change: Enable audit trail purge after 7 years for Veeva QMS
> calls assess_change_impact -> should REJECT per 21CFR11.10(e)
Assess Veeva upgrade from 24R1 to 24R2 with no e-sig change
> calls assess_change_impact -> should be Minor per CSA low riskCursor 配置
请参阅 config/cursor_config.json.example — 将其添加到 .cursor/mcp.json
ChatGPT(支持 MCP)
如果为 ChatGPT 自定义 GPT 使用 MCP,请参考 config/chatgpt_mcp_config.json。ChatGPT 将通过 stdio 调用工具。
Cypher 查询 - 事实依据
所有查询均位于 src/cypher_tools.py。关键查询如下:
影响范围(护城河):
MATCH (start:ComputerizedSystem {system_id: $system_id})
MATCH path = (start)-[:SENDS_VIA*1..$depth]->(downstream:ComputerizedSystem)
WHERE downstream.gxp_impact IN ['Direct', 'GxP Relevant']
RETURN downstream.system_id, length(path) as distance法规防幻觉:
MATCH (s:ComputerizedSystem {system_id: $system_id})
OPTIONAL MATCH (s)-[:HAS_FUNCTION]->(f)-[:REGULATED_BY]->(reg)
RETURN collect(DISTINCT reg) as regulations智能体只能引用这里返回的 clause_ids。
从 POC 到生产
将
data/*.json替换为真实的 Veeva Vault API + ServiceNow CMDB + Okta添加用于更新
validation_status的写入工具(含审批工作流)添加面向法规 RAG 的向量搜索工具(引入 GAMP 5 第 2 版)
添加按计划调用
find_periodic_review_overdue的定期评审智能体
您现在拥有每个 CSV 自动化智能体都必须查询的那一层。
故障排除
No module named mcp:运行pip install mcpClaude 看不到工具:检查配置中的绝对路径,重启 Claude,并查看日志
~/Library/Logs/Claude/mcp*.logNeo4j 连接失败:会自动回退到模拟模式 — 请检查
NEO4J_URI
祝您好运,独占市场。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceTransforms code repositories and development documentation into a queryable Neo4j knowledge graph, enabling AI assistants to perform intelligent code analysis, dependency mapping, impact assessment, and automated documentation generation across 15+ programming languages.7
- FlicenseNot gradedqualityDmaintenanceAI-native code intelligence graph that builds a persistent knowledge graph of your codebase in Neo4j and exposes it to AI assistants via MCP, enabling contextual code analysis, impact analysis, and dependency tracking.21

coderadiusofficial
AlicenseNot gradedqualityAmaintenanceEnables AI agents to query architecture context, data contracts, and blast radius to prevent cross-repo architectural breakage before merging.30Apache 2.0- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query and analyze code across multiple repositories through a unified knowledge graph, with tools for symbol search, impact analysis, and graph algorithms.48MIT
Related MCP Connectors
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
Architecture-grounded query for AI agents. Governance constraints, system dependencies, evidence.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/saram-io/gxp_mdm_mcp_server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server