SNOMED GraphRAG MCP Server
Provides tools for querying a Neo4j graph database containing SNOMED CT medical terminology, enabling graph-based search and traversal of concepts and relationships.
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., "@SNOMED GraphRAG MCP Server Find concepts related to sctid 119299002"
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.
SNOMED GraphRAG MCP Server
基于 Neo4j 与 SNOMED 子集的 GraphRAG MCP 服务,提供 graph_search_concept、graph_get_related 两个 Tools。
1. 快速开始
环境:Python 3.10+、Neo4j 5.x(Docker Desktop 且 Docker 已运行)、uv 或 pip、PowerShell 或 CMD。以下在项目根执行。
1.1 数据与 Neo4j
# 生成 concept_minimal、复制 DR
python scripts/gen_concept_minimal.py
copy SNOMED_CSV\DR_118170007_new.csv docker\import\
# 启动 Neo4j
cd docker && docker compose up -d --force-recreate && cd ..
# Neo4j 启动约 10s 后执行 build(PowerShell)
Get-Content docker\import\build_minimal.cypher -Raw | docker exec -i neo4j cypher-shell -u neo4j -p password
# 校验(PowerShell)
$env:NEO4J_PASSWORD="password"
uv run python scripts/check_neo4j.pyCMD 下:
type docker\import\build_minimal.cypher | docker exec -i neo4j cypher-shell -u neo4j -p password;set NEO4J_PASSWORD=password再执行check_neo4j.py。Neo4j 密码非password时替换。
1.2 安装依赖
uv sync或 pip install "mcp[cli]" neo4j。
1.3 配置 MCP(Cursor / Claude Desktop)
在 MCP 配置中加入(cwd、command 改成本机项目绝对路径):
{
"mcpServers": {
"snomed-graph-rag": {
"command": "D:/ai/gientech/code/rag-neo-mcp-week6/.venv/Scripts/python.exe",
"args": ["-u", "-m", "mcp_server.main"],
"cwd": "D:/ai/gientech/code/rag-neo-mcp-week6",
"env": { "PYTHONUNBUFFERED": "1", "NEO4J_PASSWORD": "password" }
}
}
}Cursor:设置 → MCP,或编辑
%USERPROFILE%\.cursor\mcp.json。完整示例见mcp_config_example.json。若出现「No server info found」:确保
command指向 项目根\.venv\Scripts\python.exe,args含-u,或改用run_mcp.bat作command、args: []。
1.4 重启 Cursor,确认 Docker 中 Neo4j 已启动
Related MCP server: neo4j-mcp
2. 探索更复杂的 RAG 应用场景和范式
相对「文档切片 + 向量检索 + 一次查回」的简单 RAG,本项目从应用场景和检索范式两方面做更复杂探索,并落实到实现。
2.1 应用场景
维度 | 简单 RAG | 本项目 |
数据形态 | 扁平文本/切片 | 领域知识图谱:SNOMED 本体(ObjectConcept、RoleGroup、定义关系) |
领域 | 通用文档 | 医学术语:FSN、sctid、SPECIMEN_SOURCE_IDENTITY 等 |
语义结构 | 语义相似 | 显式关系: |
本项目实现:build_minimal.cypher 构建 ObjectConcept、RoleGroup、HAS_ROLE_GROUP、SPECIMEN_SOURCE_IDENTITY;mcp_server/neo4j_client + Cypher 查询该图。
2.2 检索范式
多范式并存(非单一向量检索):
graph_search_concept:按 FSN 子串或 sctid 的关键词/属性检索(图上的索引查找);
graph_get_related:按图结构 + 关系类型的图遍历检索,模式
(c:ObjectConcept)-[:HAS_ROLE_GROUP]->(rg:RoleGroup)-[r]->(c2:ObjectConcept),type(r) IN $types。
图原生检索:用 Cypher 在 Neo4j 上做模式匹配,关系类型直接参与查询,替代「向量检索 + 过滤」。
2.3 工具化 / Agent 范式
RAG 即工具:图检索封装为 MCP 的
graph_search_concept、graph_get_related,由 Cursor/LLM 按问题选工具、组合调用,而非固定一条检索流水线。检索与生成解耦:模型根据自然语言选工具与参数(如
rel_types),再基于图返回结果生成回答(Tool-augmented / Agent-RAG)。
3. MCP 应用
3.1 在 Cursor 里用
在对话中用自然语言提问,例如:「sctid 119299002 有哪些 SPECIMEN_SOURCE_IDENTITY 相关概念?」、「按 FSN 搜 Concept (119299002)」。
模型会自动选
graph_search_concept或graph_get_related,把 Neo4j 查到的结果当上下文再回答。流程:提问 → Cursor 调用 Tool → MCP 查 Neo4j → 文本结果给模型 → 生成回答。
3.2 两个 Tool
Tool | 作用 |
graph_search_concept | 按 FSN 子串或 sctid 检索 ObjectConcept;参数 |
graph_get_related | 按 sctid 与关系类型(如 SPECIMEN_SOURCE_IDENTITY)查经 RoleGroup 的相邻概念;参数 |
3.3 示例问题
「sctid 119299002 有哪些 SPECIMEN_SOURCE_IDENTITY 相关概念?」→
graph_get_related「在 SNOMED 图里查和 116154003 有定义关系的概念」→
graph_get_related「按 FSN 搜 Concept (119299002)」→
graph_search_concept
3.4 前端界面(可选)
不通过 Cursor 时,可在浏览器查图:uv sync --extra web,然后$env:NEO4J_PASSWORD="password";uv run uvicorn web.app:app --host 127.0.0.1 --port 8000,打开 http://127.0.0.1:8000。
3.5 错误与边界
sctid 不存在、keyword 无匹配、Neo4j 断线时,Tool 返回明确提示,不抛错。
Available Tools
2 toolsgraph_search_conceptB
在 SNOMED 图中按 FSN 或 sctid 检索概念。 keyword: 关键词(FSN 子串或 sctid) limit: 返回条数
Inputs: keyword (required), limit. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: graph_search_concept retrieves concepts by search, and graph_get_related fetches related concepts via relationships. There is no overlap or ambiguity.
Both tools follow the consistent 'graph_<verb>_<noun>' pattern with snake_case. 'graph_search_concept' and 'graph_get_related' are parallel and predictable.
With only 2 tools for a complex domain like SNOMED CT, the server is severely under-scoped. Typical SNOMED interactions require many more operations (e.g., detail retrieval, hierarchy browsing, multiple relation types).
The tool surface has major gaps: no tool to get full concept details (descriptions, synonyms), no hierarchy navigation, and graph_get_related is limited to a single relation type (SPECIMEN_SOURCE_IDENTITY). Missing core CRUD-like operations for a knowledge graph.
Maintenance
Related MCP Connectors
Repository knowledge graph MCP server for codebase understanding and debugging.
MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Stateless agentic tools over MCP: concept extraction, long-context, knowledge graph, planning.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables LLMs to perform semantic and fulltext searches within Neo4j while executing complex, search-augmented Cypher queries for GraphRAG applications. It provides tools for database schema discovery and supports multi-provider embeddings to facilitate advanced graph traversals.53MIT
- AlicenseNot gradedqualityBmaintenanceMCP server for Neo4j graph database operations, enabling Cypher queries, node/relationship management, and schema discovery.1BSD 3-Clause
- FlicenseNot gradedqualityBmaintenanceMCP server for indexing source code from repositories into a Neo4j graph database and enabling Graph RAG-based search and traversal of functions via natural language queries.-
- AlicenseAqualityDmaintenanceMCP server for Neo4j that provides abstract graph operations for LLMs, enabling safe and consistent interaction with Neo4j databases through tools like search, insert, update, delete, and schema introspection.8MIT