모델 컨텍스트 프로토콜을 통해 그래프 데이터베이스 작업을 관리하기 위한 Neo4j MCP 서버 구현입니다.
🔌 Cursor와 Claude Desktop 모두와 호환됩니다!
npx를 사용하여 서버를 직접 실행할 수 있습니다.
지엑스피1
Related MCP server: M.I.M.I.R - Multi-agent Intelligent Memory & Insight Repository
패키지를 글로벌하게 설치하려면 다음을 수행하세요.
npm install -g neo4j-mcpserver그런 다음 실행합니다.
NEO4J_CONNECTION=neo4j+s://your-instance.databases.neo4j.io,neo4j,your-password neo4j-mcpserverNeo4j 연결 세부 정보는 두 가지 방법으로 제공할 수 있습니다.
단일 연결 문자열 사용:
NEO4J_CONNECTION=<uri>,<user>,<password>별도의 환경 변수 사용:
NEO4J_URI=<your-uri>
NEO4J_USER=<your-user>
NEO4J_PASSWORD=<your-password>프로젝트 루트에서 .env 파일을 사용할 수도 있습니다.
NEO4J_URI=neo4j+s://your-instance.databases.neo4j.io
NEO4J_USER=neo4j
NEO4J_PASSWORD=your-passwordCursor에서 Neo4j MCP 서버를 설정하려면:
커서 설정 열기
기능 > MCP 서버로 이동
"+ 새 MCP 서버 추가" 버튼을 클릭하세요
다음 정보를 입력하세요:
이름: 서버의 별명을 입력하세요(예: "neo4j-mcp")
유형: 유형으로 "명령"을 선택하세요
명령어: 서버를 실행하기 위한 명령어를 입력하세요: GXP7
중요: 자격 증명을 실제 Neo4j 데이터베이스 자격 증명으로 바꾸세요.
Neo4j 데이터베이스에 대해 Cypher 쿼리를 실행합니다.
Cursor에서의 사용 예:
MATCH (n) RETURN n LIMIT 5문제가 발생하는 경우:
Neo4j 자격 증명 확인
Neo4j URI, 사용자 이름 및 비밀번호가 올바른지 확인하세요.
Neo4j 데이터베이스에 액세스할 수 있는지 확인하세요.
경로 문제
설치 경로에 공백이 없는지 확인하세요.
경로에 슬래시(/)를 사용하세요
도구 감지 문제
커서를 다시 시작해 보세요
서버가 실행 중인지 확인하세요(Cursor의 MCP 서버 목록 확인)
환경 변수가 올바르게 설정되었는지 확인하세요
로컬로 실행하려면:
git clone <repository-url>
cd neo4j-mcpserver
npm install
npm run build
npm start아이에스씨
Execute a Cypher query against the Neo4j database
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The Cypher query to execute | |
| parameters | No | Query parameters (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. While 'Execute' implies a write operation, the description doesn't clarify whether this tool can perform read-only queries, mutations, or both. It lacks information about permissions required, transaction handling, result formats, or potential side effects like data modification or performance impacts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that communicates the core functionality without unnecessary words. It's appropriately sized for a straightforward tool and is front-loaded with the essential information. Every word earns its place in this minimal description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a database query execution tool with no annotations and no output schema, the description is insufficient. It doesn't explain what kind of results to expect, error handling, security considerations, or whether queries are read-only or can modify data. The combination of a powerful database tool with minimal description creates significant gaps in understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description adds no additional parameter information beyond what's in the schema. This meets the baseline expectation when schema coverage is complete, but doesn't provide extra value like Cypher syntax examples or parameter format guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Execute') and target resource ('Cypher query against the Neo4j database'), making the purpose immediately understandable. It lacks sibling differentiation, but since there are no sibling tools on this server, this doesn't reduce clarity. The description avoids tautology by specifying what type of query and database are involved.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or limitations. It simply states what the tool does without context about appropriate use cases. With no sibling tools, the need for differentiation is reduced, but general usage context is still missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
neo4j-queryScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool has a single, clear purpose: executing Cypher queries against a Neo4j database.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'neo4j-query' follows a clear and descriptive pattern, though no pattern can be established or broken with a single tool.
A single tool is too few for a database server's apparent scope, which typically requires operations like creating, updating, deleting, and querying data. This minimal set limits functionality and forces all operations through a generic query interface, which is insufficient for structured interactions.
The tool surface is severely incomplete for a Neo4j database server. While 'neo4j-query' allows executing arbitrary Cypher queries, it lacks dedicated tools for common operations like creating nodes, updating relationships, or managing transactions, leaving significant gaps that agents must work around with raw queries.
Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, documents.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Codebase graphs, caller impact analysis, and recorded project context for AI coding agents.
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
