Skip to main content
Glama
deenesjakoruzh
memgraph

Memgraph MCP Server

Official
by memgraph
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

[!WICHTIG]
Dieses Repository wurde in das Monorepo Memgraph AI Toolkit integriert, um die Duplizierung von Tools zu vermeiden.
Es wird in einem Monat gelöscht. Bitte folgen Sie dort der MCP-Integration für alle zukünftigen Entwicklungen und öffnen Sie in diesem Repo gerne Probleme oder PRs.

🚀 Memgraph MCP-Server

Memgraph MCP Server ist eine leichtgewichtige Serverimplementierung des Model Context Protocol (MCP), die für die Verbindung von Memgraph mit LLMs entwickelt wurde.

mcp-server

⚡ Schnellstart

📹 Memgraph MCP Server-Schnellstartvideo

1. Führen Sie den Memgraph MCP Server aus

  1. Installieren Sie uv und erstellen Sie venv mit uv venv . Aktivieren Sie die virtuelle Umgebung mit .venv\Scripts\activate .

  2. Abhängigkeiten installieren: uv add "mcp[cli]" httpx

  3. Führen Sie den Memgraph MCP-Server aus: uv run server.py .

2. Führen Sie den MCP-Client aus

  1. Installieren Sie Claude für Desktop .

  2. Fügen Sie den Memgraph-Server zur Claude-Konfiguration hinzu:

MacOS/Linux

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

Windows

code $env:AppData\Claude\claude_desktop_config.json

Beispielkonfiguration:

{
    "mcpServers": {
      "mpc-memgraph": {
        "command": "/Users/katelatte/.local/bin/uv",
        "args": [
            "--directory",
            "/Users/katelatte/projects/mcp-memgraph",
            "run",
            "server.py"
        ]
     }
   }
}

[!NOTIZ]
Möglicherweise müssen Sie den vollständigen Pfad zur UV-Programmdatei in das Befehlsfeld eingeben. Sie erhalten diesen, indem Sie which uv unter MacOS/Linux oder where uv unter Windows ausführen. Stellen Sie sicher, dass Sie den absoluten Pfad zu Ihrem Server angeben.

3. Chatten Sie mit der Datenbank

  1. Führen Sie Memgraph MAGE aus:

    docker run -p 7687:7687 memgraph/memgraph-mage --schema-info-enabled=True

    Die Konfigurationseinstellung --schema-info-enabled ist auf True gesetzt, um LLM die Ausführung der Abfrage SHOW SCHEMA INFO zu ermöglichen.

  2. Öffnen Sie Claude Desktop und sehen Sie sich die aufgelisteten Memgraph-Tools und -Ressourcen an. Probieren Sie es aus! (Sie können Dummy-Daten aus Memgraph Lab Datasets laden.)

Related MCP server: mcp-graphql

🔧Werkzeuge

run_query()

Führen Sie eine Cypher-Abfrage gegen Memgraph aus.

🗃️ Ressourcen

get_schema()

Holen Sie sich Memgraph-Schemainformationen (Voraussetzung: --schema-info-enabled=True ).

🗺️ Roadmap

Der Memgraph MCP Server steht noch ganz am Anfang. Wir arbeiten aktiv daran, seine Funktionen zu erweitern und die Integration von Memgraph in moderne KI-Workflows noch einfacher zu gestalten. In Kürze werden wir eine TypeScript-Version des Servers veröffentlichen, um JavaScript-basierte Umgebungen besser zu unterstützen. Darüber hinaus planen wir, dieses Projekt in unser zentrales AI Toolkit- Repository zu migrieren, wo es neben anderen Tools und Integrationen für LangChain, LlamaIndex und MCP verfügbar sein wird. Unser Ziel ist es, ein einheitliches Open-Source-Toolkit bereitzustellen, das die nahtlose Entwicklung graphenbasierter Anwendungen und intelligenter Agenten mit Memgraph als Kern ermöglicht.

Available Tools

1 tool
run_queryC

Run a query against Memgraph

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden but only states the action without behavioral details. It doesn't disclose if this is read-only or mutating, what permissions are needed, error handling, or performance implications (e.g., timeouts, rate limits). This leaves significant gaps for safe invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, direct sentence with no wasted words—it's front-loaded and appropriately sized for a simple tool. Every word earns its place by stating the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't cover behavioral traits, parameter details, or return values, making it inadequate for a tool that likely executes database operations with potential side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds no parameter semantics beyond the schema's 'query' field. It doesn't explain what the query should contain (e.g., syntax, format), expected inputs, or constraints, failing to compensate for the low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Run a query against Memgraph' clearly states the action (run) and target (Memgraph), but it's vague about what type of query (Cypher? SQL?) and what resources are affected. Without sibling tools, differentiation isn't needed, but the purpose remains somewhat generic.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool—there are no alternatives mentioned, no context for usage, and no prerequisites or exclusions. The description assumes the agent knows when to run queries without any framing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedrun_query
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.8/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'run_query' follows a clear verb_noun pattern.

Tool Count2/5

One tool is too few for a database server's apparent scope, as it severely limits functionality (e.g., no schema management, data manipulation beyond queries, or connection handling). This is a significant mismatch for the domain.

Completeness1/5

The tool surface is severely incomplete for a database server. It only supports running queries, lacking essential operations like creating/dropping databases, managing schemas, listing tables, or handling transactions, which will cause frequent agent failures.

Resources

Related MCP Connectors

Related MCP Servers

  • mcp-graphql

    launchthatbrand
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables LLMs to interact with GraphQL APIs by providing schema introspection and query execution capabilities.
    913 npm
    3
    MIT

  • MCP Database Server

    manpreet2000
    A
    license
    D
    quality
    D
    maintenance
    A Model Context Protocol server that enables LLMs to interact with databases (currently MongoDB) through natural language, supporting operations like querying, inserting, deleting documents, and running aggregation pipelines.
    5
    6 npm
    MIT

Appeared in Searches