Click on "Install 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., "@mcp-server-ladybug find all Person nodes in the graph"
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.
An MCP server implementation that interacts with LadybugDB graph databases, providing Cypher query capabilities to AI Assistants and IDEs.
LadybugDB is an embedded graph database built for query speed and scalability. It is optimized for handling complex join-heavy analytical workloads on very large graphs.
Key features:
Property Graph data model with Cypher query language
Embedded database - runs in-process with your application
Columnar disk-based storage for analytical performance
Strongly typed schema with explicit data types
JSON support through the json extension
Interoperability with Parquet, Arrow, DuckDB, and more
Related MCP server: Gremlin MCP Server
The server provides one prompt:
ladybugdb-initial-prompt: A prompt to initialize a connection to LadybugDB and start working with it
The server offers one tool:
query: Execute a Cypher query on the LadybugDB database
Inputs:
query (string, required): The Cypher query to execute
All interactions with LadybugDB are done through writing Cypher queries.
Result Limiting: Query results are automatically limited to prevent using up too much context:
Maximum 1024 rows by default (configurable with --max-rows)
Maximum 50,000 characters by default (configurable with --max-chars)
Truncated responses include a note about truncation
pip install mcp-server-ladybug
mcp-server-ladybug --db-path :memory:Note: Replace
:memory:with a path like/path/to/local.lbdbto persist data to disk.
docker run -it --rm ghcr.io/ladybugdb/mcp-server-ladybug:latest --db-path :memory:Note: Replace
:memory:with a path like/path/to/local.lbdbto persist data to disk.
uvx mcp-server-ladybug --db-path :memory:Note: Replace
:memory:with a path like/path/to/local.lbdbto persist data to disk.
git clone https://github.com/LadybugDB/mcp-server-ladybug.git
cd mcp-server-ladybug
uv pip install -e .
mcp-server-ladybug --db-path :memory:Note: Replace
:memory:with a path like/path/to/local.lbdbto persist data to disk.
Parameter | Type | Default | Description |
| Choice |
| Transport type. Options: |
| Integer |
| Port to listen on for sse and stream transport mode |
| String |
| Host to bind the MCP server for sse and stream transport mode |
| String |
| Path to LadybugDB database file |
| Integer |
| Maximum number of rows to return from queries |
| Integer |
| Maximum number of characters in query results |
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"mcp-server-ladybug": {
"command": "uvx",
"args": [
"mcp-server-ladybug",
"--db-path",
":memory:"
]
}
}
}Note: Replace
:memory:with a path like/path/to/local.lbdbto persist data to disk.
CREATE NODE TABLE Person (id INT64 PRIMARY KEY, name STRING, age INT64);
CREATE NODE TABLE City (name STRING PRIMARY KEY, population INT64);
CREATE REL TABLE Follows (FROM Person TO Person, since INT64);
CREATE REL TABLE LivesIn (FROM Person TO City);COPY Person FROM 'persons.csv';
COPY City FROM 'cities.csv';
COPY Follows FROM 'follows.csv';MATCH (a:Person)-[:Follows]->(b:Person)
WHERE a.age > 25
RETURN a.name, b.name, a.age;INSTALL json;
LOAD json;
CREATE NODE TABLE Product (id INT64 PRIMARY KEY, details JSON);
COPY Product FROM 'products.json';
MATCH (p:Product)
WHERE json_extract(p.details, '$.category') = 'electronics'
RETURN p.id, json_extract(p.details, '$.name') AS product_name;uv pip install -e .
python -m mcp_server_ladybug --db-path :memory:Note: Replace
:memory:with a path like/path/to/local.lbdbto persist data to disk.
MIT License
Use this to execute a Cypher query on the LadybugDB database
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Cypher query to execute on the LadybugDB graph database |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description fails to disclose behavioral traits such as whether queries are read-only, modification capabilities, rate limits, or authentication needs. The description only states the basic action.
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, concise sentence that directly conveys the tool's purpose. No extraneous information is present.
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?
Given the simplicity of the tool (one parameter, no output schema, no annotations), the description is adequately complete in stating the primary function. However, it lacks behavioral context such as mutation restrictions or error behavior, which might be needed for safe usage.
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 coverage is 100% with the parameter already having a description. The tool description adds no additional meaning beyond what the schema provides, resulting in redundancy without added value.
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 verb 'execute' and the resource 'Cypher query on the LadybugDB database'. It is specific and unambiguous, with no sibling tools requiring differentiation.
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 phrase 'Use this to' explicitly indicates when to use the tool. No exclusions or alternatives are needed as there are no sibling tools, but prerequisites or restrictions are not mentioned.
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. Dates show when Glama detected each change.
v0.1.2queryWith only a single tool, there is no possibility of confusion between tools. The tool's purpose is clearly defined as executing Cypher queries on the LadybugDB database.
With only one tool named 'query', there is no pattern to assess consistency. However, the name is simple and descriptive, matching common conventions for a single-operation server.
A single tool is minimal for a database server. While a query tool is essential, the server likely needs additional tools for schema exploration, data manipulation, or other database operations to be functional.
The tool set is severely incomplete for typical database interactions. It only provides query execution, lacking tools for schema inspection, data definition, or other common operations, which will likely cause agent failures.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
A collaborative substrate over your data: vector, knowledge graph, SQL, geospatial, streaming.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/LadybugDB/mcp-server-ladybug'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
