listGraphs
List all graphs in the repository
LABSCO SUMMARY
Query access to a knowledge graph without an update path
sparqlQuery is declared read-only, so a model exploring an unfamiliar graph cannot rewrite it with a mis-generated statement — the risk of handing a triple store to an assistant drops to wasted tokens. listGraphs supplies the graph names the query tool expects, which makes it the usual first call. Neither tool takes a connection parameter, so which repository you reach is settled by the server's configuration rather than per call.
What it is
A GraphDB client with two tools: a read-only SPARQL query scoped to a graph, and a listing of the repository's graphs.
What you get
- SPARQL execution against the repository, declared read-only, with a target graph and an output format you specify
- The names of every graph the repository holds, which is what the query tool's graph parameter expects
Requirements
A GraphDB repository the server can reach, and GPL-3.0 terms if you redistribute it.
Setup effort
One command plus credentials — npx -y mcp-server-graphdb, then supply credentials
USE CASES
01
Getting your bearings in a triple store someone else loaded
The graph names come first, because a SPARQL query aimed at the wrong graph returns nothing and looks like an empty repository.
02
Pulling a result set out in the shape the next step expects
The query tool takes the response format as an argument, so results arrive ready for whatever consumes them instead of needing a conversion pass.
2 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
sparqlQuery
Execute a read-only SPARQL query against the GraphDB repository
BEFORE YOU INSTALL
What to know first
Tools you get
2 tools when we connected. Both tools are read-only, so a SPARQL UPDATE will not write to your store. Class List, Predicates, Statistics, Sample Data and Graph Content are resources, not tools.
Requires
- npx on PATH
- yarn
- GRAPHDB_PASSWORD in your environment
- GRAPHDB_USERNAME in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 2 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y mcp-server-graphdbMCP Clients
Claude Desktop
Clone and build the server
CLAUDE DESKTOP · TERMINAL
git clone https://github.com/keonchennl/mcp-server-graphdb.git
cd mcp-server-graphdb
yarn install
yarn buildAdd this to the mcpServers section of claude_desktop_config.json
<YOUR_PATH_TO_MCP_SERVER_GRAPHDB> is the full path of the mcp-server-graphdb folder you cloned; the GRAPHDB_* values are your GraphDB endpoint, repository and login.
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"graphdb": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MCP_SERVER_GRAPHDB>/dist/index.js"
],
"env": {
"GRAPHDB_ENDPOINT": "http://localhost:7200",
"GRAPHDB_REPOSITORY": "<YOUR_GRAPHDB_REPOSITORY>",
"GRAPHDB_USERNAME": "<YOUR_GRAPHDB_USERNAME>",
"GRAPHDB_PASSWORD": "<YOUR_GRAPHDB_PASSWORD>"
}
}
}
}
