Gremlin

Enables AI agents to interact with Gremlin-compatible graph databases via natural language, performing schema discovery, queries, and data import/export.

typescript

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "kpritam-gremlin-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@kpritam/gremlin-mcp"
      ],
      "env": {
        "LOG_LEVEL": "info",
        "GREMLIN_USE_SSL": "true",
        "GREMLIN_ENDPOINT": "localhost:8182",
        "GREMLIN_PASSWORD": "s3cr3t",
        "GREMLIN_USERNAME": "admin"
      }
    }
  }
}

You can connect your AI assistants to a Gremlin-compatible graph database and interact with it through natural language. This MCP server translates conversational requests into graph queries, schema discovery, data loading, and exports, letting you explore, analyze, and manage your graph without writing Gremlin by hand.

How to use

You integrate an MCP client with the server using the published package or a local build, then point your client at your Gremlin endpoint. Your AI assistant can perform schema discovery, run Gremlin traversals, monitor health, and import or export data. Start by ensuring your Gremlin database is accessible and then configure the MCP client to connect to it.

How to install

Prerequisites: you need Node.js installed to build and run the MCP server locally. Have npm available to install dependencies and run scripts.

# The npx command will automatically install the package if needed
# No separate installation step required

Configuration and usage patterns

You can run the MCP server in stdio mode (local runtime) using either the published package or a local build. Choose the approach you prefer and configure the environment to point to your Gremlin endpoint.

{
  "mcpServers": {
    "gremlin": {
      "command": "npx",
      "args": ["-y", "@kpritam/gremlin-mcp"],
      "env": {
        "GREMLIN_ENDPOINT": "localhost:8182",
        "LOG_LEVEL": "info"
      }
    }
  }
}

What you can do with tools

After connecting, you can verify health, discover the graph schema, run queries, refresh the schema cache, import data, and export subgraphs. These actions map to concrete tasks like checking connectivity, inspecting node/edge structures, executing traversals, and moving data in or out of your graph.

Examples of practical workflows

Check connectivity and schema, then query: ask your AI assistant to confirm the connection, show the graph structure, and then retrieve a subset of data or compute statistics.

Data import and export

Import data from GraphSON, CSV, or JSON in batches, and export subgraphs to JSON, GraphSON, or CSV formats. Your assistant can drive data loading and data extraction as part of routine data management.

Available tools

get_graph_status

Health Check: verify database connectivity and server health.

get_graph_schema

Schema Discovery: obtain complete graph structure including nodes, edges, and relationships.

run_gremlin_query

Query Execution: run any Gremlin traversal with full syntax support.

refresh_schema_cache

Cache Management: force immediate refresh of cached schema information.

import_graph_data

Data Import: load data from GraphSON, CSV, or JSON with batch processing.

export_subgraph

Data Export: extract subgraphs in JSON, GraphSON, or CSV formats.

Built by

VeilStrat

AI signals for GTM teams