- Home
- MCP servers
- Datomic
Datomic
- other
9
GitHub Stars
other
Language
6 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": {
"xlisp-datomic-mcp-server": {
"command": "clojure",
"args": [
"-X:mcp"
]
}
}
}You can run a dedicated MCP server that queries Datomic databases and integrates AI-powered workflows. It supports connecting to Datomic SQL, Dev-local, and Cloud setups, and provides practical ways to query entities, relationships, histories, and computed aggregations from your AI-enabled pipelines.
How to use
Start the MCP server from your development environment to enable AI-powered querying of your Datomic data. You can then connect your MCP client to the server using the local stdio interface or, if available, a remote HTTP endpoint. Use the server to explore entity attributes, query relationships between entities, perform aggregate computations, and navigate historical views of entities and transactions.
How to install
Prerequisites you need before running the server:
- Java 17 (JDK) or compatible runtime
- Clojure CLI installed on the system
Step-by-step commands you will run to start the MCP server locally:
# Start the MCP server using the Clojure CLI
clojure -X:mcp
Additional sections
Configuration and usage notes help you tailor the server to your environment.
Connection options include a local stdio setup for quick development or a potential HTTP endpoint for remote access. In the recommended local setup, you run the server as a Clojure process and connect your MCP client to the standard input/output transport.
Server startup and connection details
To start the server from your development environment, run the following command in your shell:
clojure -X:mcp
Connecting with an MCP client
After the server starts, configure your MCP client to connect via the stdio transport for local development. If your workflow uses a GUI or CI system, you may use an HTTP endpoint if it becomes available in your setup.
Available tools
query_relationships
Query entity relationships within the connected Datomic data to reveal how entities are interlinked.
aggregate_queries
Execute aggregate computations across result sets to derive summaries and analytics.
history_navigation
Navigate temporal history and transaction-time to inspect as-of, since, and historical states of entities.