Database interaction and business intelligence capabilities
A Model Context Protocol (MCP) server implementation that provides database interaction and business intelligence capabilities through SQLite. This server enables running SQL queries, analyzing business data, and automatically generating business insight memos.
The server exposes a single dynamic resource:
memo://insights
: A continuously updated business insights memo that aggregates discovered insights during analysis
The server provides a demonstration prompt:
mcp-demo
: Interactive prompt that guides users through database operations
topic
- The business domain to analyzeThe server offers six core tools:
read_query
query
(string): The SELECT SQL query to executewrite_query
query
(string): The SQL modification query{ affected_rows: number }
create_table
query
(string): CREATE TABLE SQL statementlist_tables
describe-table
table_name
(string): Name of table to describeappend_insight
insight
(string): Business insight discovered from data analysis"mcpServers": { "sqlite": { "command": "uv", "args": [ "--directory", "parent_of_servers_repo/servers/src/sqlite", "run", "mcp-server-sqlite", "--db-path", "~/test.db" ] } }
"mcpServers": { "sqlite": { "command": "docker", "args": [ "run", "--rm", "-i", "-v", "mcp-test:/mcp", "mcp/sqlite", "--db-path", "/mcp/test.db" ] } }
Docker:
docker build -t mcp/sqlite .
uv add "mcp[cli]" mcp dev src/mcp_server_sqlite/server.py:wrapper
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Knowledge graph-based persistent memory system
Read-only database access with schema inspection
Embeddings, vector search, document storage, and full-text search with the open-source AI application database
Query your ClickHouse database server.
Immutable ledger database with live synchronization
Provides AI assistants with a secure and structured way to explore and analyze data in GreptimeDB.
Connect to a Hologres instance, get table metadata, query and analyze data.
Open source MCP server specializing in easy, fast, and secure tools for Databases.
Search, Query and interact with data in your Milvus Vector Database.
Query and analyze data with MotherDuck and local DuckDB