MCP Trino Server
Integrates with Trino and Iceberg for advanced data exploration, querying, and table maintenance.
MCP Trino Server
The MCP Trino Server is a Model Context Protocol (MCP) server that provides seamless integration with Trino and Iceberg, enabling advanced data exploration, querying, and table maintenance capabilities through a standard interface.
Use Cases
- Interactive data exploration and analysis in Trino
- Automated Iceberg table maintenance and optimization
- Building AI-powered tools that interact with Trino databases
- Executing and managing SQL queries with proper result formatting
Prerequisites
- A running Trino server (or Docker Compose for local development)
- Python 3.12 or higher
- Docker (optional, for containerized deployment)
Quick Start
1. Clone the Repository
git clone https://github.com/alaturqua/mcp-trino-python.git
cd mcp-trino-python
2. Create Environment File
Create a .env file in the root directory:
TRINO_HOST=localhost
TRINO_PORT=8080
TRINO_USER=trino
TRINO_CATALOG=tpch
TRINO_SCHEMA=tiny
3. Run Trino Locally (Optional)
docker-compose up -d trino
This starts a Trino server on localhost:8080 with sample TPC-H and TPC-DS data.
Installation
Installing via Smithery
To install MCP Trino Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @alaturqua/mcp-trino-python --client claude
Using uv (Recommended)
uv sync
uv run src/server.py
Using pip
pip install -e .
python src/server.py
Transport Modes
The server supports three transport modes:
| Transport | Description | Use Case |
|---|---|---|
stdio | Standard I/O (default) | VS Code, Claude Desktop, local MCP clients |
streamable-http | HTTP with streaming | Remote access, web clients, Docker |
sse | Server-Sent Events | Legacy HTTP transport |
Running with Different Transports
# stdio (default) - for VS Code and Claude Desktop
python src/server.py
# Streamable HTTP - for remote/web access
python src/server.py --transport streamable-http --host 0.0.0.0 --port 8000
# SSE - legacy HTTP transport
python src/server.py --transport sse --host 0.0.0.0 --port 8000
Usage with VS Code
Add to your VS Code settings (Ctrl+Shift+P → Preferences: Open User Settings (JSON)):
{
"mcp": {
"servers": {
"mcp-trino-python": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"--with",
"trino",
"--with",
"loguru",
"mcp",
"run",
"/path/to/mcp-trino-python/src/server.py"
],
"envFile": "/path/to/mcp-trino-python/.env"
}
}
}
}
Or add to .vscode/mcp.json in your workspace (without the mcp wrapper key).
Usage with Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"trino": {
"command": "python",
"args": ["./src/server.py"],
"env": {
"TRINO_HOST": "your-trino-host",
"TRINO_PORT": "8080",
"TRINO_USER": "trino"
}
}
}
}
Docker Usage
Build the Image
docker build -t mcp-trino-python .
Run with stdio (for VS Code)
docker run -i --rm \
-e TRINO_HOST=host.docker.internal \
-e TRINO_PORT=8080 \
-e TRINO_USER=trino \
mcp-trino-python
Run with Streamable HTTP
docker run -p 8000:8000 \
-e TRINO_HOST=host.docker.internal \
-e TRINO_PORT=8080 \
mcp-trino-python \
--transport streamable-http --host 0.0.0.0 --port 8000
Docker Compose
# Start Trino + MCP server with Streamable HTTP
docker-compose up -d
# Start with SSE transport
docker-compose --profile sse up -d
# Run stdio for testing
docker-compose --profile stdio run --rm mcp-trino-stdio
VS Code with Docker
{
"mcp": {
"servers": {
"mcp-trino-python": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--network",
"mcp-trino-python_trino-network",
"-e",
"TRINO_HOST=trino",
"-e",
"TRINO_PORT=8080",
"-e",
"TRINO_USER=trino",
"mcp-trino-python"
]
}
}
}
}
Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
| TRINO_HOST | Trino server hostname | localhost |
| TRINO_PORT | Trino server port | 8080 |
| TRINO_USER | Trino username | trino |
| TRINO_CATALOG | Default catalog | None |
| TRINO_SCHEMA | Default schema | None |
| TRINO_HTTP_SCHEME | HTTP scheme (http/https) | http |
| TRINO_PASSWORD | Trino password | None |
Tools
Query and Exploration Tools
-
show_catalogs
- List all available catalogs
- No parameters required
-
show_schemas
- List all schemas in a catalog
- Parameters:
catalog: Catalog name (string, required)
-
show_tables
- List all tables in a schema
- Parameters:
catalog: Catalog name (string, required)schema: Schema name (string, required)
-
describe_table
- Show detailed table structure and column information
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
execute_query
- Execute a SQL query and return formatted results
- Parameters:
query: SQL query to execute (string, required)
-
show_catalog_tree
- Show a hierarchical tree view of catalogs, schemas, and tables
- Returns a formatted tree structure with visual indicators
- No parameters required
-
show_create_table
- Show the CREATE TABLE statement for a table
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
show_create_view
- Show the CREATE VIEW statement for a view
- Parameters:
view: View name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
show_stats
- Show statistics for a table
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
Iceberg Table Maintenance
-
optimize
- Optimize an Iceberg table by compacting small files
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
optimize_manifests
- Optimize manifest files for an Iceberg table
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
expire_snapshots
- Remove old snapshots from an Iceberg table
- Parameters:
table: Table name (string, required)retention_threshold: Age threshold (e.g., "7d") (string, optional)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
Iceberg Metadata Inspection
-
show_table_properties
- Show Iceberg table properties
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
show_table_history
- Show Iceberg table history/changelog
- Contains snapshot timing, lineage, and ancestry information
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
show_metadata_log_entries
- Show Iceberg table metadata log entries
- Contains metadata file locations and sequence information
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
show_snapshots
- Show Iceberg table snapshots
- Contains snapshot details including operations and manifest files
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
show_manifests
- Show Iceberg table manifests for current or all snapshots
- Contains manifest file details and data file statistics
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)all_snapshots: Include all snapshots (boolean, optional)
-
show_partitions
- Show Iceberg table partitions
- Contains partition statistics and file counts
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
show_files
- Show Iceberg table data files in current snapshot
- Contains detailed file metadata and column statistics
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
-
show_entries
- Show Iceberg table manifest entries for current or all snapshots
- Contains entry status and detailed file metrics
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)all_snapshots: Include all snapshots (boolean, optional)
-
show_refs
- Show Iceberg table references (branches and tags)
- Contains reference configuration and snapshot mapping
- Parameters:
table: Table name (string, required)catalog: Catalog name (string, optional)schema: Schema name (string, optional)
Query History
- show_query_history
- Get the history of executed queries
- Parameters:
limit: Maximum number of queries to return (number, optional)
License
This project is licensed under the Apache 2.0 License. Please refer to the LICENSE file for the full terms.
เซิร์ฟเวอร์ที่เกี่ยวข้อง
Unofficial ChEMBL MCP Server
Access the ChEMBL chemical database for drug discovery, chemical informatics, and bioactivity research using specialized tools via its REST API.
Quanti: connectors MCP
Unify your marketing team around one AI-powered source of truth. Quanti connects your marketing data to your warehouse. Execute SQL queries on BigQuery, explore table schemas, discover pre-built use cases, and analyze performance across Google Analytics, Google Ads, Meta Ads, TikTok, affiliate networks and more. all through natural conversation
Knowledge Graph Memory Server
A knowledge graph server that provides persistent, multi-context memory for AI models.
aml
AML Watcher MCP Server gives AI agents direct, real-time access to AML Watcher's proprietary sanctions, watchlist, and PEP databases. Connect your agentic workflows to 215+ sanctions regimes, 2.6M+ PEP profiles, and coverage across 235+ countries, no complex integrations required.
JDBC Explorer
A server that enables LLMs to connect and interact with databases via JDBC, built using the Spring AI MCP framework.
OData MCP Bridge (Go)
A Go bridge providing universal access to OData v2 services through MCP tools, with support for multiple authentication methods.
KuzuMem-MCP
A distributed memory bank MCP tool that stores memories in a KùzuDB graph database, with repository and branch filtering capabilities.
Memory Cache Server
An MCP server that reduces token consumption by efficiently caching data between language model interactions.
Couchbase
Interact with Couchbase databases using natural language. Perform CRUD operations, query buckets, and execute N1QL queries.
Epicor Kinetic MCP Server by CData
A read-only MCP server by CData that enables LLMs to query live data from Epicor Kinetic.
