ModelsAtlas
Explore
Atlas / MCP servers / alaturqua / Trino

TrinoSAFE

mcp/alaturqua/trino-3
MCP server by alaturqua · Audited 2026-10-09
⚑ Report / re-scanSource ↗

MCP Server for Trino developed via MCP Python SDK

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
5 4r · 1w · 0d
Transport
sse · stdio · streamable-http
License
Apache-2.0
Stars
25
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://mseep.ai/app/alaturqua-mcp-trino-python)

[](https://smithery.ai/server/@alaturqua/mcp-trino-python) [](https://www.python.org/downloads/) [](https://code.visualstudio.com/) [](https://github.com/alaturqua/mcp-trino-python/pkgs/container/mcp-trino-python) [](https://opensource.org/licenses/Apache-2.0)

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

  1. A running Trino server (or Docker Compose for local development)
  2. Python 3.12 or higher
  3. 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)

Read from source at commit 609f8f41b02cOBSERVED · 2026-10-09
02
Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude-code
claude mcp add mcp-trino-python --env TRINO_PASSWORD=${TRINO_PASSWORD} -- uvx mcp-trino-python
claude-desktop
{
  "mcpServers": {
    "mcp-trino-python": {
      "command": "uvx",
      "args": [
        "mcp-trino-python"
      ],
      "env": {
        "TRINO_PASSWORD": "${TRINO_PASSWORD}"
      }
    }
  }
}
03
Exposed tools (5)
4 read · 1 write · 0 destructive.
ToolRiskDescription
execute_querywriteExecute a SQL query and return formatted results.
show_catalog_treereadGet a hierarchical tree view showing the full structure of catalogs, schemas, and tables.
show_catalogsreadList all available catalogs.
show_query_historyreadGet the history of executed queries.
show_schemasreadList all schemas in a catalog.
04
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED
What the source does
Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found
Findings (1)
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements.txt
loguru, mcp, python-dotenv, trino
Why it matters. 4 requirement(s) not pinned with ==
Fix. pin exact versions
Gates applied: no_behavioural_pass.
Audited 2026-10-09 · audit v0.4.1 · source sha 609f8f41b02cfull audit observations/trust-audit/mcp-server/alaturqua__trino-3.json · Report an issue / request a re-scan
05
Audit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
DateSourceVerdictGradeScoreChange
2026-10-09609f8f41b02cSAFEB89first audit
06
Questions
What is the Trino MCP server?
MCP Server for Trino developed via MCP Python SDK
What tools does Trino expose?
5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Trino safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Trino need?
It reads TRINO_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Trino run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mcp-trino-python.
How current is this page?
The grade is for one exact copy of the source (609f8f41b02c), read on 2026-10-09. The repository is watched and re-audited when it changes.
Advertisement