ModelsAtlas
Explore
Atlas / MCP servers / isaacwasserman / Snowflake

SnowflakeSAFE

mcp/isaacwasserman/snowflake-1
MCP server by isaacwasserman · Audited 2026-10-06
⚑ Report / re-scanSource ↗
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
8 4r · 3w · 1d
Transport
stdio
License
GPL-3.0
Stars
184
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/isaacwasserman-mcp-snowflake-server)

Overview

A Model Context Protocol (MCP) server implementation that provides database interaction with Snowflake. This server enables running SQL queries via tools and exposes data insights and schema context as resources.

Components

Resources

  • `memo://insights`

A continuously updated memo aggregating discovered data insights. Updated automatically when new insights are appended via the append_insight tool.

  • `context://table/{table_name}`

(If prefetch enabled) Per-table schema summaries, including columns and comments, exposed as individual resources.

Tools

The server exposes the following tools:

Query Tools

  • `read_query`

Execute SELECT queries to read data from the database. Input:

  • query (string): The SELECT SQL query to execute

Returns: Query results as array of objects

  • `write_query` (enabled only with --allow-write)

Execute INSERT, UPDATE, or DELETE queries. Input:

  • query (string): The SQL modification query

Returns: Number of affected rows or confirmation

  • `create_table` (enabled only with --allow-write)

Create new tables in the database. Input:

  • query (string): CREATE TABLE SQL statement

Returns: Confirmation of table creation

Schema Tools

  • `list_databases`

List all databases in the Snowflake instance. Returns: Array of database names

  • `list_schemas`

List all schemas within a specific database. Input:

  • database (string): Name of the database

Returns: Array of schema names

  • `list_tables`

List all tables within a specific database and schema. Input:

  • database (string): Name of the database
  • schema (string): Nam
Read from source at commit 02c57c9752feOBSERVED · 2026-10-06
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_snowflake_server --env SNOWFLAKE_PRIVATE_KEY_PATH=${SNOWFLAKE_PRIVATE_KEY_PATH} -- uvx mcp_snowflake_server
claude-desktop
{
  "mcpServers": {
    "mcp_snowflake_server": {
      "command": "uvx",
      "args": [
        "mcp_snowflake_server"
      ],
      "env": {
        "SNOWFLAKE_PRIVATE_KEY_PATH": "${SNOWFLAKE_PRIVATE_KEY_PATH}"
      }
    }
  }
}
03

Exposed tools (8)

4 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
append_insightwriteAdd a data insight to the memo
create_tablewriteCreate a new table in the Snowflake database
describe_tablereadGet the schema information for a specific table
list_databasesreadList all available databases in Snowflake
list_schemasreadList all schemas in a database
list_tablesreadList all tables in a specific database and schema
read_querywriteExecute a SELECT query.
write_querydestructiveExecute an INSERT, UPDATE, or DELETE query on the Snowflake database
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 surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (2 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (2)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
write_query
Why it matters. 1 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:167
curl -LsSf https://astral.sh/uv/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-06 · audit v0.4.1 · source sha 02c57c9752fefull audit observations/trust-audit/mcp-server/isaacwasserman__snowflake-1.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
2026-10-0602c57c9752feSAFEB89first audit
06

Questions

What tools does Snowflake expose?

8 in total: 4 read-only, 3 that write, and 1 that can delete or overwrite (write_query). Every one is listed on this page with its risk.

Is Snowflake 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. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Snowflake need?

It reads SNOWFLAKE_PRIVATE_KEY_PATH 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 Snowflake run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp_snowflake_server.

How current is this page?

The grade is for one exact copy of the source (02c57c9752fe), read on 2026-10-06. The repository is watched and re-audited when it changes.

Advertisement