IcebergSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
AI-native Lakehouse Integration
[](https://pypi.org/project/iceberg-mcp) [](https://github.com/ryft-io/iceberg-mcp/blob/main/LICENSE)
IcebergMCP is a Model Context Protocol (MCP) server that lets you interact with your Apache IcebergTM Lakehouse using natural language in Claude, Cursor, or any other MCP client.
Table of Contents
- Installation
- Prerequisites
- Claude
- Cursor
- Configuration
- Available Tools
- Examples
- Limitations & Security Considerations
- Contributing
Installation
Prerequisites
- Apache IcebergTM catalog managed in AWS Glue
- AWS profile configured on the machine, with access to the catalog
uvpackage manager - install viabrew install uvor see official installation guide
Claude
- Inside Claude, go to Settings > Developer > Edit Config > claudedesktopconfig.json
- Add the following:
{
"mcpServers": {
"iceberg-mcp": {
"command": "uv", // If uv can't be found, replace with full absolute path to uv
"args": [
"run",
"--with",
"iceberg-mcp",
"iceberg-mcp"
],
"env": {
"ICEBERG_MCP_PROFILE": ""
}
}
}
}Cursor
- Inside Cursor, go to Settings -> Cursor Settings -> MCP -> Add new global MCP server
- Add the follo
8addc360c75fOBSERVED · 2026-10-08Connect
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.
claude mcp add iceberg-mcp -- uvx iceberg-mcp
{
"mcpServers": {
"iceberg-mcp": {
"command": "uvx",
"args": [
"iceberg-mcp"
]
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_iceberg_tables | read | Provides a list of iceberg tables from the Iceberg catalog for a given namespace |
get_namespaces | read | Provides a list of namespaces from the Iceberg catalog. |
get_table_partitions | read | Provides the partitions for a given Iceberg table |
get_table_properties | read | catalog: Catalog = get_catalog() |
get_table_schema | read | Provides the schema for a given Iceberg table |
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.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
8addc360c75ffull audit observations/trust-audit/mcp-server/ryft-io__iceberg.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 8addc360c75f | SAFE | B | 89 | first audit |
Questions
What tools does Iceberg expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Iceberg 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 Iceberg need?
No credential environment variables were found in its source, so it appears to need none.
How does Iceberg run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as iceberg-mcp.
How current is this page?
The grade is for one exact copy of the source (8addc360c75f), read on 2026-10-08. The repository is watched and re-audited when it changes.