← Explore all mcp servers

AWS DATA SERVICES / AWS Labs

AWS S3 Tables MCP

Inspect S3 Tables metadata and query Iceberg data, with writes explicitly enabled.

“AWS Labs MCP server for S3-based table storage and Iceberg operations.”

01 / THE REASONING

Why this made the selection.

  • Specialized publisher integration with documented IAM and data access boundaries.
  • Explore namespaces, schema and table metadata before querying selected datasets.
  • The README manages S3 Tables and can query them, but the default mode is read-only and SQL writes are append-only.
  • Table buckets and namespaces are documented as having no delete or update operations.

02 / THE REVIEW RECORD

What we actually inspected.

Source review has boundaries.
A clear record is more useful than a “safe” badge.

Material inspected

  • src/s3-tables-mcp-server/README.md
  • src/s3-tables-mcp-server/pyproject.toml
  • src/s3-tables-mcp-server/awslabs/s3_tables_mcp_server/server.py
  • Root README.md and LICENSE
  • LICENSE

Our findings

  • server.py initializes allow_write=false and wraps mutating operations in a guard; the CLI sets it from --allow-write.
  • Pinned pyproject.toml requires Python >=3.11; the catalogue resolves the conflicting README runtime example in favor of package metadata.
  • The server creates and queries S3 Tables, including CSV ingestion and metadata reads, for an assistant talking to S3-based table storage.
  • It operates in read-only mode unless --allow-write is set. Write tools otherwise return a permission error.
  • Even with writes enabled, SQL updates and deletes are not available, and bucket and namespace operations do not include delete or update.

Not established by this review

  • Server startup, authentication, live tool execution and security isolation were not tested.
  • Published package/container parity with a source revision and hosted implementation internals were not tested.
  • The server was not started and its tools were not called.
  • A pin does not verify transitive dependencies.
  • No tools/list or tool call was made.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

Connect a server deliberately.

Upstream setup instructions ↗

DOCUMENTED COMMAND

uvx awslabs.s3-tables-mcp-server@latest

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

  1. Install uv with Python 3.11 or newer and configure a dedicated profile with access to the selected S3 Tables resources.
  2. Start the documented uvx process without --allow-write and inspect buckets, namespaces and schema first.
  3. For deliberate writes enable the flag separately, grant only the required IAM actions and inspect the destination schema before appending.

Before you start

  • Python 3.11 or newer, uv/uvx and a local stdio MCP client.
  • An AWS account, configured credentials and access to the intended region and service resources.

Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

{
  "mcpServers": {
    "awslabs-s3-tables": {
      "command": "uvx",
      "args": [
        "awslabs.s3-tables-mcp-server@latest"
      ],
      "env": {
        "AWS_PROFILE": "s3-tables-reader",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

04 / FOLLOW THE EVIDENCE

The source trail.

Our notes are separate from the original resource.
Check upstream before adopting a new version.

  1. https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/s3-tables-mcp-server/README.md

    Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports

  2. https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/s3-tables-mcp-server/pyproject.toml

    Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports

  3. https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/s3-tables-mcp-server/awslabs/s3_tables_mcp_server/server.py

    Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports

  4. https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md

    Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports

  5. Applicable licence ↗Checked

    https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE

    Supports: license

Evidence & Ask