← Explore all mcp servers

AWS DATA SERVICES / AWS Labs

AWS Labs Lambda Tools

Turns selected existing Lambda functions into MCP tools, allowing controlled access to application operations and private networks.

“A Model Context Protocol (MCP) server for AWS Lambda to select and run Lambda function as MCP tools without code changes.”

01 / THE REASONING

Why this made the selection.

  • Specialized publisher integration with documented IAM and data access boundaries.
  • Expose one reviewed internal application function without making its private network publicly reachable.
  • The README publishes selected Lambda functions as MCP tools without changing their code.
  • The client credentials only need to invoke those functions. The function role, not the model, reaches other AWS services and private networks.

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/lambda-tool-mcp-server/README.md
  • src/lambda-tool-mcp-server/pyproject.toml
  • src/lambda-tool-mcp-server/awslabs/lambda_tool_mcp_server/server.py
  • Root README.md and LICENSE
  • LICENSE

Our findings

  • validate_function_name explicitly returns true when both selectors are empty. The invocation handler calls RequestResponse and returns the payload; remote function semantics remain outside this source review.
  • The server selects Lambda functions and runs them as MCP tools without code changes, including functions that reach private resources.
  • The model may invoke Lambda and may not access other AWS services directly. The default profile and region are default and us-east-1.
  • No prefix and no list lets every function through the name check. Setting only FUNCTION_TAG_KEY or only FUNCTION_TAG_VALUE selects no function. Tool text is taken from the Lambda description, which the README says must explain when and how to call it.

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.lambda-tool-mcp-server@latest

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

  1. Review the existing function code and execution role before exposing it as a tool.
  2. Configure an explicit FUNCTION_LIST and IAM permissions limited to necessary discovery/invocation.
  3. Inspect input/output contracts and use application-level idempotency for operations that may be retried.

Before you start

  • Python 3.10 or newer, uv/uvx and an MCP client that can launch a local stdio process.
  • 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-lambda-tool": {
      "command": "uvx",
      "args": [
        "awslabs.lambda-tool-mcp-server@latest"
      ],
      "env": {
        "AWS_PROFILE": "YOUR_RESTRICTED_PROFILE",
        "AWS_REGION": "us-east-1",
        "FUNCTION_LIST": "YOUR_REVIEWED_FUNCTION"
      }
    }
  }
}

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/lambda-tool-mcp-server/README.md

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

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

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

  3. https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/lambda-tool-mcp-server/awslabs/lambda_tool_mcp_server/server.py

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

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

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

  5. Applicable licence ↗Checked

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

    Supports: license

Evidence & Ask