---
title: "AWS Labs Lambda Tools: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/awslabs-lambda-tool/
description: "Turns selected existing Lambda functions into MCP tools, allowing controlled access to application operations and private networks."
---

# AWS Labs Lambda Tools: review, setup & limitations · Undominated.ai

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

[← Explore all mcp servers](/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.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/awslabs/mcp)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 5 linked sources
 Publisher AWS Labs
 Licence [Apache-2.0 ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE)
 Revision 8840003820a7
 [Read what was—and wasn’t—checked ↓](#review)

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

 [AWS Labs · upstream description ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/lambda-tool-mcp-server/README.md) Our analysis follows below.

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.

### A good fit for

 - Expose one reviewed internal application function without making its private network publicly reachable.
- Reuse Lambda function descriptions and optional EventBridge schemas to document tool inputs.
- Calling an internal Lambda without opening that network to the model
- Limiting the tool list with FUNCTION_PREFIX, FUNCTION_LIST, or both halves of a tag

### Weigh up before choosing

 - Empty FUNCTION_LIST and FUNCTION_PREFIX select all discovered functions. Explicit list and prefix are alternatives, then paired tag filters narrow selection.
- Invocation is RequestResponse, not a dry run. Function execution roles, network access and application logic determine the downstream read/write effects.
- EventBridge schema text is added to tool documentation; that is not evidence of end-to-end input or business-rule validation.
- The monorepo now recommends Agent Toolkit for AWS for production. This specialized local server remains documented; its leaf and root documentation were checked for deprecation.
- Empty prefix and list means every function passes the name check.
- A half-set tag filter selects no functions.
- The README does not have the server call downstream AWS services itself. That access sits in the Lambda role.
- A pin does not verify transitive dependencies. Documented uvx examples use a floating package tag, not the reviewed commit.
- This review did not execute the resource.
- The server was not started and its tools were not called.

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 ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/lambda-tool-mcp-server/README.md)

DOCUMENTED COMMAND

 uvx awslabs.lambda-tool-mcp-server@latest Copy command ↗

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

 - Review the existing function code and execution role before exposing it as a tool.
- Configure an explicit FUNCTION_LIST and IAM permissions limited to necessary discovery/invocation.
- 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"
 }
 }
 }
} Copy configuration ↗

### Compatibility

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.

### Implementation

Python

### Transports

stdio

### AWS data services

 - Discovers and invokes Lambda functions using caller credentials; each function can access resources available to its own execution role.

### Cost model

AWS service, model, query and storage charges apply; running the MCP process does not include those services.

04 / FOLLOW THE EVIDENCE

## The source trail.

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

 - [Publisher setup, capabilities and operating boundaries ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/lambda-tool-mcp-server/README.md) Checked 2026-10-14 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
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/lambda-tool-mcp-server/pyproject.toml) Checked 2026-10-14 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
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/lambda-tool-mcp-server/awslabs/lambda_tool_mcp_server/server.py) Checked 2026-10-14 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
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports, license
- [Applicable licence ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE Supports: license

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### AWS Keyspaces MCP ↗ Inspect Cassandra-compatible schemas and run SELECT queries with dedicated database credentials.](/mcp-servers/awslabs-keyspaces/)[### AWS Labs Amazon Kendra Index ↗ Queries an existing Kendra index and returns document excerpts, source URIs and confidence labels for retrieval workflows.](/mcp-servers/awslabs-kendra-index/)[### AWS Labs Amazon MQ ↗ Inspects and manages Amazon MQ brokers, with additional RabbitMQ management operations.](/mcp-servers/awslabs-amazon-mq/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
