Practical overview
When it fits
Use it when you have AWS Lambda functions and want to make them callable by an MCP-compatible LLM client, including workflows where a Lambda function accesses resources using its own AWS role.
Who it is for
- Developers who want an MCP-compatible LLM client to invoke existing AWS Lambda functions.
- Teams that want Lambda functions to mediate model access to AWS services, private networks or external services.
- Builders exploring function-backed LLM tools with the repository’s sample Lambda functions.
Documented uses
- Expose matching Lambda functions as individual named tools or through generic listing and invocation tools.
- Let an LLM client pass parameters to a selected Lambda function.
- Use Lambda functions to perform lookups, calculations or data processing that the model can request.
Requirements & limits
The repository is public and identifies the project as MIT-licensed. Its documented setup requires Python 3.12 or later, an AWS account with configured credentials, Lambda functions and an MCP-compatible client.
- The server is a bridge between an LLM client and AWS Lambda; it does not replace the client, model or functions.
- Pre-discovery mode registers each function as an individual tool at startup; generic mode uses list_lambda_functions and invoke_lambda_function.
- The default filter exposes functions whose names start with mcp2lambda-.
- The client invokes Lambda, while the functions can use their own roles to reach AWS services; the accessible operations depend on those functions and permissions.
- Function descriptions should explain purpose and parameters so the model can choose and invoke tools.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Connect Claude Desktop to a local MCP2Lambda server
Configure Claude Desktop to start MCP2Lambda locally and access the Lambda tools available to the server.
Before you start
- Python 3.12 or higher
- AWS account with configured credentials
- AWS Lambda functions
- Claude Desktop or another MCP-compatible client
Steps
Clone the MCP2Lambda repository and configure AWS credentials, for example with the AWS CLI.
Add an mcp2lambda server entry to the Claude Desktop configuration using the documented uv command, the repository directory path and run main.py.
Start the MCP server locally with uv run main.py from the repository directory.
Expected outcome
Claude Desktop is configured to launch the local MCP server, which can expose available Lambda functions as tools.
Guide limitations
- The documented Claude Desktop configuration requires the full local repository path.
- By default, only functions whose names start with mcp2lambda- are available; the server also describes prefix or allowed-name selection.
- The Lambda function descriptions should specify their purpose and parameters to help the model use them.
Deploy the repository’s sample Lambda functions
Build and deploy the included sample functions with AWS SAM for use with MCP2Lambda.
Before you start
- AWS account with configured credentials
- AWS SAM CLI
- The MCP2Lambda repository
Steps
Change to the sample_functions directory.
Run sam build.
Run sam deploy.
Expected outcome
The sample functions are deployed with the mcp2lambda- prefix used by the server’s default function-name filter.
Guide limitations
- The sample functions have basic permissions and can only write to CloudWatch logs.
- The customer lookup samples use hard-coded demonstration responses.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 17 October 2026
- Original website title
- danilop/MCP2Lambda · Official homepage title · retained in its source language