mcpField
S
serverlessrun

serverlessrun

Local
github.com/CloudCorpRecordsCloud & Infra0Updated 2w ago
Repository

About serverlessrun

serverlessrun exposes a core subset of AWS Lambda operations to developers through tools shaped for the documented Lambda REST API. It covers function inspection and invocation, versions, aliases, layers, event source mappings, and account settings; signing and execution can be supplied by the caller.

Key features

  1. 01List, inspect, and invoke functions
  2. 02List function versions and aliases
  3. 03Inspect layers and layer versions
  4. 04List event source mappings
  5. 05Retrieve account settings
  6. 06Injectable request executor or signer

Use cases

  1. 01Inspect Lambda functions and invoke them
  2. 02Review versions, aliases, and layers
  3. 03Check event source mappings and account settings

MCP support

The MCP server exposes 10 tools for selected AWS Lambda REST API operations. It does not include its own SigV4 signer; callers must inject a signer or executor to make signed AWS requests.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "cloudcorprecords-serverlessrun": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/serverlessrun"
      ]
    }
  }
}
Run commandnpx -y @reneturcios/serverlessrun

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@reneturcios/serverlessrun0.1.0
ocighcr.io/cloudcorprecords/serverlessrun:0.1.0

Tools

10

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
markerstringNoOptional pagination marker from a previous response, sent as the Marker query parameter to fetch the next page.
max_itemsnumberNoOptional maximum number of functions to return, sent as the MaxItems query parameter.

Details

From the project README

serverlessrun

AWS Lambda as MCP tools, shaping requests for the documented Lambda REST API. serverlessrun is a clean-room rebuild of the core surface of the aws-lambda MCP server, under a new name: the same tool names and request shapes, fresh code, no copied branding.

Tools (core subset, 10)

list_functions, get_function, invoke_function, list_versions_by_function, get_alias, list_aliases, list_layers, get_layer_version, list_event_source_mappings, get_account_settings.

Not in this subset: function create/update/delete and code upload, configuration and policy management, tags, concurrency controls, function URLs, destinations, event source mapping writes, and code signing.

How it works

Every tool shapes a documented Lambda REST request (API version 2015-03-31) and hands it to an injectable executor: execute({ service: "lambda", operation, path, method, body, query }). Library users can inject their own executor or signer to run against real AWS with their own signing stack.

Setup

export AWS_ACCESS_KEY_ID=...
export AWS_SECRET_ACCESS_KEY=...
export AWS_REGION=us-east-1        # optional, this is the default
export AWS_SESSION_TOKEN=...       # optional

Honest limitation: this rebuild ships no SigV4 signer of its own. With credentials set but no signer injected, calls fail with SigV4 signing not configured: inject a signer/executor. With no credentials, calls fail with an error naming AWS_ACCESS_KEY_ID.

CLI

npx @reneturcios/serverlessrun list_functions '{}'
npx @reneturcios/serverlessrun mcp        # stdio MCP server

Each tool name is a subcommand taking one JSON object argument.

MCP client config

{
  "mcpServers": {
    "serverlessrun": {
      "command": "npx",
      "args": ["-y", "@reneturcios/serverlessrun", "mcp"],
      "env": { "AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..." }
    }
  }
}

Docker

docker run -i -e AWS_ACCESS_KEY_ID -e AWS_SECRET_ACCESS_KEY ghcr.io/cloudcorprecords/serverlessrun

Development

npm install
npm run build
npm test

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.