Lambda MCP Server Demo (Streamable HTTP)

Created By
mikegc-awsa year ago
Creates a simple MCP tool server with "streaming" HTTP.
Overview

What is Lambda MCP Server?

Lambda MCP Server is a serverless implementation of the Model Context Protocol (MCP) that allows developers to create and deploy cloud-hosted tools using AWS Lambda with minimal setup.

How to use Lambda MCP Server?

To use the Lambda MCP Server, clone the repository, deploy the server using AWS SAM, and create tools using the provided decorator pattern. A sample client is included to demonstrate its functionality.

Key features of Lambda MCP Server?

  • Serverless architecture using AWS Lambda
  • Built-in session state management for maintaining context
  • API key authentication for secure access
  • Example tools included for demonstration

Use cases of Lambda MCP Server?

  1. Building intelligent agents using Amazon Bedrock.
  2. Creating serverless applications that require context management.
  3. Developing tools that interact with AWS services like S3 and DynamoDB.

FAQ from Lambda MCP Server?

  • What is the Model Context Protocol (MCP)?

MCP is a protocol designed for managing context in serverless applications.

  • Is there a client included?

Yes, a TypeScript client that supports Streamable HTTP is included in the repository.

  • How do I manage session state?

Session state is automatically managed using DynamoDB, allowing you to maintain context across tool invocations.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
mikegc-aws
Star
50
Language
Python
License
MIT-0 license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago