# Mcp Proxy For Aws > AWS MCP Proxy Server - **Type:** MCP server - **Install:** `agentstack add mcp-aws-mcp-proxy-for-aws` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [aws](https://agentstack.voostack.com/s/aws) - **Installs:** 0 - **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [aws](https://github.com/aws) - **Source:** https://github.com/aws/mcp-proxy-for-aws ## Install ```sh agentstack add mcp-aws-mcp-proxy-for-aws ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # MCP Proxy for AWS ## Overview The **MCP Proxy for AWS** package provides two ways to connect AI applications to MCP servers on AWS: 1. **Using it as a proxy** - It becomes a lightweight, client-side bridge between MCP clients (AI assistants like Claude Desktop, Kiro CLI) and MCP servers on AWS. (See [MCP Proxy](#mcp-proxy)) 2. **Using it as a library** - Programmatically connect popular AI agent frameworks (LangChain, LlamaIndex, Strands Agents, etc.) to MCP servers on AWS. (See [Programmatic Access](#programmatic-access)) ### When Do You Need This Package? - You want to connect to **MCP servers on AWS** (e.g., using Amazon Bedrock AgentCore) that use AWS IAM authentication (SigV4) instead of OAuth - You're using MCP clients (like Claude Desktop, Kiro CLI) that don't natively support AWS IAM authentication - You're building AI agents with popular frameworks like LangChain, Strands Agents, LlamaIndex, etc., that need to connect to MCP servers on AWS - You want to avoid building custom SigV4 request signing logic yourself ### How This Package Helps **The Problem:** The official MCP specification supports OAuth-based authentication, but MCP servers on AWS can also use AWS IAM authentication (SigV4). Standard MCP clients don't know how to sign requests with AWS credentials. **The Solution:** This package bridges that gap by: - **Handling SigV4 authentication automatically** - Uses your local AWS credentials (from AWS CLI, environment variables, or IAM roles) to sign all MCP requests using [SigV4](https://docs.aws.amazon.com/IAM/latest/UserGuide/reference_sigv.html) - **Providing seamless integration** - Works with existing MCP clients and frameworks - **Eliminating custom code** - No need to build your own MCP client with SigV4 signing logic ## Which Feature Should I Use? **Use as a proxy if you want to:** - Connect MCP clients like Claude Desktop or Kiro CLI to MCP servers on AWS with IAM credentials - Add MCP servers on AWS to your AI assistant's configuration - Use a command-line tool that runs as a bridge between your MCP client and AWS **Use as a library if you want to:** - Build AI agents programmatically using popular frameworks like LangChain, Strands Agents, or LlamaIndex - Integrate AWS IAM-secured MCP servers directly into your Python applications - Have fine-grained control over the MCP session lifecycle in your code ## Prerequisites * [Install Python 3.10+](https://www.python.org/downloads/release/python-3100/) * [Install the `uv` package manager](https://docs.astral.sh/uv/getting-started/installation/) * AWS credentials configured (via [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html), environment variables, or IAM roles) * (Optional, for docker users) [Install Docker Desktop](https://www.docker.com/products/docker-desktop) --- ## MCP Proxy The MCP Proxy serves as a lightweight, client-side bridge between MCP clients (AI assistants and developer tools) and IAM-secured MCP servers on AWS. The proxy handles SigV4 authentication using local AWS credentials and provides dynamic tool discovery. ### Installation #### Using PyPi ```bash # Run the server uvx mcp-proxy-for-aws@1.6.0 ``` **Note:** It is recommended to pin to a specific version (e.g., `@1.6.0`) to ensure reproducible behavior. Using `@latest` may pull in breaking changes. Check [PyPI](https://pypi.org/project/mcp-proxy-for-aws/) for the latest stable version. **Note:** The first run may take tens of seconds as `uvx` downloads and caches dependencies. Subsequent runs will start in seconds. Actual startup time depends on your network and hardware. #### Using a local repository ```bash git clone https://github.com/aws/mcp-proxy-for-aws.git cd mcp-proxy-for-aws uv run mcp_proxy_for_aws/server.py ``` #### Using Docker Docker images are published to the [public AWS ECR registry](https://gallery.ecr.aws/mcp-proxy-for-aws/mcp-proxy-for-aws). You can use the pre-built image: ```bash # Pull the latest image docker pull public.ecr.aws/mcp-proxy-for-aws/mcp-proxy-for-aws:latest # Or pull a specific version docker pull public.ecr.aws/mcp-proxy-for-aws/mcp-proxy-for-aws:1.1.6 ``` Or build the image locally: ```bash # Build the Docker image docker build -t mcp-proxy-for-aws . ``` ### Configuration Parameters | Parameter | Description | Default |Required | |----------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------|--- | | `endpoint` | MCP endpoint URL (e.g., `https://your-service.us-east-1.amazonaws.com/mcp`) | N/A |Yes | | --- | --- | --- |--- | | `--service` | AWS service name for SigV4 signing, if omitted we try to infer this from the url | Inferred from endpoint if not provided |No | | `--profile` | AWS profile(s) to use. First profile is the default. Additional profiles enable per-call switching via `aws_profile` tool parameter (e.g., `--profile prod-readonly dev staging`) | Falls back to `AWS_PROFILE` if `--profile` and `AWS_MCP_PROXY_PROFILES` are not set |No | | `--region` | AWS region to use | Uses `AWS_REGION` environment variable if not set |No | | `--metadata` | Metadata to inject into MCP requests as key=value pairs (e.g., `--metadata KEY1=value1 KEY2=value2`) | `AWS_REGION` is automatically injected based on `--region` if not provided |No | | `--read-only` | Disable tools which may require write permissions (tools which DO NOT require write permissions are annotated with [`readOnlyHint=true`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint)) | `False` |No | | `--retries` | Configures number of retries done when calling upstream services, setting this to 0 disables retries. | 0 |No | | `--log-level` | Set the logging level (`DEBUG/INFO/WARNING/ERROR/CRITICAL`) | `INFO` |No | | `--timeout` | Set desired timeout in seconds across all operations | 180 |No | | `--connect-timeout` | Set desired connect timeout in seconds | 60 |No | | `--read-timeout` | Set desired read timeout in seconds | 120 |No | | `--write-timeout` | Set desired write timeout in seconds | 180 |No | | `--tool-timeout` | Maximum seconds a tool call may take before being cancelled. When set, returns a graceful error to the agent instead of hanging indefinitely | 300 |No | | `--skip-auth` | Skip request signing when AWS credentials are unavailable instead of failing | `False` |No | | `--disable-telemetry` | Disables telemetry data collection | `False` |No | ### Optional Environment Variables Set the environment variables for the MCP Proxy for AWS: ```bash # Credentials through profile export AWS_PROFILE= # Credentials through parameters export AWS_ACCESS_KEY_ID= export AWS_SECRET_ACCESS_KEY= export AWS_SESSION_TOKEN= # AWS Region export AWS_REGION= # Multi-profile switching (alternative to --profile flag, useful for plugin integration) export AWS_MCP_PROXY_PROFILES="prod-readonly dev staging" ``` > **Note:** `AWS_MCP_PROXY_PROFILES` takes precedence over `--profile` / `AWS_PROFILE` when set. ### Multi-account access The proxy supports per-call AWS profile switching, allowing agents to work across multiple accounts without restarting. **Configuration:** ```bash # Via CLI flag (first profile is default, rest are switchable) mcp-proxy-for-aws https://aws-mcp.us-east-1.api.aws/mcp --profile prod-readonly dev staging # Via environment variable (same behavior, for plugin integration) AWS_MCP_PROXY_PROFILES="prod-readonly dev staging" mcp-proxy-for-aws https://aws-mcp.us-east-1.api.aws/mcp ``` **How it works:** - The proxy injects an `aws_profile` parameter into auth-requiring tools - The agent can pass `aws_profile` on any call to route it through a specific profile's credentials - If `aws_profile` is omitted, the default (first) profile is used - Invalid profiles are rejected with an error listing allowed values - Each non-default profile gets its own dedicated connection to the backend **Example MCP config (Kiro):** ```json { "mcpServers": { "aws": { "command": "uvx", "args": ["mcp-proxy-for-aws@1.6.0", "https://aws-mcp.us-east-1.api.aws/mcp"], "env": { "AWS_MCP_PROXY_PROFILES": "prod-readonly dev staging" } } } } ``` ### Setup Examples Add the following configuration to your MCP client config file (e.g., for Kiro CLI, edit `~/.kiro/settings/mcp.json`): **Note** Add your own endpoint by replacing `` #### Running from local - using uv ```json { "mcpServers": { "": { "disabled": false, "type": "stdio", "command": "uv", "args": [ "--directory", "/path/to/mcp_proxy_for_aws", "run", "server.py", "", "--service", "", "--profile", "default", "--region", "us-east-1", "--read-only", "--log-level", "INFO", ] } } } ``` > [!NOTE] > Cline users should not use `--log-level` argument because Cline checks the log messages in stderr for text "error" (case insensitive). #### Using Docker Using the pre-built public ECR image: ```json { "mcpServers": { "": { "command": "docker", "args": [ "run", "-i", "--rm", "--volume", "/full/path/to/.aws:/app/.aws:ro", "public.ecr.aws/mcp-proxy-for-aws/mcp-proxy-for-aws:latest", "" ], "env": {} } } } ``` Or using a locally built image: ```json { "mcpServers": { "": { "command": "docker", "args": [ "run", "--rm", "--volume", "/full/path/to/.aws:/app/.aws:ro", "mcp-proxy-for-aws", "" ], "env": {} } } } ``` --- ## Programmatic Access The MCP Proxy for AWS enables programmatic integration of IAM-secured MCP servers into AI agent frameworks. The library provides authenticated transport layers that work with popular Python AI frameworks. By default, the library resolves AWS credentials automatically from the standard [boto3 credential chain](https://docs.aws.amazon.com/boto3/latest/guide/credentials.html#configuring-credentials) (environment variables, shared credentials file, etc.). You can optionally pass credentials programmatically via the `credentials` parameter. When provided, these take precedence over the `aws_profile` parameter. Note that `aws_region` must be explicitly specified when using `credentials`. ```python from botocore.credentials import Credentials from mcp_proxy_for_aws.client import aws_iam_streamablehttp_client creds = Credentials(access_key="...", secret_key="...", token="...") mcp_client = aws_iam_streamablehttp_client( endpoint=mcp_url, aws_region=region, aws_service=service, credentials=creds, # Optional: explicitly pass AWS credentials ) ``` #### Injecting Metadata You can inject metadata into the MCP `_meta` field on every request using the `metadata` parameter. This is useful for passing additional context to the server that cannot be sent as HTTP headers due to size limits. ```python from mcp_proxy_for_aws.client import aws_iam_streamablehttp_client mcp_client = aws_iam_streamablehttp_client( endpoint=mcp_url, aws_region=region, aws_service=service, metadata={ "custom/session-context": "my-value", "custom/tracking-id": "abc-123", }, ) ``` ### Integration Patterns The library supports two integration patterns depending on your framework: #### Pattern 1: Client Factory Integration **Use with:** Frameworks that accept a factory function that returns an MCP client, e.g. Strands Agents, Microsoft Agent Framework. The `aws_iam_streamablehttp_client` is passed as a factory to the framework, which handles the connection lifecycle internally. **Example - Strands Agents:** ```python from mcp_proxy_for_aws.client import aws_iam_streamablehttp_client mcp_client_factory = lambda: aws_iam_streamablehttp_client( endpoint=mcp_url, # The URL of the MCP server aws_region=region, # The region of the MCP server aws_service=service # The un … ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [aws](https://github.com/aws) - **Source:** [aws/mcp-proxy-for-aws](https://github.com/aws/mcp-proxy-for-aws) - **License:** Apache-2.0 Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-aws-mcp-proxy-for-aws - Seller: https://agentstack.voostack.com/s/aws - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.