Skip to main content
hc
Submit
mcpSource-backed
MCP Proxy for AWS logo

MCP Proxy for AWS

AWS-maintained proxy and Python library that lets MCP clients and agent frameworks connect to IAM-secured MCP servers on AWS by signing requests with AWS SigV4 credentials.

by aws · submitted by oktofeesh1·added 2026-06-06·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL
https://heyclau.de/entry/mcp/aws-mcp-proxy-for-aws
Source URLs
https://github.com/aws/mcp-proxy-for-aws/blob/main/README.md, https://github.com/aws/mcp-proxy-for-aws
Brand
MCP Proxy for AWS
Brand domain
aws.amazon.com
Brand asset source
brandfetch
Safety notes
MCP Proxy for AWS signs MCP requests with local AWS credentials, so tool calls can inherit the AWS permissions of the selected profile or role., Multi-profile mode injects an `aws_profile` parameter into auth-requiring tools; restrict the profile list to accounts and roles an agent may safely use., The `--read-only` flag disables tools that require write permissions when the upstream tool annotations identify them, but it is not a substitute for IAM least privilege., The `--skip-auth` option can bypass request signing when credentials are unavailable; avoid it unless the endpoint is intentionally unauthenticated., Docker examples mount AWS credential directories read-only; keep mounts scoped and avoid sharing long-lived credentials with untrusted containers.
Privacy notes
The proxy may process AWS access keys, session tokens, profile names, regions, SigV4 headers, MCP endpoint URLs, metadata, prompts, tool names, tool arguments, tool results, logs, telemetry, and framework session data., AWS profile names and metadata can reveal account structure, environment names, regions, and service ownership., Logs from clients, containers, or frameworks can expose endpoint URLs, selected profiles, tool arguments, and AWS error details., Store AWS credentials through standard credential providers or IAM roles, rotate temporary sessions, and avoid committing MCP client configs with real endpoints or profile names.
Author
aws
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done

  • Source provenance statusRequired

    Marked as source-backed.

    Done

  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done

  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done

  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done

  • Package verification flag

    No package verification flag provided.

    Pending

  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending

  • Baseline comparison available

    No baseline peer selected yet.

    Pending

  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

15 minutes

Install command

Provided

Config snippet

Provided

Copy snippet

Provided

Prerequisites

5 to clear

Platforms

4 listed

Install type

CLI install

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done

  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending

  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done

  • Review privacy notesRequired

    Privacy notes are present.

    Done

  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending

  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending

  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

5 prerequisites to line up before setup. Have accounts and credentials ready first.

0/5 ready
Account & credentials1Install & runtime1Configuration2General115 minutes

Safety & privacy surface

Safety & privacy surface

5 safety and 4 privacy notes across 4 risk areas. Review closely: credentials & tokens, permissions & scopes, network access.

4 areas
  • SafetyCredentials & tokensMCP Proxy for AWS signs MCP requests with local AWS credentials, so tool calls can inherit the AWS permissions of the selected profile or role.
  • SafetyPermissions & scopesMulti-profile mode injects an `aws_profile` parameter into auth-requiring tools; restrict the profile list to accounts and roles an agent may safely use.
  • SafetyPermissions & scopesThe `--read-only` flag disables tools that require write permissions when the upstream tool annotations identify them, but it is not a substitute for IAM least privilege.
  • SafetyCredentials & tokensThe `--skip-auth` option can bypass request signing when credentials are unavailable; avoid it unless the endpoint is intentionally unauthenticated.
  • SafetyCredentials & tokensDocker examples mount AWS credential directories read-only; keep mounts scoped and avoid sharing long-lived credentials with untrusted containers.
  • PrivacyCredentials & tokensThe proxy may process AWS access keys, session tokens, profile names, regions, SigV4 headers, MCP endpoint URLs, metadata, prompts, tool names, tool arguments, tool results, logs, telemetry, and framework session data.
  • PrivacyLocal filesAWS profile names and metadata can reveal account structure, environment names, regions, and service ownership.
  • PrivacyNetwork accessLogs from clients, containers, or frameworks can expose endpoint URLs, selected profiles, tool arguments, and AWS error details.
  • PrivacyCredentials & tokensStore AWS credentials through standard credential providers or IAM roles, rotate temporary sessions, and avoid committing MCP client configs with real endpoints or profile names.

Safety notes

  • MCP Proxy for AWS signs MCP requests with local AWS credentials, so tool calls can inherit the AWS permissions of the selected profile or role.
  • Multi-profile mode injects an `aws_profile` parameter into auth-requiring tools; restrict the profile list to accounts and roles an agent may safely use.
  • The `--read-only` flag disables tools that require write permissions when the upstream tool annotations identify them, but it is not a substitute for IAM least privilege.
  • The `--skip-auth` option can bypass request signing when credentials are unavailable; avoid it unless the endpoint is intentionally unauthenticated.
  • Docker examples mount AWS credential directories read-only; keep mounts scoped and avoid sharing long-lived credentials with untrusted containers.

Privacy notes

  • The proxy may process AWS access keys, session tokens, profile names, regions, SigV4 headers, MCP endpoint URLs, metadata, prompts, tool names, tool arguments, tool results, logs, telemetry, and framework session data.
  • AWS profile names and metadata can reveal account structure, environment names, regions, and service ownership.
  • Logs from clients, containers, or frameworks can expose endpoint URLs, selected profiles, tool arguments, and AWS error details.
  • Store AWS credentials through standard credential providers or IAM roles, rotate temporary sessions, and avoid committing MCP client configs with real endpoints or profile names.

Prerequisites

  • Python 3.10+ and `uv`, or Docker for the public ECR image path.
  • AWS credentials configured through AWS CLI profiles, environment variables, or IAM roles.
  • The SigV4-protected MCP endpoint URL, AWS region, and optional AWS service name for signing.
  • Least-privilege AWS profiles prepared before enabling multi-profile switching for agents.
  • A decision on read-only mode, retries, timeouts, logging level, and telemetry settings before use.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
intermediate
Full copyable content
uvx mcp-proxy-for-aws@latest SIGV4_MCP_ENDPOINT_URL --region AWS_REGION --profile AWS_PROFILE

About this resource

Content

MCP Proxy for AWS is an AWS-maintained proxy and Python library for connecting MCP clients and agent frameworks to MCP servers on AWS that use IAM SigV4 authentication. It handles request signing with local AWS credentials so standard MCP clients do not need to implement SigV4 support themselves.

The package can run as a stdio bridge for clients such as Claude Desktop and Kiro CLI, or it can be imported as a library for Python agent frameworks such as LangChain, LlamaIndex, Strands Agents, and Microsoft Agent Framework.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, package metadata, server implementation, SigV4 helper, client library, PyPI JSON, public ECR gallery page, and license file for current install, credential, profile, signing, and integration behavior.

Features

  • Sign MCP requests to AWS-hosted MCP endpoints with SigV4.
  • Resolve AWS credentials from profiles, environment variables, shared credential files, or IAM roles.
  • Run as a stdio bridge for MCP clients that cannot sign AWS IAM requests.
  • Use multi-profile switching so agents can call allowed AWS profiles per tool call.
  • Infer or accept the AWS service name used for SigV4 signing.
  • Inject metadata such as region into MCP requests.
  • Enable read-only mode for tools that are annotated as write-capable by the upstream server.
  • Configure retries, connect/read/write timeouts, tool-call timeout, and log level.
  • Run from PyPI with uvx, from source with uv, or from the public AWS ECR image.
  • Import the Python client helpers in LangChain, LlamaIndex, Strands Agents, or Microsoft Agent Framework workflows.

Installation

Run the proxy with uvx and the SigV4-protected MCP endpoint:

uvx mcp-proxy-for-aws@latest SIGV4_MCP_ENDPOINT_URL --region AWS_REGION --profile AWS_PROFILE

For multiple allowed profiles, pass profiles on the command line or set AWS_MCP_PROXY_PROFILES. The first profile is the default, and later profiles can be selected per call through the injected aws_profile parameter.

Use --read-only when the agent should avoid write-capable tools, and combine it with least-privilege IAM credentials. The README also documents a public ECR image for Docker-based MCP client configs.

Use Cases

  • Connect Claude to an MCP server on AWS that requires IAM SigV4 signing.
  • Let Kiro CLI or another MCP client use AWS credentials without custom signing code.
  • Bridge Bedrock AgentCore-style MCP endpoints into local MCP clients.
  • Give an agent a constrained set of AWS profiles for cross-account inspection.
  • Use read-only mode while still enforcing least privilege through IAM.
  • Build Python agents that call IAM-secured MCP servers through framework-specific client helpers.
  • Run the proxy in Docker with a read-only AWS credential mount for local development.

Safety and Privacy

MCP Proxy for AWS makes AWS credentials usable by agent tool calls. Keep IAM permissions narrow, prefer short-lived credentials, and restrict multi-profile mode to profiles that are appropriate for the task. The --read-only flag helps filter write-capable tools when annotations are available, but IAM permissions remain the real enforcement boundary.

Avoid --skip-auth unless the upstream MCP endpoint is intentionally public or protected by another control. Be careful with Docker credential mounts and framework logs; profile names, endpoint URLs, AWS errors, SigV4 metadata, tool arguments, and tool results can all reveal sensitive account or workload data.

Treat MCP client configs, .env files, AWS credential directories, session tokens, endpoint URLs, telemetry, and logs as sensitive. Rotate credentials and avoid giving agents profiles that can modify production systems unless the host workflow includes explicit approval.

Duplicate Check

No aws/mcp-proxy-for-aws source entry, MCP Proxy for AWS entry, or matching source URL was found in content/mcp. Existing AWS Labs MCP coverage is distinct from this SigV4 proxy and Python client bridge for IAM-secured MCP servers on AWS.

#proxy#aws#security#cloud#infrastructure

Source citations

Add this badge to your README

Show that MCP Proxy for AWS is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/aws-mcp-proxy-for-aws.svg)](https://heyclau.de/entry/mcp/aws-mcp-proxy-for-aws)

How it compares

MCP Proxy for AWS side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).

Field
MCP Proxy for AWS logoMCP Proxy for AWS

AWS-maintained proxy and Python library that lets MCP clients and agent frameworks connect to IAM-secured MCP servers on AWS by signing requests with AWS SigV4 credentials.

Open dossier
AWS Labs logoAWS IAM MCP Server

Official AWS Labs MCP server for AWS Identity and Access Management that lets AI assistants inspect and manage IAM users, roles, groups, policies, and access keys, with policy simulation and an opt-in read-only mode.

Open dossier
AWS logoAWS Services MCP Server - MCP Servers

Comprehensive AWS cloud services integration for infrastructure management, deployment, and monitoring

Open dossier
Bifrost logoBifrost MCP Gateway

Open-source AI gateway that can connect to downstream MCP servers and expose their aggregated tools through a single HTTP or SSE MCP endpoint for Claude Desktop, Cursor, and other MCP clients.

Open dossier
Next steps
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustDiffersPackage not verifiedPackage not verifiedPackage verifiedPackage not verified
Source provenanceDiffersSource-backedSource-backedNo submission linkSource-backed
SubmitterDiffersoktofeesh1jaso0n0818—oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandMCP Proxy for AWS logoMCP Proxy for AWSAWS Labs logoAWS LabsAWS logoAWSBifrost logoBifrost
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedFirst-partySource-backed
AuthorawsAWS LabsAWS Labsmaximhq
Added2026-06-062026-06-212025-09-162026-06-06
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Harness
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓MCP Proxy for AWS signs MCP requests with local AWS credentials, so tool calls can inherit the AWS permissions of the selected profile or role. Multi-profile mode injects an `aws_profile` parameter into auth-requiring tools; restrict the profile list to accounts and roles an agent may safely use. The `--read-only` flag disables tools that require write permissions when the upstream tool annotations identify them, but it is not a substitute for IAM least privilege. The `--skip-auth` option can bypass request signing when credentials are unavailable; avoid it unless the endpoint is intentionally unauthenticated. Docker examples mount AWS credential directories read-only; keep mounts scoped and avoid sharing long-lived credentials with untrusted containers.✓Run with the `--readonly` flag (shown above) to block all mutating operations. Without it the server can create and delete IAM users, roles, groups, policies, and access keys — high-impact identity changes — so enable write access only deliberately and with scoped permissions. IAM controls account-wide access; a misused write operation can grant or revoke permissions broadly. Prefer non-production accounts while evaluating, and use policy simulation to test changes before applying them. This server acts on real IAM with your AWS credentials; scope the profile tightly and run it only on a trusted host.✓Scope AWS credentials to the intended accounts, regions, and services because infrastructure actions can affect production resources.✓Bifrost can expose all selected downstream MCP tools through one `/mcp` gateway endpoint, so treat the endpoint like an access layer for every connected tool. The docs state that default LLM tool calls are suggestions until an explicit tool execution API call is made, but agent mode can enable configured automatic execution. Gateway-mode auto-approval is controlled by the external MCP host, such as Claude Desktop, Cursor, Cline, or a custom client, not by Bifrost's `tools_to_auto_execute` setting. Stdio connections spawn local commands inside the Bifrost runtime; Docker deployments need images that include the requested executables. Use virtual keys, per-tool allowlists, auth headers, OAuth, per-user credentials, and network controls to limit which clients can reach high-impact tools.
Privacy notes✓The proxy may process AWS access keys, session tokens, profile names, regions, SigV4 headers, MCP endpoint URLs, metadata, prompts, tool names, tool arguments, tool results, logs, telemetry, and framework session data. AWS profile names and metadata can reveal account structure, environment names, regions, and service ownership. Logs from clients, containers, or frameworks can expose endpoint URLs, selected profiles, tool arguments, and AWS error details. Store AWS credentials through standard credential providers or IAM roles, rotate temporary sessions, and avoid committing MCP client configs with real endpoints or profile names.✓IAM user/role/group names, ARNs, policy documents, and account metadata can be returned through tool calls and exposed to the model. Access key IDs and other identity material may appear in responses; never expose secret access keys, and keep account identifiers and policy contents out of public prompts, issues, and screenshots.✓AWS resource names, configuration, metrics, logs, ARNs, and account metadata may be exposed through tool calls and responses.✓Bifrost may process provider prompts, model responses, MCP tool names, tool arguments, tool results, headers, virtual keys, OAuth tokens, per-user credentials, logs, traces, metrics, and downstream server metadata. Per-user auth stores credentials against a signed-in user, virtual key, or session identity; review credential lifecycle, revocation, and orphaned-session behavior. Logs, config stores, provider settings, MCP sessions, and gateway analytics can contain sensitive operational or user data. Keep real provider keys, virtual keys, OAuth secrets, MCP endpoint URLs, and upstream service credentials in environment variables or secret stores, not committed config.
Prerequisites
  • Python 3.10+ and `uv`, or Docker for the public ECR image path.
  • AWS credentials configured through AWS CLI profiles, environment variables, or IAM roles.
  • The SigV4-protected MCP endpoint URL, AWS region, and optional AWS service name for signing.
  • Least-privilege AWS profiles prepared before enabling multi-profile switching for agents.
  • An AWS account with IAM access and permissions for the IAM read (and, if write is enabled, manage) operations you intend to use.
  • Python 3.10 or newer and `uv` / `uvx` installed (Astral) to run the package.
  • AWS credentials configured locally (for example via `aws configure` or `AWS_PROFILE`) scoped least-privilege; read-only IAM permissions are enough for the recommended `--readonly` mode.
  • An MCP client that supports stdio servers; the server runs locally on the same host as the client.
  • Python 3.8+ installed for running uvx commands
  • uv package manager installed (provides uvx command for running Python packages)
  • AWS account with active credentials and appropriate IAM permissions
  • AWS credentials configured via one of: IAM access keys (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY), AWS profile (~/.aws/credentials), or IAM role (for EC2/ECS)
  • Node.js with `npx`, Docker, or another supported Bifrost Gateway deployment path.
  • Bifrost Gateway version `v1.4.0-prerelease1` or newer for MCP gateway mode.
  • Downstream MCP server commands or HTTP/SSE endpoint URLs prepared before registering clients.
  • Provider API keys, virtual keys, gateway auth settings, and governance policies reviewed before sharing the endpoint.
Install
uvx mcp-proxy-for-aws@latest SIGV4_MCP_ENDPOINT_URL
uvx awslabs.iam-mcp-server@latest --readonly
uvx awslabs.core-mcp-server@latest && claude mcp list
npx -y @maximhq/bifrost
Config
{
  "mcpServers": {
    "aws": {
      "command": "uvx",
      "args": [
        "mcp-proxy-for-aws@latest",
        "SIGV4_MCP_ENDPOINT_URL",
        "--region",
        "AWS_REGION",
        "--profile",
        "AWS_PROFILE",
        "--read-only"
      ],
      "env": {
        "AWS_MCP_PROXY_PROFILES": "prod-readonly dev staging"
      }
    }
  }
}
{
  "mcpServers": {
    "awslabs.iam-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.iam-mcp-server@latest", "--readonly"],
      "env": {
        "AWS_PROFILE": "${AWS_PROFILE}",
        "AWS_REGION": "us-east-1",
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "aws": {
      "env": {
        "AWS_REGION": "${AWS_REGION:-us-east-1}",
        "AWS_PROFILE": "${AWS_PROFILE}",
        "FASTMCP_LOG_LEVEL": "${FASTMCP_LOG_LEVEL:-ERROR}"
      },
      "args": [
        "awslabs.core-mcp-server@latest"
      ],
      "command": "uvx",
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "bifrost": {
      "url": "BIFROST_MCP_URL",
      "headers": {
        "Authorization": "Bearer ${BIFROST_VIRTUAL_KEY}"
      },
      "type": "http"
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Source-backed guides for putting this to work.

Auditing MCP Client Configuration Before Team Rollout

Audit MCP client configuration before sharing it with a team.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by YB0y

Auto Mode Hard-Deny Policies For Safe Automation

Set autoMode.hard_deny rules to block risky actions in auto mode.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by kiannidev
AWS logo

Claude Code on Amazon Bedrock Setup

Configure Claude Code to run on Amazon Bedrock with correct AWS auth.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by kiannidev

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.