aws-mcp-connector
Talk to AWS CLI from an MCP-speaking agent. Run any aws <service> <operation> command through the Model Context Protocol, with read-only defaults and gated write access.
README
<div align="center">
๐ aws-mcp-connector
Talk to AWS CLI from an MCP-speaking agent.
</div>
A single static Go binary that speaks the Model Context Protocol
and lets an agent run AWS CLI commands: any aws <service> <operation>
invocation, across every service the CLI supports, with a read-only-by-default
safety gate on anything that mutates state.
No Python, no uv, no runtime dependency to install โ just a binary and
an .mcp.json. It shells out to the aws binary already installed and
configured on the host (profile, SSO, IAM role, or static keys โ whatever
the AWS CLI's own credential chain resolves) instead of reimplementing the
AWS SDK, so it gets the full breadth of the CLI for free rather than a
hand-curated subset of services.
โจ Why this exists
An agent that only has a narrow, hand-picked set of AWS tools hits a wall the moment you need something outside that set. This connector instead wraps the AWS CLI itself, so an agent can run
aws s3 ls,aws ec2 describe-instances,aws iam list-usersโ anything the CLI can do โ without waiting on a new tool to be written for it. Mutating commands are blocked by default and require both a server-level opt-in and a per-callconfirm=true, so exploring/debugging is safe out of the box.
๐งฐ Tools
| Tool | What it does | Write? |
|---|---|---|
aws_exec |
Run any aws <service> <operation> ... command. Read-only by default โ mutating commands need AWS_MCP_ALLOW_WRITE=true on the server and confirm=true on the call. |
โ (gated) |
aws_help |
Show aws <service> [subcommand] help text โ always safe, use it to check exact syntax before calling aws_exec. |
|
aws_whoami |
Show the AWS identity (account, ARN, user/role) the configured credentials resolve to. | |
aws_list_profiles |
List named profiles configured in ~/.aws/config on the host. |
Every tool accepts an optional response_format: markdown (default,
pretty tables for a chat UI) or json (for programmatic use).
๐ Quickstart
Fastest path: grab a prebuilt bundle from the latest release โ
download aws-mcp-connector-plugin-<version>-<os>-<arch>.zip, unzip it,
and point Cowork/Claude at the plugin/ folder inside (see step 4 of
SETUP.md). No Go toolchain required.
From source:
# 1. Build
cd go-server
go mod tidy
go build -o aws-connector-server .
cp aws-connector-server ../plugin/servers/go/
# 2. Set up auth โ needs the aws CLI itself installed and configured
# (aws configure / aws sso login) โ see SETUP.md
export AWS_PROFILE=default # optional, only if not using "default"
# 3. Run
./go-server/aws-connector-server # serves MCP over stdio
Or make build โ see the Makefile for every shortcut
(test, vet, fmt, lint, tidy).
Full walkthrough โ including wiring this up as a Claude/Cowork plugin โ is in SETUP.md.
๐ Configuration
Everything is environment variables, passed through by the plugin's
.mcp.json:
| Variable | Purpose | Default |
|---|---|---|
AWS_PROFILE |
Named profile from ~/.aws/config to use. |
unset (default profile) |
AWS_REGION |
Default region if not set elsewhere. | AWS CLI's own default |
AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY / AWS_SESSION_TOKEN |
Static credentials โ only needed if not using a profile/SSO/role. | unset |
AWS_MCP_ALLOW_WRITE |
"true" to permit mutating commands at all (still needs confirm=true per call). |
false (read-only) |
AWS_MCP_ALLOWED_SERVICES |
Comma-separated allowlist of AWS CLI service names, e.g. "s3,ec2". |
unset (unrestricted) |
AWS_MCP_CLI_PATH |
Path to the aws binary. |
aws resolved via PATH |
๐งช Quality bar
This isn't a toy script โ it's got the same checks you'd expect from a production Go service:
- โ
Unit tests for every input-validation path (
go test ./...) - โ
go vet+gofmtclean - โ golangci-lint (govet, staticcheck, errcheck, gosec, and more)
- โ govulncheck โ no known vulnerabilities in the dependency graph
- โ CodeQL static security analysis on every push
- โ End-to-end verified against a real (or sandboxed) AWS CLI backend โ not mocks
- โ Dependabot keeps Go modules and Actions current
All of it runs in CI on every push and PR.
๐ท๏ธ Releases & versioning
Versions follow semver and are cut automatically by
release-please from
Conventional Commits on main:
fix: ...โ patch (v0.1.0โv0.1.1)feat: ...โ minor (v0.1.1โv0.2.0)feat!: .../BREAKING CHANGE:footer โ major (v0.2.0โv1.0.0)
Every merged PR updates a standing "chore(main): release vX.Y.Z" PR with an auto-generated CHANGELOG.md. Merging that PR:
- tags the release and publishes it on GitHub
- builds and attaches zipped, ready-to-install plugin bundles for linux/darwin/windows ร amd64/arm64
- regenerates
server.jsonfrom those exact assets (fresh version + SHA-256 hashes) and publishes it to the official MCP Registry viamcp-publisher, authenticated with GitHub OIDC โ no stored secrets
See .github/workflows/release-please.yml
and .github/workflows/publish-mcp-registry.yml
(also runnable by hand for an existing tag via workflow_dispatch).
๐ Layout
aws-mcp-connector/
โโโ README.md โ you are here
โโโ SETUP.md โ step-by-step setup guide
โโโ CONTRIBUTING.md โ how to contribute
โโโ CODE_OF_CONDUCT.md
โโโ SECURITY.md โ vulnerability reporting
โโโ CODEOWNERS
โโโ LICENSE โ MIT
โโโ Makefile โ build / test / lint shortcuts
โโโ .golangci.yml โ lint rules
โโโ release-please-config.json โ semver/changelog automation config
โโโ .release-please-manifest.json
โโโ server.json โ MCP Registry manifest (regenerated fresh per release by CI)
โโโ scripts/
โ โโโ render-server-json.sh โ rebuilds server.json from a release's zip assets
โโโ .github/
โ โโโ workflows/
โ โ โโโ ci.yml โ build, vet, test, lint, govulncheck
โ โ โโโ codeql.yml โ security scanning
โ โ โโโ pr-title.yml โ Conventional Commits PR title check
โ โ โโโ release-please.yml โ version PRs, tagging, GitHub releases
โ โ โโโ publish-mcp-registry.yml โ publishes server.json to the MCP Registry
โ โ โโโ rebuild-release-assets.yml โ manual re-attach fallback
โ โโโ ISSUE_TEMPLATE/
โ โโโ PULL_REQUEST_TEMPLATE.md
โ โโโ dependabot.yml
โโโ go-server/ โ the MCP server source
โ โโโ main.go
โ โโโ main_test.go
โ โโโ go.mod / go.sum
โ โโโ README.md
โโโ plugin/ โ installable Cowork/Claude plugin
โโโ .claude-plugin/plugin.json
โโโ .mcp.json โ holds credentials locally โ never commit real ones
โโโ servers/go/ โ compiled binary goes here
๐ค Contributing
PRs and issues are very welcome โ see CONTRIBUTING.md for the full guide (setup, coding conventions, how to add a new tool) and the Code of Conduct.
main is protected: every change, including the maintainer's, lands via
pull request with CI green. PR titles must follow
Conventional Commits โ that's what
drives the automatic versioning above.
Found a security issue? Please follow SECURITY.md instead of opening a public issue.
๐ License
MIT ยฉ FerhatDundar
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.