s3-mcp-connector
Enables agents to interact with any S3-compatible storage (AWS S3, LocalStack, MinIO) via MCP, providing tools like list, read, write, delete objects and buckets.
README
<div align="center">
๐ชฃ s3-mcp-connector
Talk to Amazon S3 โ or LocalStack, MinIO, any S3-compatible store โ from an MCP-speaking agent.
</div>
A single static Go binary that speaks the Model Context Protocol and exposes 8 tools for working with S3: list buckets, list/read/write/delete objects, create/delete buckets. Point it at real AWS or at a local LocalStack/MinIO instance with one environment variable โ same binary, same tools, zero code changes.
No Python, no uv, no runtime dependency to install โ just a binary and
an .mcp.json.
โจ Why this exists
An agent that can only talk about your S3 buckets isn't that useful. This gives it hands: it can look inside a bucket, read a config file out of it, drop a report back in, or clean up a stale prefix โ safely, with guardrails on size and destructive actions built in.
๐งฐ Tools
| Tool | What it does | Write? |
|---|---|---|
s3_list_buckets |
List buckets visible to the credentials | |
s3_list_objects |
List objects in a bucket, optional prefix, paginated | |
s3_head_object |
Object metadata (size, type, ETag) without downloading | |
s3_get_object |
Read an object's content โ text or base64, size-capped | |
s3_put_object |
Write a small text/base64 object (โค 5 MB) | โ๏ธ |
s3_delete_object |
Delete one object | ๐๏ธ destructive |
s3_create_bucket |
Create a bucket | โ๏ธ |
s3_delete_bucket |
Delete an empty bucket | ๐๏ธ destructive |
Every tool accepts an optional response_format: markdown (default,
pretty tables for a chat UI) or json (for programmatic use).
s3_get_object auto-detects text vs. binary content and caps output at
200,000 bytes by default (raise via max_bytes, hard cap
5,000,000) โ it's built for reading configs, logs, and small data
files, not bulk transfer. Reach for the AWS CLI or SDK directly for large
objects.
๐ Quickstart
Fastest path: grab a prebuilt bundle from the latest release โ
download s3-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 s3-connector-server .
cp s3-connector-server ../plugin/servers/go/
# 2. Spin up LocalStack to test against (no AWS account needed)
cd ..
docker compose up -d
# 3. Point the connector at it
export AWS_ACCESS_KEY_ID=test
export AWS_SECRET_ACCESS_KEY=test
export AWS_REGION=us-east-1
export S3_ENDPOINT_URL=http://localhost:4566
export S3_FORCE_PATH_STYLE=true
./go-server/s3-connector-server # serves MCP over stdio
Or make build && make localstack-up โ see the Makefile for
every shortcut (test, vet, fmt, lint, tidy, localstack-down).
Full walkthrough โ including wiring this up as a Claude/Cowork plugin and switching from LocalStack to real AWS โ is in SETUP.md.
๐ Configuration
Everything is environment variables, passed through by the plugin's
.mcp.json:
| Variable | Purpose | Default |
|---|---|---|
AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY |
AWS credentials. Any non-empty values work against LocalStack. | โ |
AWS_REGION |
Region to use. | us-east-1 |
S3_ENDPOINT_URL |
Custom endpoint. Leave unset for real AWS. | (unset) |
S3_FORCE_PATH_STYLE |
true for LocalStack/MinIO (path-style addressing). |
false |
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 real LocalStack โ every tool (create/delete bucket, put/get/head/list/delete object, and the 404 error path) was exercised against a live S3-compatible service, 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
s3-mcp-connector/
โโโ README.md โ you are here
โโโ SETUP.md โ step-by-step setup guide (LocalStack + real AWS)
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 / localstack shortcuts
โโโ docker-compose.yml โ LocalStack, for local testing
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 Ferhat Dundar
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.