MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
This read-only MCP Server allows you to connect to IBM Cloud Object Storage data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for IBM Cloud Object Storage (https://www.cdata.com/drivers/ibmcloudobjectstorage/download/mcp).
MIT -
S3-compatible cloud object storage from XNS, set up and managed by your AI assistant.
npm Apache-2.0 -
MCP server for the OpenBucket S3-compatible object storage platform
npm MIT -
hanzo-tools-s3updated this year
Hanzo S3 MCP tool — buckets and objects on S3-compatible storage
pypi MIT -
Production-ready IBM Cloud Object Storage MCP Server with 37 comprehensive tools. Full S3 API compatibility with stdio + HTTP modes for AI assistants, Watsonx Orchestrate, and agent frameworks.
npm MIT -
Model Context Protocol server for the OVHcloud API, focused on Object Storage
npm MIT -
MCP server for Scaleway IAM (Applications, API keys, Policies, Permission sets) and Object Storage (buckets, Bucket Policies, object CRUD)
npm MIT -
Model Context Protocol server for the OVHcloud API, focused on Object Storage
npm MIT -
Governed AI-ops for MinIO object storage: capacity & usage RCA, bucket exposure audit, lifecycle/ILM
pypi MIT -
codegithub.com/tuist/codeactive
Git hosting whose source of truth is a write-ahead log in object storage. Stateless replicas, no control plane, MCP for agents.
MPL-2.0 ★ 10 -
nos-upload-mcpgithub.com/nicepkg/nos-upload-cliupdated this year
NOS Upload MCP Server - AI-friendly file upload service for Netease Object Storage
npm MIT -
MCP server for Oracle Cloud Infrastructure -- Compute, Object Storage, Block Storage, Networking, Autonomous Database, and IAM via the OCI SDK
MIT -
MCP server for object storage, supporting a range of operations for object storage
MIT -
Lightweight, serverless SQLite for AI agents and personal apps. Built with Rust, backed by S3-compatible object storage, and accessible via HTTP, WebSocket, MCP, or CLI.
AGPL-3.0 ★ 2 -
A fast, native macOS client for object storage — Amazon S3, S3-compatible services (MinIO, R2, Ceph…) and Alibaba Cloud OSS: browse, multipart upload/download, versions, presign, and a built-in MCP server for AI.
MIT ★ 1 -
MCP server for the Garage (deuxfleurs) S3-compatible storage Admin API - bucket, key and permission management via MCP tools, plus optional read-only S3 object access. Built via vibe coding with Claude Code.
MIT -
Lightweight object storage that speaks S3 (boto3/AWS SDK compatible), plain HTTP, and MCP. SQLite for metadata, flat files on disk.
oci WTFPL ★ 5 -
lego-obs-mcphttps://gitee.com/tapque_sdk/legoupdated this year
MCP server for managing configuration files on OBS (Object Storage Service)
cargo MIT -
@superfiles/mcpupdated this year
MCP server for SuperFiles — programmable object storage and CDN via AI assistants
npm MIT -
Multi-tenant control plane for S3-compatible object storage: tenant-scoped credentials, Cedar policies, quotas, audit and events. Not an S3 proxy — clients move bytes over presigned URLs. Connect API, web console, Go and Python SDKs, and an MCP server for AI agents.
go AGPL-3.0 ★ 3 -
static-hosting-mcpgithub.com/bobbyhyam/static-hosting-mcpupdated this year
MCP server that publishes self-contained artifacts to a Google Cloud Storage bucket and manages per-object read access by Google-account email.
pypi MIT -
minio-mcp-servergithub.com/bhayanak/minio-mcp-serverupdated this year
MCP server to manage MinIO / S3-compatible object storage - create and manage buckets, upload/download/delete objects, set lifecycle policies, manage access policies, and query storage metadata. Unlike the read-only REST API servers, this is a stateful, CRUD-capable server
MIT ★ 1 -
Explore and retrieve content from Volcengine's Torch Object Storage (TOS) using natural language queries.
★ 1 -
Local and multi-cloud object storage and file system abstraction with CLI, gRPC, REST, QUIC, and MCP server
AGPL-3.0 -
A Model Context Protocol (MCP) server that provides a bridge between MCP-compatible clients and MinIO object storage. This server exposes MinIO operations as MCP tools for seamless bucket management and object operations.
★ 4 -
@idrivee2/s3-mcpactive
Model Context Protocol server for IDrive e2 S3-compatible object storage.
npm UNLICENSED -
A Model Context Protocol (MCP) server for Amazon S3 and S3-compatible object storage, enabling AI assistants to browse buckets, read and write objects, and generate presigned URLs.
go Apache-2.0 ★ 11 -
@rovela-ai/mcp-r2active
MCP server for R2 object storage - enables Claude to view images and manage files
npm MIT -
illuminati-mcpgithub.com/Illuminati-Networks/illuminati-mcpupdated this year
Illuminati Networks MCP server — drive VPS, proxies, and CDN/object storage from any MCP client.
MIT -
The MCP Server based on the S3 protocol can perform operations on Amazon S3 and other S3-compatible object storage services.
Apache-2.0 ★ 8 -
MCP server for Contabo: manage VPS/VDS, snapshots, object storage, secrets & domains via Cursor, Claude & other MCP clients.
npm GPL-3.0 ★ 7 -
oci-mcp-servergithub.com/sauryadas/oci-mcp-serverupdated this year
MCP server giving Claude natural-language access to Oracle Cloud Infrastructure — compute, networking, OKE, and Object Storage.
-
Production-ready MCP server for IBM Cloud Object Storage with 37 comprehensive tools. Supports stdio + HTTP modes for seamless integration with AI assistants, Watsonx Orchestrate, and agent frameworks.
MIT -
VideoFetch MCP server — let any AI agent download video/audio straight into your own object storage
pypi MIT -
minio-mcp-servergithub.com/saeedshoh/minio-mcp-serverupdated this year
MCP server exposing MinIO/S3 object storage operations (list, read, write, delete, presigned URLs) as tools for LLM agents.
★ 1 -
Alibaba Cloud Object Storage Service (OSS) MCP Server, built on the Model Context Protocol (MCP), enables developers to quickly integrate OSS data management capabilities into AI applications.
npm MIT -
percept-vision-pluginupdated this year
Percept Vision — store videos in object storage + their CV understanding in Redis, then search and ask questions about them. MCP plugin.
pypi MIT -
A self-hosted AI platform: inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more, behind a single OpenAI-compatible endpoint. One docker-compose up.
WTFPL ★ 18 -
A capability runtime for AI agents — write a JavaScript function, run it in a fresh ~1ms sandbox, and keep what works as a live HTTPS endpoint or MCP server. Secrets, durable state, object storage, and inboxes included.
NOASSERTION ★ 1 -
Visual and code-based DAG builder for Apache Airflow 3: design on a canvas, generate readable Python, validate with DagBag, deploy to a folder, object storage or git. Runs as an Airflow plugin, standalone server or MCP server.
pypi Apache-2.0 -
basicdeploy-mcpno update data
The runtime your AI agent deploys to. One MCP call spins up a live container with a PostgreSQL database, S3-compatible object storage, environment variables, and a public HTTPS URL — no servers, no config, no DevOps. Your agent creates containers, deploys apps (Node/Python/Go/Docker, auto-detected), runs commands, reads logs, sets always-on, and shares or deletes them.
smithery -
An open-source, AI-native desktop client for all your object storage: Cloudflare R2, AWS S3, Alibaba Cloud OSS, Tencent Cloud COS, Qiniu and any S3-compatible service, on macOS, Windows and Linux. / 开源、AI 原生的对象存储桌面客户端,在 macOS、Windows、Linux 上统一管理 R2、S3、OSS、COS、七牛等国内外对象存储。
Apache-2.0 -
YouTube Download to Cloud Storage — FlashDatano update data
# YouTube Download to Cloud Storage — FlashData Deliver YouTube video, audio or clips to your own S3 or other supported cloud storage. Track asynchronous delivery and its output manifest. Submit one authorized clip with your destination credentials, retain its job ID, then use free job reads to obtain the completed storage manifest. [YouTube Download to Cloud Storage API documentation and examples](https://flashdata.dev/docs/sources/youtube_download?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_download-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Download to Cloud Storage listing](https://smithery.ai/servers/flashdata/youtube-download) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_download`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the per-TB rate. Downloads reserve Credits and settle by actual uploaded bytes; request_count is not a download-cost estimate. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_download` without submitting a data query. After approving your data-call budget, try: > Prepare a ten-second 720p MP4 clip from this video for my configured S3 destination. Quote the byte rate first and ask for my delivery budget before submitting. This server exposes `youtube_download`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call video_id and storage are required. Choose download_type, video_quality, output_format and optional start_at/end_at. Only async is supported. Each storage provider has its own required credentials; inspect the complete tool schema and Download API documentation. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_download", "arguments": { "video_id": "jNQXAC9IVRw", "mode": "async", "download_type": "audio_video", "video_quality": "<=720", "output_format": "mp4", "start_at": "00:00:00", "end_at": "00:00:10", "storage": { "storage_type": "s3", "storage_url": "your-media-bucket", "access_key": "YOUR_ACCESS_KEY", "secret_key": "YOUR_SECRET_KEY", "region": "us-east-1", "object_prefix": "flashdata-clips" } } } ``` ## Work with the output Submit once, save the returned id, and call get_job with job_id until job.status is completed. Read output.results[0] for file_url, file_size, downloaded_bytes and output_format. Pending or processing is not completed delivery. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "job": { "id": "job_EXAMPLE", "source": "youtube_download", "status": "completed" }, "output": { "results": [ { "file_url": "s3://customer-bucket/clip.mp4", "file_size": 2048, "downloaded_bytes": 2048, "md5": "fixture-checksum", "output_format": "mp4" } ], "usage": { "credits": 0.001 } }, "http_status": 200, "request_id": "fixture-request" } ``` For example, after receiving the real id, call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Poll only the read, not the original download submission. Storage credentials travel to FlashData to perform the upload and may be retained by your MCP client in tool history; use narrowly scoped credentials and your client's protected configuration. ## Limits and result handling Only asynchronous delivery is supported. Supply your own destination and credentials; media access and retention follow your storage settings. Private object URLs are not public download links. Charges reserve Credits and settle by uploaded bytes. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
MWS S3 MCP AI CLIgithub.com/stufently/mws-s3-mcp-ai-clino update data
An MCP server and command-line client for MWS S3 object storage in one Go binary. It connects Claude, Cursor or Codex to an existing bucket for browsing, previewing and restoring files. By default the server is read-only and offers 14 tools: buckets, objects, metadata, prefix usage, largest objects and unfinished multipart uploads. Write, delete and bucket-admin tools (32 tools in total) appear only when the matching allow_write, allow_delete or allow_admin switch is on, and a destructive call asks a person first under the default confirm policy. Optional bucket and prefix allowlists narrow access further; local upload and download are confined to a chosen directory. Needs an S3 access key ID and secret. The bundle published here is the linux-amd64 build; binaries for linux-arm64, macOS and Windows and a container image are on the GitHub Releases page.
smithery -
Beget S3 MCP AI CLIgithub.com/stufently/beget-s3-mcp-ai-clino update data
An MCP server and command-line client for Beget S3 object storage in one Go binary. It connects Claude, Cursor or Codex to an existing bucket for browsing, previewing and restoring files. By default the server is read-only and offers 10 tools: buckets, objects, metadata, prefix usage, largest objects and unfinished multipart uploads. Write, delete and bucket-admin tools (18 tools in total) appear only when the matching allow_write, allow_delete or allow_admin switch is on, and a destructive call asks a person first under the default confirm policy. Optional bucket and prefix allowlists narrow access further; local upload and download are confined to a chosen directory. Needs an S3 access key ID and secret. The bundle published here is the linux-amd64 build; binaries for linux-arm64, macOS and Windows and a container image are on the GitHub Releases page.
smithery -
An MCP server and command-line client for Timeweb Cloud S3 object storage in one Go binary. It connects Claude, Cursor or Codex to an existing bucket for browsing, previewing and restoring files. By default the server is read-only and offers 14 tools: buckets, objects, metadata, prefix usage, largest objects and unfinished multipart uploads. Write, delete and bucket-admin tools (31 tools in total) appear only when the matching allow_write, allow_delete or allow_admin switch is on, and a destructive call asks a person first under the default confirm policy. Optional bucket and prefix allowlists narrow access further; local upload and download are confined to a chosen directory. Needs an S3 access key ID and secret. The bundle published here is the linux-amd64 build; binaries for linux-arm64, macOS and Windows and a container image are on the GitHub Releases page.
smithery -
An MCP server and command-line client for Cloud.ru S3 object storage in one Go binary. It connects Claude, Cursor or Codex to an existing bucket for browsing, previewing and restoring files. By default the server is read-only and offers 14 tools: buckets, objects, metadata, prefix usage, largest objects and unfinished multipart uploads. Write, delete and bucket-admin tools (32 tools in total) appear only when the matching allow_write, allow_delete or allow_admin switch is on, and a destructive call asks a person first under the default confirm policy. Optional bucket and prefix allowlists narrow access further; local upload and download are confined to a chosen directory. Needs an S3 access key ID and secret. The bundle published here is the linux-amd64 build; binaries for linux-arm64, macOS and Windows and a container image are on the GitHub Releases page.
smithery -
MinIO存储管理MCP工具 - 提供完整的MinIO对象存储管理功能
npm MIT -
MCP server for StoreFS distributed S3 storage management
npm Apache-2.0 -
@rockjing/aliyunoss-cligithub.com/rockjing/aliyunoss-cliupdated this year
阿里云 OSS CLI 工具,保留 MCP stdio 兼容入口
npm MIT -
MCP server for Obsideo: encrypted S3-compatible storage with cryptographic possession proofs. 12 GB free, self-serve signup, runs on your machine.
npm NOASSERTION -
MCP server for XNS S3-compatible storage — agent-driven Relayer install & management. Mirrored from GitLab.
Apache-2.0 ★ 3 -
MCP server for object CRUD in one AWS S3 or S3-compatible bucket.
npm MIT -
MCP (Model Context Protocol) server for Storj decentralized cloud storage: lets Claude Desktop, Cursor, Windsurf and other AI assistants upload, download, list, search and share files on Storj through 28 tools. Built on storj-uplink-nodejs.
npm MIT ★ 1 -
minio-mcp-serverupdated this year
MCP server for MinIO/S3 — bucket management, object CRUD, presigned URLs, policies, analytics
npm MIT -
Lightweight, self-hosted S3-compatible object store in Rust: soft delete, point-in-time recovery, built-in MCP. AGPL-3.0.
AGPL-3.0 -
S3-compatible storage MCP gateway — Streamable HTTP + stdio, 39 tools, file → public URL
MIT -
腾讯云COS MCP服务器 - 基于Node.js的Model Context Protocol服务器,提供腾讯云对象存储服务功能
npm MIT -
MCP Server for Infino
npm Apache-2.0 -
@storage4everyone/mcpactive
Model Context Protocol server that lets AI agents use Storage4Everyone buckets with your API key
npm Apache-2.0