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.
-
Cloud189 Agent Storage — secure, reliable, extensible, free cloud storage for AI agents, powered by Tianyi Cloud 189 / 天翼云盘
★ 6 -
MCP server for XNS S3-compatible storage — agent-driven Relayer install & management. Mirrored from GitLab.
Apache-2.0 ★ 3 -
NMTS (NeedMoreTruthStorage · nmts.me) — Command-line and MCP access to NMTS: open-source, end-to-end encrypted storage on the Walrus network. NMTS charges no fee; you pay the network from your own wallet. For people at a terminal and for the agents they run.
npm Apache-2.0 ★ 1 -
@0pi/mcp-servergithub.com/dizzydes/botboxupdated this year
Ephemeral shared workspace for AI agents - cache contexts, bridge multi-agent workflows, and share data between sessions. Free 2-hour temporary storage.
npm MIT -
Command-line and MCP access to NMTS (NeedMoreTruthStorage, https://nmts.me): open-source, end-to-end encrypted storage on the Walrus network. No fee to NMTS; you pay the network from your own wallet. For people and for their agents.
npm Apache-2.0 -
Self-hosted file storage for AI agents
Apache-2.0 ★ 16 -
eustore-mcp-servergithub.com/aibollingmo/eustore-mcp-serverupdated this year
MCP server for eustore.dev — autonomous sovereign storage + vector database for AI agents. S3-compatible storage and semantic vector search, fully API-driven, no dashboard needed.
npm MIT -
ton-sovereign-deployupdated this year
Sovereign one-command CLI + MCP server to deploy a static site to .ton (TON Storage + .ton DNS + ADNL), self-host first, agent-callable. CLI, MCP server (3 tools), and a programmable SDK on one deploy contract.
npm MIT -
LimeWire MCP: hosted file storage for AI agents. Client manifests for Cursor, Gemini CLI, Codex and Agent Plugins clients.
MIT ★ 1 -
Keeps your Mac roomy: finds what is safe to delete, warns before storage or memory runs out. CLI, TUI and MCP server for people and AI agents.
npm MIT OR Apache-2.0 -
eustore-mcp-servergithub.com/AIBOLLINGMO/eustore-mcp-serverupdated this year
MCP server for eustore.dev — autonomous sovereign storage + vector database for AI agents. S3-compatible, semantic search, crypto-native.
MIT -
Durable state and artifact storage for multi-machine agentic work. Content-addressed artifacts, schema-validated records, first-writer-wins coordination. Cloudflare-native or local.
npm MIT -
Zotero AI plugin Research assistant for Zotero 10. Chat with your library, run federated scholarly search, RAG, OCR, systematic reviews, and manage cloud storage. Includes standalone MCP, Agentic capabilities, and skills library.
MIT ★ 97 -
Blob-Beadsgithub.com/sdheer/Blob-Beadsupdated this year
Temporal Vault MCP: A local-first, security-hardened state management server for agentic workflows. Implements Content-Addressable Storage (CAS), Zstandard compression, and AES-256-GCM encryption to provide an auditable, "time-traveling" memory layer for LLM agents.
MIT -
Strictly read-only MCP server that gives AI agents safe query access to Postgres, Oracle, SQL Server, Cosmos DB, Blob Storage, Log Analytics, Redis and KIM. Results as Parquet/NDJSON, Entra auth, one Docker image.
MIT -
Lightweight self-hosted web UI for AWS S3, MinIO, R2 and any S3-compatible storage. Multi-account, granular access control, built-in MCP server for AI agents
MIT ★ 6 -
Local MCP bridge for Easy Local Storage Manager: lets any AI agent (Claude Code, Cursor, Codex, Gemini CLI, ...) read and write the real browser's storage through the ELSM extension.
npm MIT -
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 -
Mem0 Memory Serverno update data
Enable AI agents to store, search, and delete persistent memories across sessions to enhance context retention and recall. Integrate seamlessly with Mem0.ai's cloud or self-hosted Supabase storage for scalable and reliable memory management. Optimize your LLM applications with advanced filtering, semantic search, and flexible storage modes tailored to your needs.
smithery -
mcp-server-lobstervaultgithub.com/lobster-kit/mcp-server-lobstervaultupdated this year
MCP server for LobsterVault — encrypted secret storage for AI agents
MIT -
@lobsterkit/vault-mcpgithub.com/lobster-kit/mcp-server-lobstervaultupdated this year
MCP server for LobsterVault — encrypted secret storage for agents
npm MIT -
mcp-context-servergithub.com/alex-feel/mcp-context-serverupdated this year
MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.
pypi other -
Shared Memory Storage for Multi-Agent Systems
AGPL-3.0 ★ 159 -
Persistent file storage for AI agents: a hosted MCP server. Save files, get a link a human can open.
MIT -
pondgithub.com/tenequm/pondactive
Lossless storage and search for AI agent sessions, across every agentic client.
Apache-2.0 ★ 91 -
voidwalker-mcpgithub.com/mohi-devhub/voidwalkerupdated this year
Local MCP server for Voidwalker — streams browser storage, cookies, and DOM mutations to AI agents
npm MIT -
bedrock-mcp-agentgithub.com/seziCZ/bedrock-mcp-agentupdated this year
Serverless Bedrock LLM agent leveraging Lambda-hosted MCP servers for note management, utilizing S3-based vector storage and provisioned through Python CDK.
-
veyra-snippetsgithub.com/Aquariosan/veyra-snippetsupdated this year
Code snippet storage for AI agents. Read freely, write with Veyra commit mode.
MIT -
photo-organizer-mcpgithub.com/expertvagabond/photo-organizer-mcpupdated this year
MCP server for organizing Google Photos and Drive - AI agents can auto-organize your cloud storage
npm MIT -
Local MCP memory system for AI agents with durable filesystem storage, Redis-backed short-term context, and a keyboard-first Qt/QML GUI.
★ 2 -
Vectorless agent memory. HTML storage + grep retrieval. LongMemEval-S R@5 = 98.9%. No embedding, no vector DB.
MIT -
MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.
NOASSERTION ★ 10 -
Xiaomi Smart Storage (MINAS) WebDAV control toolkit — CLI, probe, local proxy, agent skill & MCP server (Apache-2.0)
Apache-2.0 ★ 9 -
Shared memory for AI agents over MCP: one agent contributes what it learned, another one finds it. Seven tools, PostgreSQL with pgvector, PII removal before storage.
MIT ★ 2 -
Official BlazingCDN MCP server — manage CDN resources, purge cache, query metrics, cloud storage and video CDN from AI agents
npm MIT -
@payaion/mcpactive
MCP server for Payaion — file uploads, storage folders, marketplace listings, and paid downloads for AI agents on Base mainnet (USDC).
npm MIT -
MCP server giving AI agents BNB Chain, opBNB and Greenfield tools for chain data, token safety, swaps and storage.
NOASSERTION ★ 35 -
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 -
Fast native C++ storage intelligence engine, disk analyzer, and app cache inspector (Zalo/Dev tools) for Windows, scripts, and AI agents.
MIT ★ 2 -
Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Cloud Storage and Video CDN
MIT ★ 2 -
A shared TODO/backlog MCP server with a web UI, agent claim/release tracking, and encrypted local storage.
npm MIT -
MCP server, A2A agent card and ARC-4 registry decoders for Ripar. 15 tools that read Algorand box storage and compose registry calls — usable from any MCP client.
-
Local-first persistent memory layer for AI agents. SQLite-backed, MCP-compatible, cross-agent. Privacy: secret-blocking writes, file-only storage.
MIT ★ 2 -
OS keychain secrets for AI coding agents, over MCP. Native vault storage (macOS Keychain, Linux Secret Service, Windows Credential Vault), policy-governed access, audit log — CLI + 44 MCP tools.
npm AGPL-3.0 ★ 5 -
Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.
Apache-2.0 ★ 569 -
mindgithub.com/Da7-Tech/mindupdated this year
Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offline storage. One Python file, zero dependencies.
MIT ★ 78 -
mcp-inbox-readerupdated this year
MCP Server that lets AI agents read your inBox notes from your own S3/WebDAV cloud storage. Local-first, zero server.
npm MIT -
MCP server for AI agents: optimize & convert images (WebP/AVIF/JPEG), QR codes, cited storage data and 18 dev utilities. Zero-auth.
MIT ★ 1 -
safari-devtools-mcpgithub.com/hayodev/safari-devtools-mcpupdated this year
Safari DevTools MCP — real browser debugging with network interception, DOM inspection, cookie/storage management, and CSS analysis for AI agents on macOS
npm MIT -
Retrieval platform for AI agents — 14 search providers, 12-step content extraction, dead URL recovery, site capture, and local corpus storage. One API.
pypi MIT -
Persistent multi-path memory for AI agents — vector + BM25 keyword + entity graph search with RRF fusion, credential scrubbing, auto-consolidation, multi-backend storage (Qdrant + SQLite/Postgres)
npm MIT -
Local-first, offline-capable Agent memory & knowledge service. REST + MCP dual-protocol, hybrid retrieval (vector + BM25/RRF), document/webpage RAG. No LLM required for storage & retrieval
Apache-2.0 ★ 5 -
formbot-mcpgithub.com/marilynceo/formbot-mcpupdated this year
Online form creation and management for AI agents u2014 build Typeform-style surveys, collect responses with pagination, update forms with logic jumps, track completion analytics, and generate shareable links. Self-contained SQLite storage, zero external API dependencies.
-
a-mem-mcp-servergithub.com/tobs-code/a-mem-mcp-serverupdated this year
A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten
NOASSERTION ★ 10 -
Publish and share the small web tools your AI agents build, as easily as a Google Doc. Google sign-in, permissions, storage and gVisor sandboxing built in. Self-hosted.
npm AGPL-3.0 ★ 30 -
AI-optimized stash storage — dynamic RAG for agents. Store, search, and retrieve docs, code, and data on demand via MCP or REST API.
MIT ★ 1 -
The #1 Offline Photo, Video & Web Performance Model Context Protocol (MCP) Server for AI Agents (Claude Desktop, Cursor, Antigravity). Bundles 29 native tools with zero cloud storage.
npm MIT -
codemindgithub.com/twly7ho2/codemindupdated this year
CodeMind is an AI agent memory system that maintains persistent, real-time context over complex codebases. By utilizing symbol graph storage, AST chunking, and intelligent file scanning, CodeMind enables LLMs to reason about relationships across large code structures without losing track of dependencies
★ 1 -
Give any AI agent long-term memory from your Obsidian vault. Self-hosted MCP server + REST API on Cloudflare Workers: R2 storage, D1 full-text and Vectorize semantic search, safe agent writes.
MIT -
GrafMCPgithub.com/SecCodeSmith/GrafMCPupdated this year
A local MCP server that gives code agents (Claude Code, Antigravity, and any other MCP client) a shared, persistent graph memory, backed by Kuzu — an embedded database purpose-built for graph storage and graph search — plus a live web dashboard showing the memory graph and an activity log.
MIT