
AIStorageDepot
io.github.aistoragedepot-adminPublished by GitHub account aistoragedepot-adminv0.6.7Updated Oct 24, 2026
Prompt, rules, skills & docs library over MCP. No token = read-only sample of the public library.
The publisher's own server: Tigris MCP Server
Overview
Exposes an AIStorageDepot library of prompts, rules, docs and skills to MCP clients as prompts, resources and search tools.
- What you can do
- The server surfaces a stored AIStorageDepot library inside MCP-aware clients. Items marked with a slash in the app become MCP prompts whose bracketed fields appear as prompt arguments; every item (rules, docs, skills, MCP configs, prompts) is readable as a resource at aisd://item/ ; and the tools search_library(query) and get_item(id) let an agent find and fetch content programmatically. A separate pull command can sync the library into native slash-command files for Claude, Cursor, VS Code, Windsurf and Codex.
- When to use it
- Use it when you keep reusable prompts, coding rules, guidelines or skills in AIStorageDepot and want an assistant to pull them into context on demand, or to expose them as slash-commands in your editor. It is also a way to preview the public curated library without an account.
- Requirements
- Runs locally over stdio, typically via npx @aistoragedepot/mcp, so Node.js is needed. No account is required for anonymous sample mode; full access to your own and team libraries needs an API token in the AISD_TOKEN environment variable. AISD_BASE_URL can point at a self-hosted instance. Network access to the AIStorageDepot API is required.
Installation
In SourceWeft
- Open AIStorageDepot in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
@aistoragedepot/mcp
A Model Context Protocol server that exposes your AIStorageDepot library to any MCP-aware AI client — Claude Desktop, Cursor, Cline, Windsurf, and others.
Your stored content shows up where you actually work:
- Prompts → the items you mark with / in the app become MCP prompts (slash-commands) — any type, with each prompt's
[field]surfaced as a prompt argument you fill in. - Resources → every item (rules, docs, skills, MCP configs, prompts) is readable at
aisd://item/<id>, so an agent can pull "my coding rules" or "my project guidelines" into context on demand. - Tools →
search_library(query)andget_item(id)let an agent find and fetch anything in your library programmatically.
Try it with no account (sample mode)
AISD_TOKEN is optional. Run the server with no token and it serves a free, read-only
sample of the public curated library — a good way to see AIStorageDepot inside your editor
before signing up. Add a token later to switch to your own & team libraries. Add the server
with an empty env (or omit AISD_TOKEN):
Setup
👉 Easiest path: step-by-step instructions for each app (config-file locations and all) are at https://www.aistoragedepot.com/connect. The manual version:
- In AIStorageDepot, go to Settings → API tokens and create a token (free for individuals). Copy it.
- Add the server to your MCP client's config. Example (Claude Desktop /
claude_desktop_config.json, Cursor~/.cursor/mcp.json, etc.):
- Restart the client. The items you marked / appear as slash-commands; everything is available as
resources; and the
search_library/get_itemtools are ready.
Configuration
Slash-commands (pull)
Not every client turns MCP prompts into / slash-commands (some only use the tools). To get
your library as native slash-commands, sync it to command files — for every AI tool you
use, not just Claude:
Tools that aren't installed are skipped automatically. Each tool gets its own dialect
(frontmatter, argument hints, $ARGUMENTS where supported). Skills run as-is.
Prompts take input: their [fields] show as an argument hint, and whatever you type
after the command fills them —
— with the AI asking for any value you left out.
Re-runs are safe: each target only clears its own files (claude: its namespaced folder;
the others: only files with the aisd- prefix — your own commands are never touched).
Notes
- Read-only in v0.1 (it surfaces and fetches your content; it doesn't write back).
- The library snapshot is cached for ~30s, so a burst of calls hits the API once.
- Revoke a token any time in Settings → API tokens; the server loses access immediately.
Local development
Source: README.md at commit c08f56e
Tools
0Version history
1- v0.6.7LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Storage integrations
Tigris MCP Server
dev.storageOfficial publisher
Remote MCP endpoint that connects AI assistants to Tigris for bucket and object management in cloud object storage.
Kinnovis Self-Storage
ai.b77Official publisher
Lets an assistant manage Kinnovis self-storage tariffs from chat.
File Storage
ai.b77Official publisher
Remote MCP server that lets an assistant upload files from a chat and return public CDN links for them.

Bulk File Downloader — URL Lists to Storage, Links & SHA-256
Published by GitHub account kriton-dev
Bulk File Downloader — URL Lists to Storage, Links & SHA-256's hosted MCP server; credential required; Streamable HTTP.

SSH Host Storage & Remote Exec
Published by GitHub account xlbbb-cn
Local stdio MCP server that stores SSH hosts with encrypted credentials and lets an assistant run remote commands, interactive prompts and multi-step playbooks.