Docs / Connecting to Your AI Tools

Connecting to Your AI Tools

Storing items is half the job. This is how your library plugs into the tools you actually work in. There are three ways to reach it — pick per situation:

Live over MCP — the agent reaches into your library on demand. Recommended for most people.
Slash commands via pull — install skills as typed / commands, or keep local copies. Optional.
Send to an AI — one click opens a prompt in Claude/ChatGPT/Perplexity.

1. Connect over MCP (recommended)

MCP (Model Context Protocol) is the open standard AI tools use to reach outside sources. Connect once per tool and your agent can search your library, read your rules and docs, and use your prompts as slash commands — always your latest version.

Setup (about two minutes per tool):

Create a token. In the app, Settings → API tokens → New token. Copy it — you see it once.
Open the Connect page and pick your tool. It generates the exact config for your operating system.
Paste the config into your tool's config file, drop in your token, and fully restart the tool (closing the window usually isn't enough).

Supported tools: Claude Desktop, Cursor, VS Code, Claude Code, Cline, Windsurf, Codex. The Connect page has the precise config-file location and steps for each.

Windows: the generated config wraps the launcher in cmd /c on purpose — Windows can't spawn npx directly (you'd get a silent connection failure). Use the config exactly as Connect gives it to you.

Shortcut — let your AI do it. If you use a coding agent (Cursor, Claude Code, VS Code, Cline, Windsurf, Codex), you don't have to hand-edit anything: give it the config and ask it to set up the MCP server. You'll usually want it at the user level (available in every project); most tools also do project level (just this repo) — tell your AI which.

Once connected, your prompts appear as /aistoragedepot:… slash commands, and your skills, rules, and docs are things the agent reads when you ask.

2. Slash commands and the `pull` command

You don't need this for prompts — connecting over MCP already makes your prompts into slash commands. pull is for two specific wants:

Type a skill as a command. Over MCP a skill is something the agent reads; pull installs it as a typed /aistoragedepot:… command.
Keep local copies that work with no token and offline.

The Connect page gives you a copy-paste command. It defaults to skills only:

npx -y @aistoragedepot/mcp pull --token=YOUR_TOKEN --workspaces=all --to=all --types=skill

Flags:

--token= — your API token. No space after the =.
--workspaces=all — include team/company libraries, not just personal.
--to=all — write for every installed tool.
--types=skill — pull skills only (the default we recommend). Add --types=all to also keep local copies of prompts.

Why the default is skills-only

If you pull prompts while also connected over MCP, each prompt shows up twice in your slash menu — once from the pull ((user)) and once live from MCP ((MCP)). They do the same job; the (MCP) one is always current. Pulling skills only avoids the duplicate, because a skill can only ever become a slash command via pull. If you want offline prompts too, add --types=all and just prefer the (MCP) copy when you see both.

3. Send to an AI

Any prompt has a Send to AI button that opens it in your preferred assistant (Claude, ChatGPT, or Perplexity), prefilled and ready. A dropdown adds one-click actions — polish the prompt, or turn a one-off into a reusable [bracketed] template. Set your default assistant in Settings.

Troubleshooting connections

npm error … ENOENT … _cacache — a corrupted npm cache, not your token or our package. Run npm cache clean --force, then retry the command.
Connected but nothing shows up — fully quit and reopen the tool (system-tray quit, or end the process). Closing the window often isn't enough.
Windows: silent failure — make sure the config uses cmd /c (not a bare npx). Regenerate it from the Connect page if unsure.
Revoked or wrong token — the connection stops working the instant a token is revoked. Create a fresh one in Settings → API tokens.