# Mountable

> A filesystem your agents can mount anywhere.

## Docs

- [Overview](/docs): What Mountable is and how a sandbox gets a filesystem without holding your keys.
- [Quickstart](/docs/quickstart): Install the CLI, sign in, create a filesystem, and mount it.
- [Mount from a sandbox](/docs/sandbox): Your backend creates a mount session with an API key and hands the sandbox a one-time ticket.
- [Agents](/docs/agents): The two-sided agent workflow: a backend creates a ticket with an API key, a sandbox mounts with it; JSON output, exit codes, error codes and safe retries.
- [Permissions](/docs/permissions): Whole-filesystem grants, read-only and read-write, and what revokes a session.
- [Billing](/docs/billing): A card before your first filesystem, monthly invoices in EUR or USD, and what happens if one goes unpaid.
- [CLI reference](/docs/cli): Installing the CLI; every mountable command and flag; --json output, exit codes, retries; MOUNTABLE_API_KEY, MOUNTABLE_ORG and the other environment variables.
- [MCP](/docs/mcp): Run mountable mcp as an MCP server for Claude Code, Claude Desktop or Cursor; its seven tools; mounting stays a local command.
- [Skill](/docs/skill): Install the Mountable skill so coding agents know the workflow, the error codes and the retry rules.
- [API reference](/docs/api): Where to find the Mountable API's OpenAPI document and how to authenticate.
- [Contract and limits](/docs/limits): What a mount guarantees on one machine and across machines, what is not supported, durability, the service stage, quotas, known issues and platforms.

## Optional

- [Full docs](/llms-full.txt): every page above in one file