Fast.io

by MediaFire

292 downloads

Not rated

GitHub

About

AI-first file sharing and collaboration. 251 MCP tools give agents a full workspace: file storage, branded shares, comments, workflows, and built-in RAG. Free tier includes 50GB storage and 5,000 monthly credits, no credit card. Built by the team behind MediaFire. Works with Clau

Details

Author: MediaFire
Downloads: 292
Categories: File Management, Communication, Knowledge Base, Automation, Developer Tools

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Fast.io

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

From the repository

Connect to the Fast.io MCP server by configuring a Streamable HTTP endpoint in your MCP client using the URL https://mcp.fast.io/mcp.

`auth`

Auth & sessions: signin, signup, signout, 2FA, PKCE, API keys, OAuth sessions. Call action='describe' for the full action/param reference. Destructive: api-key-delete, oauth-revoke, oauth-revoke-all.

`upload`

File upload: stream-upload (one-shot — auto-finalizes, no filesize needed), chunked (create-session → chunk → finalize, for exact-known-size or files split across blobs), web URL import, and batch (many small files). Call action='describe' for the full action/param reference. Side effects: finalize/stream/stream-upload/web-import/batch create files and consume storage credits. Same-name uploads to a folder OVERWRITE the existing node in place (preserved as a recoverable version). BYTES → SERVER: the **DEFAULT for every file/binary is the `POST /blob` sidecar** — a plain HTTP POST outside the MCP pipe (the create-session/blob-info response hands you a ready-to-run curl command) that returns a `blob_id` you pass to stream-upload/chunk/batch: no base64, no MCP size limit, up to 100 MB. Use `content_base64` (inline base64, capped a few MB by the MCP transport) ONLY when your client cannot make the POST /blob call. `content` is small text only (verbatim UTF-8). UPLOAD STRATEGY (read top-to-bottom, pick the FIRST that matches): (1) Have a URL? → `web-import` (single call). (2) DEFAULT for a file/binary → `POST /blob`, then `stream-upload` with `blob_id` (single call, auto-finalizes, NO filesize required). Unknown/generated size and no way to reach /blob → `stream-upload` with `content_base64`. (3) Known exact byte count, or a large file split across blobs → `create-session` + `chunk`(`blob_id`) + `finalize`. **filesize must match the bytes you actually upload — mismatch causes finalize to fail with code 10522 and you must cancel the session.** (4) Multiple small files (≤4 MB each, ≤200 total) into one folder? → `batch`. Prefer `blob_id` (POST /blob) for every file/binary upload; fall back to `content_base64` only when you cannot reach /blob. Do NOT guess `filesize` for generated content — use `stream-upload`. max_size is a hard ceiling that aborts mid-transfer — always overestimate or omit (server uses plan limit).

`user`

User profile, contacts, invitations, and assets. Call action='describe' for the full action/param reference. Destructive: close.

`org`

Organization management: CRUD, billing, members, invitations, ownership transfer, assets, discovery. Call action='describe' for the full action/param reference. Destructive: close (permanently deletes org and all data).

`workspace`

Workspace management: list/details/update/delete, archive, members, notes, quickshares, share import, import toggle. NOTE: metadata actions MOVED — templates + AI extraction → `metadata` tool; node-level metadata → `storage` tool. The `metadata-*` actions here are deprecated one-release execute-and-warn shims, removed next release. Call action='describe' for the full action/param reference. Destructive: delete (workspace + all files). ⚠️ intelligence COSTS CREDITS (10/page) — only enable on explicit user request; toggle is rate-limited. Verbosity (detail param): list/available/members/list-shares default to terse (compact rows). details defaults to full (drill-down). Pass an explicit detail='standard'|'full' to override.

`share`

Share management: create/update/delete, archive, password auth, members, autotitle. NOTE: quickshare-create is DEPRECATED (returns error 10756) — use the `fileshare` tool's `create` action for durable single-file shares. Call action='describe' for the full action/param reference. Destructive: delete (permanent). Side effects: autotitle AI-generates + applies a title/description (consumes credits, mutates share metadata). ⚠️ intelligence on create COSTS CREDITS (10/page) — default false unless user explicitly requests RAG. Verbosity (detail param): list/available/members default to terse (compact rows). public-details defaults to standard. details defaults to full (drill-down). Pass an explicit detail='terse'|'standard'|'full' to override.

`fileshare`

File Shares: durable single-file share links. create/list/details/update/delete, per-user grants (grant-list/grant-add/grant-revoke incl. grant-by-email with pending invites), and direct read/preview/version URLs. Call action='describe' for the full action/param reference. Bound to ONE workspace file (immutable binding); deletion NEVER touches the bound file. Recipient 404 is UNIFORM — not-found / revoked / expired are indistinguishable by design (do not speculate). Passwords are supplied via the x-ve-password header (the `password` input) — never placed in URLs. Destructive: delete (removes the share, not the file). Reversible access change: grant-revoke (re-grantable). download-url / preview-url / version-download-url return a DIRECT API URL — gated shares require Authorization and/or x-ve-password HEADERS on the GET (the password is never embedded in the URL).

`room`

Coordination Rooms — a private, workspace-scoped space for agentic teams (agents + humans) to join, post messages, track each other's status/presence, and hand off files. Create is idempotent per (workspace, topic_slug). Presence is refreshed by ANY room call; liveness ≠ progress. Hand files off via the `upload` tool into the room's storage. Call action='describe' for the full protocol + action/param reference.

`storage`

Files & folders on workspaces/shares: list, search, copy, move, delete, rename, trash, transfer, versions, locks, previews, and per-node metadata (get/set/delete/extract/versions). Call action='describe' for the full action/param reference. Destructive: purge (irreversible). delete moves to trash. metadata-delete removes metadata keys. Verbosity (detail param): list/recent/search/trash-list default to terse (compact rows). details defaults to full (drill-down). Pass an explicit detail='standard'|'full' to override.

`metadata`

AI metadata templates & extraction (the unstructured-data automation pipeline): template CRUD/clone, assign/resolve, the AI pipeline (eligible -> preview-match -> suggest-fields -> template-create -> nodes-add/-list -> auto-match -> extract-all), saved views, and lexical metadata search. Call action='describe' for the full action/param reference. Node-level metadata (get/set/delete/extract on a single file) lives on the `storage` tool. Destructive: template-delete, view-delete, nodes-remove. AI/credit side-effects: preview-match, suggest-fields, auto-match, extract-all (each spends AI credits).

`find`

Unified search across a workspace or share — ONE query, results GROUPED BY TYPE into buckets (files, metadata [workspace only], comments), each independently paginated and health-reported. Call action='describe' for the full action/param reference. This is the grouped SUPERSET; for a single result type prefer the narrower tools: `storage action=search` (files only), `metadata action=search` (lexical metadata fields only). The code-mode `search` tool searches the API endpoint catalog, not your content.

`download`

Download URLs for files (file-url), folder ZIPs (zip-url), and quickshare links (quickshare-details — DEPRECATED, use the `fileshare` tool's `create` action for new shares). Consumes bandwidth credits. Call action='describe' for the full action/param reference.

`ai`

Ripley — the MCP delegation surface over Fastio's RAG agent. Ripley is read-only for storage CONTENT: it answers natural-language questions about workspace/share files & folders (with citations) and never creates/edits/deletes your files — for content writes, call the primitive MCP tools directly. It DOES create/manage chat threads (chat-create/chat-update/chat-delete/message-send) and can generate shares (share-generate). Prefer Ripley over issuing many primitive reads: ask one NL question and let the server-side agent search + synthesize. Quick start: action='ask' (question + profile) → returns {answer_text, citations, chat_id, message_id, web_url}; action='status' for an engineered workspace-status summary. Lower-level chat/message actions remain for multi-turn control. Call action='describe' for the full action/param reference. Destructive: chat-delete. Side effects: ask/status/chat-create/message-send consume credits; chat-cancel terminates an in-progress message (partial tokens billed; idempotent). Verbosity (detail param): chat-list/message-list default to terse (compact rows). chat-details/message-details default to full (drill-down). Pass an explicit detail='standard'|'full' to override (best-effort: chat/message/activity endpoints may not yet honor detail server-side).

`comment`

Comments on files: add/list/delete/react, anchor to image regions, A/V timestamps, PDF pages, or text selections. Call action='describe' for the full action/param reference. Destructive: delete, bulk-delete. Verbosity (detail param): list/list-all default to terse (compact rows). details defaults to full (drill-down). Pass an explicit detail='standard'|'full' to override (best-effort — may be a silent no-op until the comments API honors output=; see describe).

`event`

Event log and activity monitoring for workspaces and shares. Also surfaces the per-member DASHBOARD — a 'what's on your plate' feed of cards (@mentions, file activity) for one workspace, with view-only dismiss/snooze and a best-effort AI overlay. Call action='describe' for the full action/param reference. Verbosity (detail param): search/activity-list/activity-poll default to terse (compact rows). summarize defaults to standard (envelope around the AI summary). details defaults to full (drill-down). Pass an explicit detail='terse'|'standard'|'full' to override (best-effort on summarize/activity-list/activity-poll — only search/details honor output=; see describe).

`member`

Workspace/share member management: list, add, remove, update, transfer ownership, join, leave. Call action='describe' for the full action/param reference. Destructive: remove.

`invitation`

Workspace/share invitations: list, filter by state, update, revoke. Call action='describe' for the full action/param reference. Destructive: delete.

`asset`

Brand asset management (logos, banners, profile photos) on org/workspace/share/user. Upload, delete, list, read. Call action='describe' for the full action/param reference. Destructive: delete.

`how-to`

Built-in product help — ask a natural-language "how do I…" question about Fastio and get a grounded, product-aware answer (or a short clarifying question) back in one call. EXPLAIN-ONLY / ADVISORY: it returns GUIDANCE TEXT and performs NO platform action (it will not create shares, move files, or change anything) — read the guidance, then act with the other tools. Answers are grounded in Fastio's own how-to knowledge AND phrased in terms of these MCP tools — they name the concrete `<tool> action="…"` calls to make — so prefer this over guessing endpoints or burning exploratory calls. For Q&A over YOUR uploaded files (RAG) use the `ai` tool instead — `how-to` answers questions about Fastio ITSELF. FREE and requires only an authenticated user (no org, no plan gate, no billing). Call action='describe' for the full action/param reference.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "fast.io": {
            "fast-io": {
                "url": "https://mcp.fast.io/mcp"
            }
        }
    }
}

McpServers

{
    "fast-io": {
        "url": "https://mcp.fast.io/mcp"
    }
}

A command-line interface for theFast.iocloud storage platform. Built in Rust for speed, reliability, and cross-platform support.

curl -fsSL https://raw.githubusercontent.com/MediaFire/fastio_cli/main/install.sh | sh

Pre-built binaries for macOS, Linux, and Windows are available on the Releasespage.

# Log in (opens browser for PKCE authentication) fastio auth login # Or log in with email/password fastio auth login --email user@example.com --password * # Check auth status fastio auth status # List organizations fastio org list # Create a workspace fastio workspace create --org <org_id> "My Workspace" # Upload a file fastio upload file --workspace <workspace_id> ./document.pdf # Download a file fastio download file --workspace <workspace_id> <node_id> --output ./downloads/ # Ask the AI about your workspace fastio ai chat --workspace <workspace_id> "What files do I have?" # Log out fastio auth logout

The CLI supports multiple authentication methods, checked in this order:
- --tokenflag (one-off bearer token)
- FASTIO_TOKENenvironment variable
- FASTIO_API_KEYenvironment variable
- Stored credentials from--profile(or default profile)

Opens your browser for secure OAuth authentication. Tokens are stored locally and automatically refreshed.
fastio auth login --email user@example.com --password

# Create an API key fastio auth api-key create --name "CI pipeline" # Use it for subsequent commands export FASTIO_API_KEY=your-key-here fastio org list

# Check 2FA status fastio auth 2fa status # Enable 2FA fastio auth 2fa setup --channel totp # Verify 2FA code after login fastio auth 2fa verify <code>

All commands support--formatto control output:

# Table format (default for terminals) fastio org list # Markdown format (default when piped; optimized for LLM consumers) fastio org list | cat # JSON format (for scripts that parse structured output) fastio org list --format json # CSV format fastio org list --format csv # Explicit markdown (GitHub-flavored, byte-equivalent to the server's ?output=markdown) fastio org list --format markdown # --format md is accepted as an alias # Filter specific fields fastio org list --fields name,id,description

Markdown replaced JSON as the non-TTY default on 2026-04-15. The rendered output isbyte-equivalentto what the Fast.io API produces for?output=markdown: aResult: success|failurepreamble, object-valued errors promoted to a leading# Errorsection, and each remaining top-level key as an H1 section in insertion order. Arrays of associative records render as GFM pipe tables (union of keys in insertion order); scalar lists render as bulleted lists.

Note on escaping: bullet values and heading text arenotescaped — the renderer takes a light-touch approach matching the server contract, because the output is meant to be read or rendered, not embedded into other markdown.Downstream consumers that render the output to HTML MUST sanitize.*The renderer does strip Unicode bidi, zero-width, and C0/C1 control characters as a Trojan-Source defense; table cells escape|,\,``, and newlines; HTML-like cell content is wrapped in inline-code fences.

Pipelines that need machine-parseable output can opt back in with--format json.

The CLI includes a built-inModel Context Protocolserver for AI agent integration. Run it as a subprocess:

This exposes the CLI's action-routed tool surface as MCP tools over stdio, compatible with Claude Desktop, VS Code, and other MCP-compatible clients. A few high-risk or local-byte operations (sign send/void, fileshare upload write-back and ws-token) remain CLI-only, and the sign tool appears only when E-Sign is enabled.

Tool responses are rendered as GitHub-flavored Markdown by default, byte-equivalent to the Fast.io API's?output=markdownoutput. Markdown is substantially more token-efficient for LLMs than pretty-printed JSON, so the MCP server uses it for every read and status response.

{ "mcpServers": { "fastio": { "command": "fastio", "args": ["mcp"] } } }

fastio mcp --tools auth,org,workspace,files,upload,download

Authentication and backend follow the standard CLI rules: the server honors the global--api-base,--token, and--profileflags (and theFASTIO_TOKEN/FASTIO_API_KEYenv vars), so you can point it at a non-default backend or profile — e.g.fastio --profile staging mcporfastio --api-base https://api.example/current mcp.


Generate shell completions for your shell:
# Bash fastio completions bash > ~/.bash_completion.d/fastio # Zsh fastio completions zsh > ~/.zfunc/_fastio # Fish fastio completions fish > ~/.config/fish/completions/fastio.fish # PowerShell fastio completions powershell > _fastio.ps1

Manage multiple accounts with named profiles:
# Set up a profile interactively fastio configure init # Log in to a specific profile fastio auth login --profile work # Use a profile for a command fastio org list --profile work # Set default profile fastio configure set-default work # List all profiles fastio configure list

Configuration files are stored in~/.fastio/`:

Apache License 2.0. SeeLICENSEfor details.

MCP server for monitoring remote file sources, detecting new files, and extracting content. Works with any storage backend via rclone (70+ providers) or custom commands.

The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI, zero dependencies.

MCP server that moves files between your filesystem and cloud storage.

Manage files and downloads on Synology NAS devices using an AI assistant.

Logs file edits, decisions, and commands so agents stay in sync, avoid conflicts, and pick up where others left off.

Persistent memory for AI agents. Store and retrieve files via 14 MCP tools with OAuth 2.0 auth. Free 10GB tier.

Quickly integrate with Tencent Cloud Storage (COS) and Data Processing (CI) capabilities powered

An MCP server for managing files and buckets on AWS S3. Requires AWS credentials for authentication.

Publish HTML, Markdown, KV, JSON, files to brewpage.app from AI assistants.

An MCP server for interacting with Dropbox files and services.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

auth

upload

user

org

workspace

share

fileshare

room

storage

metadata

find

download

ai

comment

event

member

invitation

asset

how-to

Claude Desktop / Cursor

McpServers

Install

More like this

Aws Kb Retrieval Server

Memory

Slack

Context 7

Activepieces

MaxKB

`auth`

`upload`

`user`

`org`

`workspace`

`share`

`fileshare`

`room`

`storage`

`metadata`

`find`

`download`

`ai`

`comment`

`event`

`member`

`invitation`

`asset`

`how-to`