Files (S3) MCP Server

Organization file storage via S3-compatible storage for workflow data

The Files MCP server provides organization-scoped file storage. Files are organized by organization and workspace, and can be read, written, listed, and shared via presigned download URLs.

How It Works

Files live in platform-managed storage, strictly isolated per organization and workspace - a file belonging to one organization can never be accessed by another. Each file is addressed by a storage key returned when it is written; pass that key to the read, download-URL, and delete tools.

Setup

The Files server uses platform storage - there are no configuration fields and no keys to provide:

Go to Settings > MCP Servers > Add Server.
Select Files (S3).
Click Save.
Assign it to a workspace in Settings > Workspaces > Edit.

The organization and workspace context is applied automatically at runtime.

Tools

write_file

Write text or JSON content as a file.

Parameter	Type	Required	Description
`name`	string	Yes	File name (e.g., `report.csv`, `data.json`)
`content`	string	Yes	Text content to save (max 10MB)
`path`	string	No	Subfolder path within workspace (default: `uploads`)
`mime_type`	string	No	MIME type (auto-detected from extension if omitted)
`category`	string	No	Category tag (e.g., `backups`, `reports`)
`tags`	string	No	Comma-separated tags for organization

Returns the S3 key and a presigned download URL (valid for 1 hour).

write_binary

Write binary content (base64-encoded) as a file.

Parameter	Type	Required	Description
`name`	string	Yes	File name (e.g., `image.png`, `backup.zip`)
`base64_content`	string	Yes	Base64-encoded binary content (max 10MB)
`mime_type`	string	Yes	MIME type (e.g., `image/png`, `application/pdf`)
`path`	string	No	Subfolder path within workspace
`category`	string	No	Category tag
`tags`	string	No	Comma-separated tags

read_file

Read file content by S3 key. Text files return content directly; binary files return base64-encoded content.

Parameter	Type	Required	Description
`key`	string	Yes	S3 key of the file (from `write_file` or `list_files` response)

list_files

List files and folders in the workspace storage.

Parameter	Type	Required	Description
`path`	string	No	Subfolder path (empty for workspace root)
`limit`	number	No	Maximum files to return (default: 100)

delete_file

Delete a file from storage.

Parameter	Type	Required	Description
`key`	string	Yes	S3 key of the file to delete

get_download_url

Generate a presigned download URL for sharing.

Parameter	Type	Required	Description
`key`	string	Yes	S3 key of the file
`expires_in`	number	No	URL expiry in seconds (default: 3600, max: 86400)

get_file_info

Get file metadata without downloading the content.

Parameter	Type	Required	Description
`key`	string	Yes	S3 key of the file

Returns size, content type, category, tags, source workflow/execution IDs, and last modified date.

parse_text

Extract text content from a document stored in S3. Supports PDF, DOCX, PPTX, XLSX, ODT, ODP, ODS, and RTF. Useful for processing resumes, reports, and other office documents before passing to an AI agent.

Parameter	Type	Required	Description
`key`	string	Yes	S3 key of the file to parse
`max_length`	number	No	Max text length in characters (default: 100000). Truncates if exceeded.

Returns extracted text, file metadata, and a truncated flag.

Supported formats:

Format	Extensions	Description
PDF	`.pdf`	Text extraction (not OCR - works with text-based PDFs)
Word	`.docx`	Paragraphs, tables, lists
PowerPoint	`.pptx`	Slide text, notes
Excel	`.xlsx`	Cell values across sheets
OpenDocument	`.odt`, `.odp`, `.ods`	Open format equivalents
Rich Text	`.rtf`	Legacy rich text format

Example Workflows

Saving workflow output to file storage

Trigger - Webhook receives data
Agent - Process data and generate a CSV report
Action - MCP tool files:write_file with name report-{{trigger.data.date}}.csv
Action - MCP tool files:get_download_url to create a shareable link
Agent - Send the download link via Slack or Telegram

Resume screening from email attachment

Trigger - Cron or manual
Action - google-workspace:gmail_search for new candidate emails
Action - google-workspace:gmail_read to get attachment metadata
Action - google-workspace:gmail_get_attachment to download resume (base64)
Action - files:write_binary to store resume in S3
Action - files:parse_text to extract text from the PDF/DOCX
Agent - Score resume against job description using extracted text
Action - google-workspace:sheets_append to log result in tracking sheet

← Stocks SSH→