Compatible with every major AI agent and IDE
What is the FileStack MCP Server?
Connect your Filestack account to any AI agent to handle complex file workflows, from cloud uploads to advanced AI content analysis, through simple commands.
What you can do
- Smart Uploads — Upload files directly from any public URL to your Filestack S3 storage using
upload_from_url. - AI Intelligence — Automatically extract text from documents (
get_ocr), detect objects and features in images (get_image_tags), and check for unsafe content (get_sfw_status). - Image Transformations — Generate optimized CDN URLs for resizing, blurring, or filtering images using
generate_transform_urlwithout manual editing. - Video Processing — Initiate and monitor asynchronous video transcoding jobs (
start_video_transcode) to convert files into web-ready formats like MP4 or HLS. - Metadata Inspection — Retrieve deep technical details including dimensions, mime types, and file sizes with
get_metadata.
How it works
- Subscribe to this server
- Enter your Filestack API Key (and optional Policy/Signature for security)
- Start processing assets directly from Claude, Cursor, or any MCP client
Who is this for?
- Developers — Automate asset pipelines and generate transformation URLs directly from the code editor.
- Content Moderators — Use AI to automatically flag unsafe images or tag visual assets at scale.
- Data Engineers — Extract structured text from scanned documents and images using OCR for downstream processing.
Built-in capabilities (8)
g., resize=width:400). Does not execute the request, just returns the URL. Generate a Filestack transformation URL
Detect objects and features in an image
Get metadata for a Filestack file
Extract printed or handwritten text (OCR)
Detect unsafe content (Safe for Work)
Poll status of a video transcoding job
Returns a UUID that must be used to poll for status. Start asynchronous video/audio transcoding
Upload a file to Filestack from a public URL
Why Cursor?
Cursor's Agent mode turns FileStack into an in-editor superpower. Ask Cursor to generate code using live data from FileStack and it fetches, processes, and writes. all in a single agentic loop. 8 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
FileStack in Cursor
FileStack and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect FileStack to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for FileStack in Cursor
The FileStack MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 8 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
FileStack for Cursor
Every tool call from Cursor to the FileStack MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I extract text from a scanned document or image?
Use the get_ocr tool with the file handle. The AI will perform Optical Character Recognition and return the extracted text along with its coordinates.
Is there a way to check if an uploaded image contains adult or unsafe content?
Yes, the get_sfw_status tool uses Filestack Intelligence to analyze the image and return a safety score, helping you moderate content automatically.
Can I resize an image without actually downloading and re-uploading it?
Absolutely. Use generate_transform_url to create a specific CDN URL with tasks like resize=width:400. This allows the Filestack CDN to handle the transformation on the fly.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
LeadSquared
10 toolsManage leads, sales activities, and opportunities via the LeadSquared CRM API.

Elemeno
10 toolsEquip your AI agent to manage content collections, track singletons, and monitor items via the Elemeno CMS API.

imgix (Real-time Image Processing)
10 toolsOptimize and transform images via imgix — manage CDN sources, purge assets, and monitor origin connections.

TestMu AI (formerly LambdaTest)
10 toolsManage cross-browser testing via TestMu AI — audit automation builds, inspect test sessions, and retrieve visual logs.
