MCP tool reference · #481 of 563 by publishers
get_file
Exposed by 8 servers from 8 publishers, read from the live servers by the Serverdex check; most of them sit in Media & Creative; 37.5% of them take a path parameter; the most-starred is FynePDF (1 stars).
get_file(path: string, file_id: string, …)Parameters
share = % of the 8 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| path | string | 37.5% | 100% | File path within the repo. |
| file_id | string | 25% | 100% | The file cuid (from list_files). Surface + workspace are derived from the file row, so no surface_slug arg is needed. |
| cookies | string | 12.5% | 0% | Semicolon-separated cookies to send to the target. |
| country_code | string | 12.5% | 0% | ISO 3166-1 alpha-2 country code (e.g. "fr", "us") to route the request through an IP in that country. Only takes effect when premium_proxy is True. |
| custom_google | boolean | 12.5% | 0% | Set to True if the url is a google domain in the following format: <subdomain>.google.<top-level-domain> (Example: translate.google.com, mail.google.com, www.go |
| depth | number | 12.5% | 0% | How many levels of the document tree to traverse (default 2). Lower values return less data. |
| device | string | 12.5% | 0% | desktop (default) or mobile. |
| file_key | string | 12.5% | 100% | The Figma file key (the segment after /file/ or /design/ in a Figma URL). |
| kind | string | 12.5% | 100% | — |
| premium_proxy | boolean | 12.5% | 0% | Whether to use a premium proxy for the request. Use it only if you are getting blocked by the website. |
| project_id | string | 12.5% | 100% | Hosting project UUID from create_project or list_projects. |
| reciter | string | 12.5% | 0% | For audio and timing: reciter id; defaults to the site's own |
Source: the input schema each server returns for get_file, aggregated over the 8 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with get_file
8 of 8 · 8 publishers · 8 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes get_file |
|---|---|---|---|---|---|---|
| 1 | FynePDFfynepdf · Documents & Knowledge | fynepdf | Documents & Knowledge | 1 | yes | A file's details and a fresh download link (valid 1 hour). |
| 2 | Novencenovence-ai · Content & Publishing | novence-ai | Content & Publishing | 1 | yes | Return metadata for one staged path (not file bytes). Use list_files to discover paths; use get_upload_url to replace content. Read-only. |
| 3 | Ctxvanshulgoyal101 · Developer Tools | vanshulgoyal101 | Developer Tools | 1 | yes | Return the full text of a single file in a repository, by path. Use after list_files or search_context to drill in. |
| 4 | Figmapipeworx-io · Media & Creative | pipeworx-io | Media & Creative | — | yes | Get a compact summary of a Figma design file by its file key: name, last modified time, version, editor type, role, thumbnail URL, and the list of top-level pages (id, name, type, child count). Use to understand the structure of a Figma design file without fetching the full node tree. |
| 5 | Read Quran Todayahmad-anbarje · Education & Reference | ahmad-anbarje | Education & Reference | — | yes | Links to download a surah's files: "text", the Arabic (optionally with a translation and the Tafsir al-Muyassar) as a .txt; "audio", its recording as an MP3 (leave out the surah for all of a reciter's); "timing", where each ayah and word of a recording starts and ends, as JSON; "font", the mushaf's fonts for the surah's pages (QCF v4, one a page) with the glyphs each ayah is written in; "data", fo |
| 6 | BotSpot: AI Trading, Backtests and Botslumiwealth · Finance | lumiwealth | Finance | — | yes | Returns one file from any saved strategy revision owned by the authenticated user, including an opaque editHandle for safe edits. Call list_files before reading optional files such as rules.json or helpers whose presence is unknown; read only paths returned for that revision. A known entrypoint such as main.py can be read directly. Missing optional Rules do not block diagnosis and do not require c |
| 7 | ScrapingBeescrapingbee · Search & Web | scrapingbee | Search & Web | — | yes | Download a file (PDF, image, CSV, …) from a URL through ScrapingBee and return it as an embedded resource. Scope: one URL per call, with the result returned into the conversation. This server has no batch, crawl, file-output or scheduling mode. Docs: https://www.scrapingbee.com/documentation/remote-mcp/ |
| 8 | Docktry-dock-ai · Media & Creative | try-dock-ai | Media & Creative | — | yes | Fetch metadata + a download URL for a single file by id. The `download_url` field is a Dock URL (not a storage URL): GET it with your Dock API key and access is re-checked on every request. Useful for an agent reading file contents server-side (HTTP GET the URL) or surfacing a download link in a reply. |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.