FetchPan
Server Details
Download URLs for Baidu, Quark, Rapidgator files and X, Douyin, Xiaohongshu, Instagram posts.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Most tools target distinct actions, but `download` and `start_download` both fetch a link and both handle share pick_required, differing mainly in sync vs async behavior; `get_download_link` also returns a URL for a job. Descriptions clarify the intended flow, but an agent can still misselect among these three.
All names use snake_case and mostly follow verb_noun (check_link, get_job, list_files). A few are less patterned (`download`, `download_social`, `start_download`), but the convention is readable and consistent overall.
11 tools is well within the 3-15 range and each maps to a meaningful part of the download workflow: validation, listing, fetching, job polling, account, and payment.
The surface covers the core lifecycle: check link/site, list files, start/download, poll job, get link, social downloads, account, packages, and payment link. Minor gaps exist around payment/order status and job management (e.g., cancel/list jobs), but core workflows are covered.
Available Tools
11 toolscheck_linkCheck a linkARead-onlyInspect
Is this link from a site FetchPan supports, and is that site working right now?
Does not use any quota. Call it before `download` when you are not sure.Inputs: url (required). Returns: object
create_payment_linkCreate a payment linkAInspect
Create a payment page for a traffic pack and return its URL. Give the URL to the user: only a person can pay it. Nothing is charged by calling this.
Inputs: package_code (required). Returns: object
downloadDownload a linkAInspect
Fetch a link and return a download URL, in one call. A Quark or PikPak share with folders or several
files answers status "pick_required" with a share_id and its files: call again with share_id and the
file_id of one file (open folders with list_files).
Waits up to `wait_seconds` for the file to be ready. If it is not ready yet, the result has
status "running" and a `job_id`: call `get_job`, then `get_download_link`.
Social media posts (X, Douyin, Xiaohongshu, Instagram): use `download_social` (a link given here is answered
as it would answer).Inputs: url (required), tier, file_id, password, +2 more. Returns: object
download_socialDownload a social media postAInspect
Get the video and photos of a social media post (X/Twitter, Douyin, Xiaohongshu/RedNote, Instagram) as
direct download URLs, in one call. Use it whenever the user shares such a link or asks about a post's video or
pictures: to save, watch, transcribe, describe or analyze them. The files are small (short videos, photos):
fetch the URLs and work on them directly (at most 3 at once; resume a cut download with an HTTP Range request).
A post with several photos or videos returns them all (up to 20, items) and counts as one free download;
social posts have their own free allowance (20 a day).
Files not ready within `wait_seconds` have status "running" and a `job_id`: call `get_job`, then
`get_download_link`.Inputs: url (required), tier, wait_seconds. Returns: object
get_accountGet the accountBRead-onlyInspect
The account behind the token: email, traffic balance in bytes, free files per day, and the last downloads.
Inputs: no named parameters. Returns: object
get_download_linkGet the download URLAIdempotentInspect
Get the download URL of a succeeded job. A free link uses one of the account's free files for the day; a fast link uses traffic from the account balance. Asking again for the same job and tier returns the same link.
Inputs: job_id (required), tier. Returns: object
get_jobGet a jobARead-onlyInspect
Status of a job: queued, running, succeeded or failed.
When it has succeeded it also says whether a free download is possible (`free`) and what a
fast one would cost in traffic bytes (`fast`).Inputs: job_id (required). Returns: object
list_filesList the files in a shareARead-onlyInspect
What is inside a Quark or PikPak share: its folders and files, with sizes. Lists only: downloads nothing and uses no free file.
`download` of a share with folders or several files answers "pick_required" with a `share_id` and the top
of the share. Open a folder with that `share_id` and the folder's id as `folder_id` (or start here with
`url`). Then call `download` with the url, the `share_id` and the `file_id` of ONE file.Inputs: url, page, password, share_id, +1 more. Returns: object
list_packagesList traffic packsBRead-onlyInspect
Traffic packs that can be bought (code, size in bytes, price in USDT).
Inputs: no named parameters. Returns: result
list_supported_sitesList supported sitesARead-onlyInspect
List the sites FetchPan can download from, with live status (working, slow, down).
`main_sites` are the big ones (Baidu, Quark, Rapidgator ...). `file_hosts` are the other
file hosts. `free` tells whether a free download is possible there or only a paid one.
`social_sites` are the social media sites whose posts `download_social` fetches.Inputs: no named parameters. Returns: object
start_downloadStart a download jobAInspect
Start fetching a link (or one file of a share, with share_id and file_id). Returns a job id; poll it
with get_job. Uses no free file yet. A Quark or PikPak share with folders or several files starts no
job: it answers status "pick_required" with its files, as download does.
Inputs: url (required), file_id, password, share_id. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Instagram, TikTok, YouTube and other social media links to direct media download URLs.
Parse short-video share links into watermark-free direct URLs via MCP for AI assistants.
Parse short-video share links into watermark-free direct URLs via MCP for AI assistants.
Douyin (抖音, Chinese TikTok) video search, video details, comments, creators and shop products.
Related MCP Servers
- AlicenseAqualityDmaintenanceAnalyzes images, audio, and video using Google's Gemini AI, with support for downloading videos from URLs such as Bilibili and YouTube.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables turning a Douyin share link into a local watermark-free mp4 file, or a batch of jpg files when the post is a photo gallery. Also supports inspecting a link's title, author, duration and media type before deciding to download.MIT
- AlicenseAqualityCmaintenanceTurns TikTok, Instagram, X/Twitter and Facebook post URLs into video download links plus metadata (title, author, duration, thumbnail), so AI agents can fetch social videos in one tool call.243 npmMIT
- AlicenseAqualityDmaintenanceExtracts watermark-free videos and images from Douyin (TikTok) and Xiaohongshu (RedNote) share links, with optional AI-powered video transcription support.424 PyPI27Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.