ZBS Index What actually exists in applied AI, with the source next to it

mcp server

TweekIT MCP Server

Normalize and convert more than 400 file types via TweekIT's hosted MCP streamable HTTP endpoint.

Description as published by the maintainer. Source

  • version 1.6.1
  • active

active — Most recent push to the repository was 2026-07-03.

What this server can do

5 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

convert(x1, x2, y1, y2, blob, page, alpha, inext, width, apiKey, height, outfmt, bgColor, apiSecret, noRasterize)
Convert an uploaded document payload with TweekIT. The file must already be base64 encoded (see `blob`). The conversion can be resized and cropped by providing optional geometry parameters. For raster outputs, set `alpha`/`bgColor` to control transparency handling. Args: inext: Source file extension such as `pdf`, `docx`, or `png`. outfmt: Desired output format (`Fmt` in the API body). blob: Base64 encoded document payload (`DocData`). apiKey: TweekIT API key (`ApiKey` header). Falls back to `TWEEKIT_API_KEY` env var. apiSecret: TweekIT API secret (`ApiSecret` header). Falls back to `TWEEKIT_API_SECRET` env var. noRasterize: Forwarded to TweekIT to skip rasterization when possible. width: Optional pixel width to request in the output. height: Optional pixel height to request in the output. x1: Left crop coordinate in source pixels. y1: Top crop coordinate in source pixels. x2: Right crop coordinate in source pixels. y2: Bottom crop coordinate in source pixels. page: Page number to extract for multipage inputs. alpha: Whether the output should preserve alpha transparency. bgColor: Background color to composite behind transparent pixels. Returns: A FastMCP `Image` or `File` payload, or an error description. Required: inext, outfmt, blob.
convert_url(x1, x2, y1, y2, url, page, alpha, inext, width, apiKey, height, outfmt, bgColor, apiSecret, noRasterize, fetchHeaders)
Download a remote file and convert it with TweekIT in one step. This helper first fetches `url`, infers the input extension when possible, and then forwards the bytes to `convert`. Supply `fetchHeaders` when the remote resource needs authentication or custom headers. Args: url: Direct download URL for the source document or image. outfmt: Desired output format (`Fmt`). apiKey: TweekIT API key (`ApiKey` header). Falls back to `TWEEKIT_API_KEY` env var. apiSecret: TweekIT API secret (`ApiSecret` header). Falls back to `TWEEKIT_API_SECRET` env var. inext: Optional override for the source extension if it cannot be detected from the URL or response headers. noRasterize: Forwarded to TweekIT to skip rasterization when possible. width: Optional pixel width to request in the output. height: Optional pixel height to request in the output. x1: Left crop coordinate in source pixels. y1: Top crop coordinate in source pixels. x2: Right crop coordinate in source pixels. y2: Bottom crop coordinate in source pixels. page: Page number to extract for multipage inputs. alpha: Whether the output should preserve alpha transparency. bgColor: Background color to composite behind transparent pixels. fetchHeaders: Optional mapping of HTTP headers to include when fetching. Returns: A FastMCP `Image` or `File` payload, or an error description. Required: url, outfmt.
doctype(apiKey, apiSecret, extension)
Retrieve a list of supported file formats or map a file extension to its document type. Args: apiKey (str): The API key for authentication. Falls back to TWEEKIT_API_KEY when omitted. apiSecret (str): The API secret for authentication. Falls back to TWEEKIT_API_SECRET when omitted. extension (str): The file extension to query (e.g., 'jpg', 'pdf') or leave off or use '*' to return all supported input formats. Returns: Dict[str, Any]: A dictionary containing the supported file formats or an error message.
fetch(url)
Fetch a URL and return content. - Images return as FastMCP Image. - PDFs return as File(format="pdf"). - Text/JSON return as a JSON payload with metadata and text. Required: url.
search(query, max_results)
Simple web search using DuckDuckGo HTML endpoint. Returns a list of {title, url, snippet} objects. Best‑effort parsing. Required: query.

Last successful function declaration observed on . Source: https://mcp.tweekit.io/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://mcp.tweekit.io/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 1 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-07-03 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 0 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 1.6.1 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2025-12-01 When the registry record was last updated by its maintainer. point in time Model Context Protocol
License MIT Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. as of fetch GitHub
First listed in the MCP Registry 2025-12-01 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub
mcp tools declared 5 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe mcp.tweekit.io
mcp endpoint status ok The server listed 5 functions when asked. as of probe mcp.tweekit.io

Where to get it

Also from equilibrium-team

  • TweekIT MCP Server
    Normalize and convert 400+ file types via TweekIT's hosted MCP endpoint.

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. equilibrium-team/tweekit-mcp on GitHub — GitHub, observed , trust tier 3.
  2. Tools declared by the MCP server at https://mcp.tweekit.io/mcp — mcp.tweekit.io, observed , trust tier 1.
  3. Official MCP Registry — Model Context Protocol, observed , trust tier 1.