Skip to main content
Glama

Server Details

Convert files between 110+ document, image, audio, video, archive and ebook formats from AI agents.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.4/5.0

Scored across 8 tools

Disambiguation4/5

Most tools have distinct purposes (convert_file vs start_conversion vs upload_file vs get_job_status), but get_upload_url and upload_file both address uploading local files, which could cause confusion about whether to use one or both.

Naming Consistency5/5

All tool names use consistent snake_case verb_noun pattern (get_, list_, start_, upload_, convert_), with no mixed conventions.

Tool Count5/5

8 tools is well-scoped for a file conversion service; each operation (convert, upload, status, download, formats, balance) covers a necessary step without excess.

Completeness4/5

Core conversion lifecycle is covered (discover formats, upload/convert, poll, download, credits), but minor gaps like canceling a job, deleting files, or listing job history exist.

Available Tools

8 tools
convert_fileConvert a file from a URLAInspect

End-to-end conversion of a remote file: fetches 'source_url' (with SSRF protection), uploads it to FileConvert, and starts a conversion from 'source_format' to 'target_format' (named by extension, e.g. png → webp, docx → pdf). Returns the conversion 'job_id' and the uploaded 'file_id'. Poll progress with get_job_status(job_id); when the status is Completed, call get_download_url(job_id) for the result. Conversions consume account credits. For a file you hold locally, use upload_file + start_conversion instead.

Inputs: source_url (required), format_type, source_format, target_format, +4 more.

get_balanceShow remaining creditsAInspect

Returns the credit balance of the signed-in account, plus where to get more. Every conversion costs credits; call this when a conversion fails with 'no credits' or when the user asks how many conversions they have left.

get_download_urlGet a download URL for a converted fileAInspect

Returns the download URL of a converted file. Pass 'job_id' (conversion uid) to resolve the converted file of a finished conversion, or 'file_id' to download a known file uid directly. The URL needs no authentication (the unguessable file id is the capability), so it can be handed to the user or another system as-is. It stops working when the file's retention ends — about one hour after conversion by default — so download or share it promptly.

Inputs: job_id, file_id.

get_job_statusGet conversion job statusAInspect

Returns the current status of a conversion job. Statuses: Pending → Processing → Completed or Failed (Failed includes the reason). Poll every 2–3 seconds after convert_file / start_conversion; when Completed, call get_download_url. Also returns the full conversion object, which includes the converted file uid once the job has finished.

Inputs: job_id (required).

get_upload_urlGet file upload instructionsAInspect

Returns instructions for uploading an agent-local file into FileConvert. FileConvert does NOT use presigned upload URLs; instead you upload the file bytes directly to the gateway as a multipart/form-data POST. The response gives the exact URL, HTTP method, form field name and required Authorization header. After uploading you receive a file object whose 'uid' can be passed to a conversion. If your file is reachable over http(s), prefer convert_file(source_url, target_format) which fetches and uploads it for you. Works without a token (the upload itself needs one).

Inputs: filename (required).

list_formatsList supported file formatsAInspect

Returns the file formats FileConvert can read and write, along with the format-type categories (image, video, document, audio, …). Use this first to discover valid 'format_type', 'source_format' and 'target_format' identifiers before calling convert_file. Each format includes its numeric id, name, file extension and description. Optionally pass 'format_type' to filter to a single category. Works without a token.

Inputs: format_type.

start_conversionConvert an already uploaded fileAInspect

Starts a conversion of a file that is already in FileConvert (a 'file_id' from upload_file or from an earlier job) from 'source_format' to 'target_format' (named by extension). Returns the 'job_id' to poll with get_job_status. Conversions consume account credits.

Inputs: file_id (required), format_type, source_format, target_format, +4 more.

upload_fileUpload a file you hold locallyAInspect

Uploads file bytes (base64) into FileConvert and returns a 'file_id'. Use this when the file is not reachable by URL, then call start_conversion(file_id, source_format, target_format). For files reachable over http(s), convert_file is a single call instead.

Inputs: filename (required), content_base64 (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      File conversion for AI agents: office docs to PDF, PDF to Word, document interchange (Markdown/HTML/EPUB/LaTeX), and audio/video transcodes via the hushvert hosted API. Tools: convert_file, convert_poll, list_formats, check_usage.
      4
      46 npm
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      Enables AI agents to convert documents, images, and data files across 50+ format pairs and to run PDF/image operations such as merge, split, compress, rotate, protect, unlock, extract text, and resize or compress images. Files are passed URL-in and returned URL-out (or saved locally in stdio mode), with tools for checking credits and generating Stripe checkout or billing-portal links.
      18
      50 PyPI
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources