MCP 服务器

FileConvert

online.file-convert/fileconvert
开发者工具 公开且可连接 MCP 2025-11-25

此 MCP 可以做什么

Uploads and converts files across document, image, audio, video, archive, and ebook formats, with job tracking and download links.

convert_file
Convert a file from a URL
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.
输入模式
{'type': 'object', 'required': ['source_url'], 'properties': {'source_url': {'type': 'string', 'description': 'Public http(s) URL of the file to convert. It is fetched server-side with SSRF protection (private/loopback/link-local/metadata targets are refused). Max 200 MiB.'}, 'format_type': {'type': 'string', 'description': "Optional category hint ('image', 'video', 'audio', 'document', 'archive', 'ebook'); only needed when an extension exists in several categories."}, 'source_format': {'type': 'string', 'description': "Current format of the file, named by extension, e.g. 'png', 'docx', 'mp4'. Required unless source_format_id is given."}, 'target_format': {'type': 'string', 'description': "Desired output format, named by extension, e.g. 'webp', 'pdf', 'mp3'. Must be in the same category as the source (imageâ\x86\x92image, documentâ\x86\x92document, â\x80¦). Required unless target_format_id is given."}, 'format_type_id': {'type': 'integer', 'description': 'Advanced: numeric format-type id from list_formats. Not needed when formats are given by name.'}, 'source_format_id': {'type': 'integer', 'description': 'Advanced: numeric id of the source format from list_formats. Alternative to source_format.'}, 'target_format_id': {'type': 'integer', 'description': 'Advanced: numeric id of the target format from list_formats. Alternative to target_format.'}, 'additional_arguments': {'type': 'object', 'description': 'Optional free-form conversion arguments passed through to the converter.', 'additionalProperties': True}}, 'additionalProperties': False}
get_balance
Show remaining credits
Returns the credit balance of the account that owns the API key, 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.
输入模式
{'type': 'object', 'additionalProperties': False}
get_download_url
Get a download URL for a converted file
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.
输入模式
{'type': 'object', 'properties': {'job_id': {'type': 'string', 'description': 'The conversion job id (conversion uid). When given, the converted file uid is resolved from the completed conversion. Provide either job_id or file_id.'}, 'file_id': {'type': 'string', 'description': 'A file uid to download directly. Provide either job_id or file_id.'}}, 'additionalProperties': False}
get_job_status
Get conversion job status
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.
输入模式
{'type': 'object', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'description': 'The conversion job id (conversion uid) returned by convert_file.'}}, 'additionalProperties': False}
get_upload_url
Get file upload instructions
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 an API key (the upload itself needs one).
输入模式
{'type': 'object', 'required': ['filename'], 'properties': {'filename': {'type': 'string', 'description': "The name of the local file the agent wants to upload, e.g. 'report.docx'. Used for the multipart form filename."}}, 'additionalProperties': False}
list_formats
List supported file formats
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 an API key.
输入模式
{'type': 'object', 'properties': {'format_type': {'type': 'string', 'description': "Optional format-type name to filter by (e.g. 'image', 'video', 'document'). When omitted, all formats across all types are returned."}}, 'additionalProperties': False}
start_conversion
Convert an already uploaded file
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.
输入模式
{'type': 'object', 'required': ['file_id'], 'properties': {'file_id': {'type': 'string', 'description': "The file id returned by upload_file (or by a previous conversion's converted file)."}, 'format_type': {'type': 'string', 'description': "Optional category hint ('image', 'document', â\x80¦) when an extension exists in several categories."}, 'source_format': {'type': 'string', 'description': "Current format of the file by extension, e.g. 'docx'. Required unless source_format_id is given."}, 'target_format': {'type': 'string', 'description': "Desired output format by extension, e.g. 'pdf'. Same category as the source. Required unless target_format_id is given."}, 'format_type_id': {'type': 'integer', 'description': 'Advanced: numeric format-type id from list_formats.'}, 'source_format_id': {'type': 'integer', 'description': 'Advanced: numeric source format id from list_formats.'}, 'target_format_id': {'type': 'integer', 'description': 'Advanced: numeric target format id from list_formats.'}, 'additional_arguments': {'type': 'object', 'description': 'Optional free-form conversion arguments passed through to the converter.', 'additionalProperties': True}}, 'additionalProperties': False}
upload_file
Upload a file you hold locally
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.
输入模式
{'type': 'object', 'required': ['filename', 'content_base64'], 'properties': {'filename': {'type': 'string', 'description': "File name with extension, e.g. 'report.docx'. The extension helps the converter detect the format."}, 'content_base64': {'type': 'string', 'description': 'The file bytes encoded as base64 (standard or URL-safe alphabet, padding optional). Up to 25 MiB decoded; larger files should be given to convert_file by URL.'}}, 'additionalProperties': False}
已添加
upload_file
2026年10月3日 02:44
已添加
start_conversion
2026年10月3日 02:44
已添加
list_formats
2026年10月3日 02:44
已添加
get_upload_url
2026年10月3日 02:44
已添加
get_job_status
2026年10月3日 02:44
已添加
get_download_url
2026年10月3日 02:44
已添加
get_balance
2026年10月3日 02:44
已添加
convert_file
2026年10月3日 02:44