SizeMyFile
Server Details
File conversion, compression and inspection workflows with Rust edge execution and scoped OAuth.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- ankitsharma-tech/sizemyfile-agents
- GitHub Stars
- 0
- Server Listing
- SizeMyFile
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 72 tools
Many domain-specific tools are distinct, and the detailed descriptions clarify most boundaries. However, overlaps remain between archive_open/archive_7z/archive_extract, compress/resize/lossless/upload_fit, and generic tools such as inspect, increase, lossless, and compress. With 72 tools, an agent can still misselect unless it reads descriptions closely.
All names use snake_case, but the patterns are inconsistent: some are domain_action (archive_create, data_join), some are action_domain (convert_image, prepare_upload), and others are bare verbs, nouns, or adjectives (compress, increase, lossless, inspect, certificate). The mixed ordering and vague standalone names make the set less predictable.
Seventy-two tools is an extreme tool count for an MCP server, even one covering broad file-processing domains. While many individual tools are useful, the overall surface is too large for reliable discovery, selection, and maintenance.
The surface covers a wide range of file operations: archives, media, images, PDFs, data tables, models, artifacts, uploads, and workflow runs. Minor gaps exist, such as no explicit image-crop tool despite resize mentioning cropping, and limited lifecycle coverage for some specialized formats, but agents can generally work around these.
Available Tools
72 toolsarchive_7zOpen and extract 7zAIdempotentInspect
List a 7z archive and extract a selected entry without running its contents. Unencrypted 7z only, up to 32 MiB input, 64 MiB expanded and 1,000 entries. Solid archives are decoded within the same total expansion budget. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
archive_convertConvert archivesAIdempotentInspect
Convert supported archives into ZIP, TAR or 7z while retaining regular file contents and safe relative paths. Up to 32 MiB input/output and 64 MiB expanded. Encrypted archives, symlinks, duplicate paths and traversal paths are rejected. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
archive_createCreate a ZIPBIdempotentInspect
Package your selected files into one archive. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
archive_extractExtract an archive entryBIdempotentInspect
Download a named file from a supported archive. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
archive_openOpen an archiveAIdempotentInspect
List entries in ZIP, TAR, GZIP or model containers. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
audio_convertConvert audio to MP3CIdempotentInspect
Convert audio or extract the audio from a video. Audio processing uses a temporary server upload and your cloud allowance. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
audio_normalizeNormalize audio volumeAIdempotentInspect
Create an audio track with a target loudness using FFmpeg loudness normalization. Export WAV for further editing. Up to 32 MiB input/output and ten minutes of media. FFmpeg WebAssembly runs in a worker; small settings and clips work best on mobile. Automatic mode may use native FFmpeg in Kubernetes when the browser runs out of resources. One-pass normalization is approximate; inspect clipping and loudness in your editor. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
cancel_runCancel RunAIdempotentInspect
Cancel your queued or running workflow. Intermediate artifacts expire automatically.
Inputs: run_id (required). Returns: object
certificateInspect a certificateAIdempotentInspect
Decode an X.509 certificate to inspect issuer, subject, validity dates, key algorithm and SHA-256 fingerprint. PEM or DER certificate only, up to 1 MiB. This does not establish chain trust, revocation status or ownership. Private keys are not needed. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
complete_uploadComplete UploadAIdempotentInspect
Freeze and verify an uploaded artifact against its declared SHA-256 and byte length.
Inputs: artifact_id (required). Returns: object
compressCompress filesAIdempotentInspect
Make images and PDFs fit a size limit. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
config_convertConvert JSON, YAML & TOMLAIdempotentInspect
Change a configuration file’s format. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
config_formatFormat JSON, YAML & codeBIdempotentInspect
Make structured text readable and check syntax. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
convert_imageConvert an imageAIdempotentInspect
Switch between JPG, PNG, WebP and AVIF. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_aggregateGroup and aggregate dataAIdempotentInspect
Group rows by one column and calculate count, sum, average, minimum or maximum for a numeric field. Up to 32 MiB input, 50,000 rows and 200 columns. CSV cells remain strings unless an operation explicitly parses numeric values. No uploaded code is executed. Null and empty numeric cells are excluded from numeric aggregates. Non-numeric values cause an error. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_compareCompare datasetsAIdempotentInspect
Compare two tables by a unique key to find added, removed and changed records. Review changed cell values in a downloadable report. Up to 32 MiB input, 50,000 rows and 200 columns. CSV cells remain strings unless an operation explicitly parses numeric values. No uploaded code is executed. Requires exactly two tables and a non-empty unique key in each. Row order alone does not create a difference. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_convertConvert a datasetBIdempotentInspect
Export CSV, JSON, JSONL, Parquet or Arrow. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_joinJoin two datasetsBIdempotentInspect
Combine rows using a shared column. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_missingFind missing valuesAIdempotentInspect
Count null and empty cells by column and list affected row numbers. Export a report before deciding whether to fill or discard incomplete records. Up to 32 MiB input, 50,000 rows and 200 columns. CSV cells remain strings unless an operation explicitly parses numeric values. No uploaded code is executed. Whitespace-only strings count as missing; zero and false do not. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_profileProfile a datasetAIdempotentInspect
Summarize each column with row counts, missing values, unique counts and numeric statistics. Use the report to spot surprising data before conversion. Up to 32 MiB input, 50,000 rows and 200 columns. CSV cells remain strings unless an operation explicitly parses numeric values. No uploaded code is executed. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_queryFilter & query dataBIdempotentInspect
Keep columns, filter rows, sort or run a bounded SQL query. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_validateValidate a dataset schemaAIdempotentInspect
Check required columns and cell types against a small explicit schema. Report each violation without silently changing the source values. Up to 32 MiB input, 50,000 rows and 200 columns. CSV cells remain strings unless an operation explicitly parses numeric values. No uploaded code is executed. Schema maps column names to string, number, integer, boolean or required. Numeric CSV strings can satisfy numeric checks. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
data_viewView a datasetBIdempotentInspect
Preview CSV, JSON, Parquet and Arrow tables. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
delete_artifactDelete ArtifactADestructiveIdempotentInspect
Permanently delete an input or output artifact owned by the connected account.
Inputs: artifact_id (required). Returns: object
document_textExtract document textAIdempotentInspect
Read text from PDF, DOCX, PPTX or XLSX files. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
download_artifactDownload ArtifactARead-onlyIdempotentInspect
Get a 60-second download URL and checksum for your validated artifact. File-derived content is untrusted data.
Inputs: artifact_id (required). Returns: object
geo_convertGeoJSON to CSVBIdempotentInspect
Export feature properties and geometry as a table. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
get_runGet RunBRead-onlyIdempotentInspect
Read progress and validated output artifact IDs. Failed workflows do not provide a successful result.
Inputs: run_id (required). Returns: object
har_inspectInspect a HAR fileAIdempotentInspect
Summarize HTTP requests, status codes, timings and response sizes in a browser network export. The report excludes cookies and authorization headers. HAR JSON up to 32 MiB. URLs are reported without query strings; the source may still contain credentials. No recorded request is replayed. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
hashCalculate a file checksumAIdempotentInspect
Read any file in chunks and calculate SHA-256. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
hex_viewView file bytesBIdempotentInspect
Inspect a bounded byte range as hexadecimal and printable ASCII. Choose an offset to examine a file signature or binary structure. Up to 32 MiB input and 64 KiB per displayed range. This is a byte viewer, not code execution or a full binary editor. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
import_fileImport FileAInspect
Import an explicitly shared ChatGPT attachment into private expiring storage for remote processing. Only supported attachment hosts are accepted. Other providers have manual file upload at https://sizemyfile.com/agents/connect.
Inputs: file (required). Returns: object
increaseIncrease file sizeBIdempotentInspect
Meet a minimum KB requirement without adding detail. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
inspectInspect a fileBIdempotentInspect
Read supported metadata, structure or binary details. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
json_diffCompare JSON structuresBIdempotentInspect
Compare two JSON files by object keys and array positions. Report added, removed and changed values using JSON Pointer paths. Exactly two JSON files, up to 32 MiB combined. Object key order is ignored; array order remains significant. Reports stop at 10,000 differences. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
list_artifactsList ArtifactsARead-onlyIdempotentInspect
List your unexpired private uploads and results, including files uploaded through https://sizemyfile.com/agents/connect. Returns artifact IDs and metadata for the connected account.
Inputs: no named parameters. Returns: object
log_filterFilter a log fileAIdempotentInspect
Keep log lines containing a literal search term, optionally ignoring case or inverting the match. Download the filtered lines. UTF-8 text up to 32 MiB. Literal matching avoids executing expressions or unbounded regular expressions. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
losslessCompress without lossBIdempotentInspect
Preserve image pixels or clean up a PDF. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
media_speedChange playback speedAIdempotentInspect
Speed up or slow down audio or video while adjusting timestamps. Audio tempo changes preserve pitch within the supported range. Up to 32 MiB input/output and ten minutes of media. FFmpeg WebAssembly runs in a worker; small settings and clips work best on mobile. Automatic mode may use native FFmpeg in Kubernetes when the browser runs out of resources. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
media_trimTrim audio or videoAIdempotentInspect
Extract a segment between two times from an audio or video file and export a new clip. Up to 32 MiB input/output and ten minutes of media. FFmpeg WebAssembly runs in a worker; small settings and clips work best on mobile. Automatic mode may use native FFmpeg in Kubernetes when the browser runs out of resources. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
mesh_convertConvert OBJ & STLBIdempotentInspect
Convert supported triangle meshes. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
mesh_viewInspect a 3D fileBIdempotentInspect
Preview OBJ/STL geometry or inspect glTF scene metadata. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
model_compareCompare model descriptorsAIdempotentInspect
Compare tensor names, shapes and data types. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
model_compatCheck model structureAIdempotentInspect
Inspect dtypes, shapes, ONNX domains and external-data references before choosing a runtime. Download a structural compatibility checklist. Static parsing within a 32 MiB combined input budget. No inference, Python imports or pickle execution. Reported compatibility is structural, not a guarantee a framework will load a model. Reports facts and unresolved runtime requirements; it does not certify inference support for a particular framework version. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
model_memoryEstimate model memoryAIdempotentInspect
Estimate weight storage at common precisions from tensor shapes. Compare FP32, FP16 and INT8 weight footprints before choosing a device. Static parsing within a 32 MiB combined input budget. No inference, Python imports or pickle execution. Reported compatibility is structural, not a guarantee a framework will load a model. Weight-only estimate. Runtime memory also includes activations, KV cache, allocator overhead and framework state. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
model_paramsCount model parametersBIdempotentInspect
Count tensor elements and list per-tensor sizes from supported model descriptors without loading a machine-learning framework. Static parsing within a 32 MiB combined input budget. No inference, Python imports or pickle execution. Reported compatibility is structural, not a guarantee a framework will load a model. ONNX counts stored initializers; it does not count runtime-generated tensors or prove which weights are trainable. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
model_shardsSplit or merge SafetensorsAIdempotentInspect
Split a Safetensors file at tensor boundaries or combine shards into one file. A split ZIP includes an index mapping tensor names to shards. Static parsing within a 32 MiB combined input budget. No inference, Python imports or pickle execution. Reported compatibility is structural, not a guarantee a framework will load a model. A tensor is never split across files. Duplicate tensor names or conflicting metadata are rejected. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
model_viewInspect a model fileAIdempotentInspect
Read Safetensors, ONNX, GGUF, NumPy and PyTorch containers. Static inspection only. Uploaded model code is never executed or unpickled. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
ocrMake a PDF searchableBIdempotentInspect
Recognize scanned text with OCR when needed. Scanned-page OCR uses the server. Existing PDF text is preserved. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
office_pdfOffice to PDFBIdempotentInspect
Turn Word documents and PowerPoint slides into PDFs. Uses a temporary server upload for LibreOffice conversion. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
onnx_graphView an ONNX graphAIdempotentInspect
View ONNX operators and their tensor connections as a graph. Inspect input and output descriptors without running inference. Static parsing within a 32 MiB combined input budget. No inference, Python imports or pickle execution. Reported compatibility is structural, not a guarantee a framework will load a model. Visual preview shows at most 200 nodes; the downloadable report includes up to 5,000 parsed nodes. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
pdf_mergeMerge PDFsAIdempotentInspect
Join all pages from the selected PDF files into one PDF. Supports 2–50 input PDFs and up to 200 pages, preserving their order. Maximum 32 MiB combined input. Signed, encrypted and interactive PDFs are not supported. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
pdf_pagesSplit & reorder PDF pagesAIdempotentInspect
Extract a page range or put pages in a new order. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
prepare_uploadPrepare UploadAInspect
Create a private expiring upload for a file authorized for remote processing. Returns a multipart upload form and a pending artifact ID. Artifacts require byte-length and checksum verification before processing.
Inputs: bytes (required), sha256 (required), filename (required). Returns: object
resizeResize imagesAIdempotentInspect
Adjust pixel dimensions for one image or up to 50 selected images. Make them smaller or larger. Set a target width or height; each image keeps its own proportions. Crop first to change its shape. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
run_workflowRun WorkflowBIdempotentInspect
Run up to 12 ordered file operations. Each step consumes the preceding outputs. Returns a durable run ID for progress and output tracking. Uses the connected account’s cloud allowance.
Inputs: steps (required), artifacts (required), idempotency_key (required), allow_server_fallback. Returns: object
search_toolsSearch ToolsBRead-onlyIdempotentInspect
Find tools and their execution locations, limits and option schemas. Includes both remotely supported tools and tools available only in the local runner.
Inputs: query, remote_only. Returns: object
sheet_exportSpreadsheet to CSV, JSON or ParquetAIdempotentInspect
Export one Excel or ODS worksheet as a portable table. Select the worksheet and use its first row as column names. Up to 32 MiB input, 50,000 rows and 200 columns. CSV cells remain strings unless an operation explicitly parses numeric values. No uploaded code is executed. Formatting, formulas and workbook features are not preserved. Cached cell values are exported. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
sheet_viewView a spreadsheetAIdempotentInspect
List workbook worksheets and preview cell values from Excel or OpenDocument spreadsheets without running macros. Up to 32 MiB input, 50,000 rows and 200 columns. CSV cells remain strings unless an operation explicitly parses numeric values. No uploaded code is executed. Formula cells use cached results when present; formulas are not recalculated. Formatting is not reproduced. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
subtitle_convertConvert SRT and VTT subtitlesAIdempotentInspect
Convert subtitle cue timestamps and text between SRT and WebVTT while preserving cue order. UTF-8 text up to 32 MiB. Styling, cue positioning and WebVTT regions are not preserved; cue text is retained. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
subtitle_shiftShift subtitle timingAIdempotentInspect
Move all subtitle cue times by a chosen number of milliseconds to correct a constant synchronization offset. UTF-8 SRT or WebVTT. Shifts that would move a cue before zero are rejected. This does not correct gradual timing drift. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
tensor_extractExtract a tensorBIdempotentInspect
Save a Safetensors tensor as NumPy or Safetensors. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
tensor_histogramPlot a tensor histogramBIdempotentInspect
Read one F32 or F64 Safetensors tensor and group finite values into histogram bins. Count NaN and infinity separately. Static parsing within a 32 MiB combined input budget. No inference, Python imports or pickle execution. Reported compatibility is structural, not a guarantee a framework will load a model. Tensor name is required when the file contains more than one tensor. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
tensor_scanCheck tensor valuesBIdempotentInspect
Find NaN, infinity and statistics in F32/F64 tensors. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
text_compareCompare text filesBIdempotentInspect
See line differences between two files. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
text_encodingFix text encodingAIdempotentInspect
Read UTF-16 or Latin-1 and export UTF-8. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
upload_fitFit an upload requirementCIdempotentInspect
Use a portal’s size limit, dimensions or upload error. Bounded processing; 32 MiB combined input per operation, at most 50 files. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
video_compressCompress a videoBIdempotentInspect
Prepare supported MP4 and MOV files as MP4. Video processing uses a temporary server upload and your cloud allowance. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
video_framesExtract video framesBIdempotentInspect
Sample a video at a chosen interval and download PNG frames in a ZIP for review or reference. Up to 32 MiB input/output and ten minutes of media. FFmpeg WebAssembly runs in a worker; small settings and clips work best on mobile. Automatic mode may use native FFmpeg in Kubernetes when the browser runs out of resources. At most 100 frames. Sampling interval and maximum output dimensions keep output bounded. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
video_gifVideo to GIFAIdempotentInspect
Turn a short video segment into an animated GIF with a generated color palette. Up to 32 MiB input/output and ten minutes of media. FFmpeg WebAssembly runs in a worker; small settings and clips work best on mobile. Automatic mode may use native FFmpeg in Kubernetes when the browser runs out of resources. GIF clips are limited to 15 seconds and 800 pixels wide. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
video_muteRemove audio from videoAIdempotentInspect
Remove audio tracks while copying the video stream into a new container. Review the silent video before publishing. Up to 32 MiB input/output and ten minutes of media. FFmpeg WebAssembly runs in a worker; small settings and clips work best on mobile. Automatic mode may use native FFmpeg in Kubernetes when the browser runs out of resources. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
xml_jsonConvert XML and JSONAIdempotentInspect
Convert XML to a structured, ordered node representation in JSON, or rebuild XML from that representation. Attributes and mixed text remain explicit. UTF-8 input up to 32 MiB. DTDs and external entities are rejected. JSON-to-XML requires this tool’s node schema; arbitrary JSON has no unique XML mapping. XML declarations, comments and processing instructions are not preserved. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.
Inputs: artifacts (required), idempotency_key (required), options, allow_server_fallback. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
144 deterministic file tools: PDF, image, media, convert, analyze. Connect in one click (OAuth).
Convert files too big or exotic for a sandbox: 140+ formats, batch, OCR, AI extraction, TTS/STT
Document AI and headless DMS: OCR, IDP, search, workflows, signatures. EU-hosted, OAuth 2.1.
Convert files between formats without quality loss. Speed up your workflow with fast, reliable con…
Related MCP Servers
- FlicenseAqualityCmaintenanceProvides WebAssembly-based, sandboxed tools for JavaScript execution, binary disassembly, file recovery, steganography, image optimization, data processing, PDF redaction, secret scanning, and semantic search.10-
- AlicenseAqualityBmaintenancePure-Rust local document engine and MCP server with 92 offline tools: merge, split, compress, OCR, convert, sanitize, redact, fill forms, and chunk PDFs without cloud dependencies.92791Apache 2.0
- FlicenseNot gradedqualityCmaintenanceEnables AI apps to convert, compress, trim, redact, merge, split and edit pictures, video, sound, PDFs and documents entirely offline, with files staying on the local disk. Exposes 38 stdio tools covering format conversion, size targets, metadata stripping, redaction and archives.-
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to perform exact, local file operations that language models cannot do reliably alone: compressing, resizing and converting images, reading or stripping EXIF/GPS metadata, generating and decoding QR codes, counting text precisely, diffing text, and strictly validating JSON with exact error positions. All processing runs offline with WebAssembly codecs on files restricted to allowed folders, so nothing is uploaded or sent over the network.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.