Verified conversions across 205 color spaces: CSS strings, gamut checks, .cube LUTs
ImgKits is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
ImgKits MCP: translate, blind watermark, audio, PDF→MD→translate, text utils, colorize.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http imgkits-mcp https://mcp.imgkits.com/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'
# 2 — ask your agent for something these tools do
# convert_to_markdown, ocr_image, extract_tables and 9 more
It needs AUTHORIZATION (Bearer sk_live_... API key from https://mcp.imgkits.com): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
ImgKits costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer sk_live_... API key from https://mcp.imgkits.com) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).
claude mcp add --scope user --transport http imgkits-mcp https://mcp.imgkits.com/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer sk_live_... API key from https://mcp.imgkits.com. You set it in your own client’s config, on your machine — this marketplace never holds it.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Convert PDF and image files to clean Markdown for RAG, LLM ingestion, and knowledge bases. Optionally include MinerU layout JSON (content list with blocks and bounding boxes). Input: 1-5 public https file URLs, each ≤20 MiB. Supported: pdf, png, jpeg, webp, bmp, tiff. DOCX is not supported in this release. Private, local, and metadata hosts are rejected. Processing is asynchronous upstream; this
| Parameter | Type | Required | Notes |
|---|---|---|---|
| files | array | yes | 1-5 public https file URLs. |
| include_layout_json | boolean | no | When true, also return MinerU layout JSON (content_list) for each file. |
Extract text from images, screenshots, and scanned PDF pages. Returns text blocks with block-level bounding boxes [x0, y0, x1, y1] and page indexes. Coordinates are MinerU content-list coordinates, not character-level boxes and not rescaled to pixels. Input: 1-5 public https file URLs, each ≤20 MiB. Supported: pdf, png, jpeg, webp, bmp, tiff. DOCX is not supported in this release. Private, local,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| files | array | yes | 1-5 public https file URLs. |
Extract tables from PDFs and images as HTML plus a row/column matrix. Merged cells are expanded; only the top-left cell carries content and other covered cells are empty strings. Returns row_count, column_count, page_idx, and bbox for each table. Input: 1-5 public https file URLs, each ≤20 MiB. Supported: pdf, png, jpeg, webp, bmp, tiff. DOCX is not supported in this release. Private, local, and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| files | array | yes | 1-5 public https file URLs. |
Translate up to 50,000 characters of plain text (up to 50 strings). Long inputs are split into <=1,900-character chunks automatically. Synchronous. Cost: 1 credit per call; mcp-credit-gateway charges before forwarding the request. Requires Authorization: Bearer sk_live_... on the MCP endpoint.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | no | A single string to translate. Provide this or texts, not both. |
| texts | array | no | Up to 50 strings to translate in one call. Total length must be <= 50,000 characters. |
| from | string | no | Source language code or English name. Defaults to 'auto'. |
| to | string | yes | Target language code or English name, e.g. en, zh, cht, ja, ko, fr, de, es. |
| idempotency_key | string | no | Optional per-job key for upstream job isolation. Billing is handled by mcp-credit-gateway. |
Translate a document from a public URL. Supported formats include PDF, DOCX/DOC, XLSX/XLS, PPTX/PPT, EPUB, TXT, HTML, MD and CSV. Upstream size limits: PDF <= 30 MB, other formats <= 80 MB. This is an async job: the call waits up to wait_seconds (default 30, max 120) and returns a job_id if still running. Call again with the same job_id to poll; polling does not start a new translation job. Upstre
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_url | string | no | Publicly reachable document URL (signed URLs are fine). Supported: PDF, DOCX/DOC, XLSX/XLS, PPTX/PPT, EPUB, TXT, HTML, MD, CSV, SRT and more. Upstream size limits: PDF <= 30 MB, other formats <= 80 MB |
| from | string | no | Source language code or name. Defaults to 'auto'. |
| to | string | no | Target language code or name, e.g. en, zh, cht, ja, ko, fr, de, es. |
| file_name | string | no | Optional original file name, used by the upstream for the output file name. |
| wait_seconds | integer | no | How long to wait for the async job in this call (0-120 seconds, default 30). |
| job_id | string | no | Resume polling an existing job. Polling does not create a new upstream job. |
| idempotency_key | string | no | Optional per-job key for upstream job isolation. Billing is handled by mcp-credit-gateway. |
Translate text inside 1-10 images supplied as public URLs (JPG/PNG/WebP recommended; keep each image <= 10 MB). This is an async job: the call waits up to wait_seconds (default 30, max 120) and returns a job_id if still running. Call again with the same job_id to poll; polling does not start a new translation job. Upstream result URLs expire (about 24 hours), so download promptly. Cost: 2 credits
| Parameter | Type | Required | Notes |
|---|---|---|---|
| image_urls | array | no | 1-10 public image URLs (JPG/PNG/WebP recommended). Keep each image <= 10 MB; larger files may be rejected by the upstream downloader. |
| from | string | no | Source language code or name. Defaults to 'auto'. |
| to | string | no | Target language code or name. Required for a new job. |
| paste | no | Paste mode: 0 = no text overlay, 1 = whole-image overlay (default), 2 = block overlay. | |
| font | string | no | Overlay font. Defaults to 'noto'. |
| wait_seconds | integer | no | How long to wait for the async job in this call (0-120 seconds, default 30). |
| job_id | string | no | Resume polling an existing job. Polling does not create a new upstream job. |
| idempotency_key | string | no | Optional per-job key for upstream job isolation. Billing is handled by mcp-credit-gateway. |
Translate SRT, WebVTT or ASS/SSA subtitle content (up to 1,000,000 characters). Timestamps, cue order, SRT/VTT indices and ASS event fields are preserved exactly; only cue text is translated. Synchronous. Cost: 3 credits per call, charged by mcp-credit-gateway before forwarding the request.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subtitle_content | string | yes | Raw subtitle text (SRT, WebVTT or ASS/SSA). Up to 1,000,000 characters. Timestamps are preserved exactly. |
| format | string | no | Subtitle format. Defaults to auto-detection. |
| from | string | no | Source language code or name. Defaults to 'auto'. |
| to | string | yes | Target language code or name, e.g. en, zh, cht, ja, ko, fr, de, es. |
| idempotency_key | string | no | Optional per-job key for upstream job isolation. Billing is handled by mcp-credit-gateway. |
Detect the language of up to 20,000 characters. Uses a local Unicode-script + stopword/diacritic heuristic; no upstream call. Returns a language code, confidence, reliability flag and alternatives. Billing: free by default (COST_DETECT_LANGUAGE=0).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Text to identify. Up to 20,000 characters; longer samples improve accuracy. |
| idempotency_key | string | no | Optional per-job key; relevant when COST_DETECT_LANGUAGE is above 0 (gateway billing). |
Add a visible text or image watermark to an image or PDF supplied as a public URL. Formats: JPG/PNG/WebP images up to 10 MB; PDF up to 30 MB. watermark_type=text requires text (<= 500 chars); watermark_type=image requires watermark_image_url (PNG/JPG/WebP, <= 5 MB, transparency supported). Position: top-left/top-center/top-right/center/bottom-left/bottom-center/bottom-right/tile. opacity 0.05-
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_url | string | yes | Public http(s) URL of the source image (JPG/PNG/WebP, <= 10 MB) or PDF (<= 30 MB). |
| source_type | string | no | Optional. Defaults to PDF when source_url ends in .pdf, otherwise image. |
| watermark_type | string | yes | text stamps words; image overlays a logo/PNG watermark. |
| text | string | no | Watermark text, required when watermark_type=text (<= 500 chars). |
| watermark_image_url | string | no | Public PNG/JPG/WebP watermark image URL, required when watermark_type=image (<= 5 MB; transparency supported). |
| position | string | no | Anchor for the watermark, or tile to repeat it across the page/image. |
| opacity | number | no | Watermark opacity, 0.05–1 (default 0.35). |
| scale | number | no | Image watermark width as a fraction of the source width, 0.02–0.95. |
| font_size | integer | no | Text watermark font size in pixels (images) or points (PDF), 8–256. |
| color | string | no | Text colour as #RRGGBB. Defaults to upstream choice (usually white). |
| rotation | number | no | Clockwise rotation in degrees, -180 to 180 (e.g. 45 for a diagonal stamp). |
| pages | string | no | PDF only. 1-based page selection such as "1", "1-3" or "1-3,5,8-10". |
| idempotency_key | string | no | Optional caller correlation key, echoed in the result. Billing is handled by mcp-credit-gateway. |
AI watermark removal / inpainting for ONE image (JPG/PNG/WebP, <= 10 MB) supplied as a public URL. Optional mask_image_url (white = remove) or normalized mask_rect {x,y,width,height} in 0-1; with neither, the upstream auto-detect mode is used (support depends on the upstream). COPYRIGHT / ABUSE GATE: Use only on images you own or are explicitly licensed/authorized to edit. Do not remove copyri
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_url | string | yes | Public http(s) URL of the image to clean (JPG/PNG/WebP, <= 10 MB). Only use material you own or are explicitly authorized to edit. |
| mask_image_url | string | no | Optional public URL of a mask image (white/opaque = watermark area to remove, black or transparent = keep). Mutually exclusive with mask_rect. |
| mask_rect | object | no | Optional rectangular mask in normalized coordinates (0–1). For /api/inpaint this is forwarded as mask_rect; if the upstream requires a bitmap mask, pass mask_image_url instead. Mutually exclusive wi |
| bucket | string | no | Upstream storage bucket for the result (default imgkits). |
| idempotency_key | string | no | Optional caller correlation key, echoed in the result. Billing is handled by mcp-credit-gateway. |
Embed an invisible/blind watermark into an image supplied as a public URL (JPG/PNG/WebP/BMP, <= 10 MB; at least 64x64 px recommended). Uses the AiController EncodeBlindWatermark / Alibaba Cloud IMM path. Pass watermark_text (<= 512 chars, e.g. an order id), or omit it to use the server-held BLIND_WATERMARK_KEY secret; the embedded content is never echoed back. model is DWT (default, more robus
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_url | string | yes | Public http(s) URL of the source image (JPG/PNG/WebP/BMP, <= 10 MB). Recommended at least 64x64 px so the blind watermark survives compression. |
| watermark_text | string | no | Content to embed invisibly (<= 512 chars), e.g. an order id or user id. Omit to use the server-held BLIND_WATERMARK_KEY. The content is never echoed back in the result. |
| model | string | no | Blind-watermark algorithm. DWT is more robust to scaling; DCT is faster. |
| strength | integer | no | Optional embedding strength, 1–10. Higher survives more editing but is slightly more visible. |
| idempotency_key | string | no | Optional caller correlation key, echoed in the result. Billing is handled by mcp-credit-gateway. |
Read a blind watermark from an image (public http(s) URL). Uses the AiController CreateDecodeBlindWatermarkTask + GetDecodeBlindWatermarkResult async path. Start with source_url; the call waits up to wait_seconds (default 15, max 60) and returns a job_id if still running. Poll by calling again with only job_id; polling never creates a new upstream decode task. Returns content when readab
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_url | string | no | Public http(s) URL of the watermarked image. Start a new decode job with this, or poll with job_id. |
| job_id | string | no | Existing upstream task id returned by a previous call. Polling never creates a new decode task. |
| wait_seconds | number | no | How long to wait for a result, 0–60 seconds (default 15). On timeout the call returns a job_id to poll. |
| idempotency_key | string | no | Optional caller correlation key, echoed in the result. Billing is handled by mcp-credit-gateway. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ImgKits or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| convert_to_markdown | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| ocr_image | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| extract_tables | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| translate_text | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| translate_document | untrusted-inputexternal-sink | untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| translate_image | untrusted-inputexternal-sink | untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| translate_subtitle | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| detect_language | no tags | |
| add_watermark | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| remove_watermark | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| embed_blind_watermark | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| decode_blind_watermark | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish ImgKits can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.