Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

App-Kit

REMOTE · MCP.APP-KIT.DEV

SEO audit (400 checks), text readability and grammar check, PDF to images, image conversion.

Available components

+3 this week 79 Trust /100

Last scanned (5 hours ago)

Scores higher than 79% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Marketing and SEO

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability65
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1859 tokens (~185/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 98% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 +1
    • Stability: 0.97 → pass security
  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “conversion_status” rewrote its description, which is the text the model reads security
    • Tool “create_upload” rewrote its description, which is the text the model reads security
    • Tool “image_convert” rewrote its description, which is the text the model reads security
    • Tool “images_to_pdf” rewrote its description, which is the text the model reads security
    • Tool “pdf_to_images” rewrote its description, which is the text the model reads security
    • Tool “quota_status” rewrote its description, which is the text the model reads security
    • Tool “seo_audit_fast” rewrote its description, which is the text the model reads security
    • Tool “seo_audit_status” rewrote its description, which is the text the model reads security
    • Tool “text_check” rewrote its description, which is the text the model reads security
    • Schema quality: excellent → good functional
    • New tool “image_compress” functional
    • “conversion_status” added an optional parameter “lang” cosmetic
    • “create_upload” added an optional parameter “lang” cosmetic
    • “image_convert” added an optional parameter “lang” cosmetic
    • “images_to_pdf” added an optional parameter “lang” cosmetic
    • “pdf_to_images” added an optional parameter “lang” cosmetic
    • “quota_status” added an optional parameter “lang” cosmetic
    • “seo_audit_status” added an optional parameter “lang” cosmetic
    • “text_check” added an optional parameter “response_lang” cosmetic
    • “conversion_status” reworded the description of “handle” cosmetic
    • “create_upload” reworded the description of “content_type” cosmetic
    • “create_upload” reworded the description of “filename” cosmetic
    • “create_upload” reworded the description of “size” cosmetic
    • “image_convert” reworded the description of “data_base64” cosmetic
    • “image_convert” reworded the description of “max_dim” cosmetic
    • “image_convert” reworded the description of “quality” cosmetic
    • “image_convert” reworded the description of “source_url” cosmetic
    • “image_convert” reworded the description of “target_format” cosmetic
    • “image_convert” reworded the description of “upload_id” cosmetic
    • “images_to_pdf” reworded the description of “page_size” cosmetic
    • “images_to_pdf” reworded the description of “source_urls” cosmetic
    • “images_to_pdf” reworded the description of “upload_ids” cosmetic
    • “pdf_to_images” reworded the description of “data_base64” cosmetic
    • “pdf_to_images” reworded the description of “dpi” cosmetic
    • “pdf_to_images” reworded the description of “first_page” cosmetic
    • “pdf_to_images” reworded the description of “format” cosmetic
    • “pdf_to_images” reworded the description of “last_page” cosmetic
    • “pdf_to_images” reworded the description of “source_url” cosmetic
    • “pdf_to_images” reworded the description of “upload_id” cosmetic
    • “seo_audit_fast” reworded the description of “lang” cosmetic
    • “seo_audit_fast” reworded the description of “url” cosmetic
    • “seo_audit_status” reworded the description of “handle” cosmetic
    • “text_check” reworded the description of “lang” cosmetic
    • “text_check” reworded the description of “layers” cosmetic
    • “text_check” reworded the description of “text” cosmetic
    • Tool “conversion_status” changed its title: Статус конвертации (App-Kit) → App-Kit conversion status cosmetic
    • Tool “create_upload” changed its title: Загрузка файла (App-Kit) → App-Kit file upload cosmetic
    • Tool “image_convert” changed its title: Конвертация картинки (App-Kit) → App-Kit image conversion cosmetic
    • Tool “images_to_pdf” changed its title: Картинки → PDF (App-Kit) → App-Kit images to PDF cosmetic
    • Tool “pdf_to_images” changed its title: PDF → картинки (App-Kit) → App-Kit PDF to images cosmetic
    • Tool “quota_status” changed its title: Лимиты App-Kit MCP → App-Kit usage limits cosmetic
    • Tool “seo_audit_fast” changed its title: Быстрый SEO-аудит (App-Kit) → App-Kit quick SEO audit cosmetic
    • Tool “seo_audit_status” changed its title: Статус SEO-аудита (App-Kit) → App-Kit SEO audit status cosmetic
    • Tool “text_check” changed its title: Проверка текста (App-Kit) → App-Kit text check cosmetic
  • 25 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 23 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://mcp.app-kit.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=app-kit.dev CN=WE1,O=Google Trust Services,C=US 8 Sept 2026 7 Dec 2026 ECDSA 256 ECDSA-SHA256 976fca599b7d808d13e26b9823e24daa
SANs: app-kit.dev, *.app-kit.dev
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.app-kit.dev. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
app-kit.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.app-kit.dev/mcp Verified 200
http (plaintext) http://mcp.app-kit.dev/mcp Inconclusive 406
MCP tools · 10 exposed · ~1,783 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
conversion_status ~101

Status and result of a conversion by the handle from pdf_to_images / images_to_pdf / image_convert. Does not consume quota. While status=running, call again after poll_after_s seconds. A handle is valid for 1 hour and only for the caller who started the conversion.

NameTypeReqDescription
handlestringyeshandle from pdf_to_images / images_to_pdf / image_convert
langstring–Language for human-readable messages; pass the user's language
NameTypeReqDescription
bytes_out–––
expires_at––When the links expire (UTC)
filesarray––
handle––Pass to conversion_status while status=running
pages––Number of rendered pages (pdf_to_images only)
poll_after_s–––
quota–yes–
statusstringyes–
toolstringyes–

No examples provided.

create_upload ~170

Create a one-time upload link for a local file (for clients with local file access, e.g. Claude Code, Cursor). Returns upload_id, put_url and a curl command: upload the file with a single PUT (up to 20 MB, within 10 min), then pass upload_id to a file tool. One upload_id serves one call. For a file at a public URL, pass source_url directly instead. Rate-limited per day; call quota_status for remaining calls.

NameTypeReqDescription
content_typestring–MIME type, e.g. application/pdf or image/png
filenamestringyesFile name, e.g. report.pdf
langstring–Language for human-readable messages; pass the user's language
sizeintegeryesFile size in bytes
NameTypeReqDescription
curlstringyesReady-to-run upload command
expires_atstringyesDeadline to upload and use the file (UTC)
max_bytesintegeryes–
put_urlstringyesWhere to upload the file with a single PUT (body: raw file bytes)
quota–yes–
upload_idstringyesPass to pdf_to_images / images_to_pdf / image_convert / image_compress

No examples provided.

image_compress ~253

Compress an existing image to WebP or AVIF: quality 1-100, width/height (downscale), preset (photo/picture/drawing/icon/text), lossless. Returns a result link (valid up to 5 min), original and new size, compression ratio. File up to 20 MB. Input: exactly one of source_url (public URL, the server downloads it), upload_id (create_upload, then PUT) or data_base64 (up to 512 KB). Rate-limited per day; call quota_status for remaining calls.

NameTypeReqDescription
data_base64––File as base64, only for small files (up to 512 KB)
formatstring–Output format
height––Downscale to this height, px
langstring–Language for human-readable messages; pass the user's language
lossless––Lossless compression
preset–––
quality––Quality 1-100
source_url––Public file URL (the server downloads it); preferred for hosted clients
upload_id––upload_id from create_upload (after the file PUT)
width––Downscale to this width, px
NameTypeReqDescription
compression_rationumberyes–
content_typestringyes–
converted_sizeintegeryes–
expires_atstringyes–
height–––
original_sizeintegeryes–
quota–yes–
statusstringyes–
urlstringyesResult link (valid until expires_at)
width–––

No examples provided.

image_convert ~278

Convert an existing image to another format: target_format png/jpeg/webp/bmp/tiff/gif, quality 1-100, max_dim (downscale the long side). File up to 20 MB. For avif and maximum compression use image_compress. Input: exactly one of source_url (public URL, the server downloads it), upload_id (create_upload, then PUT) or data_base64 (up to 512 KB). Output: download links (resource_link, valid for 10 min; deleted once all files of the job are downloaded) and a preview of the first image. If not done within 60 s, returns status=running and a handle: call conversion_status(handle). Rate-limited per day; call quota_status for remaining calls.

NameTypeReqDescription
data_base64––File as base64, only for small files (up to 512 KB)
langstring–Language for human-readable messages; pass the user's language
max_dim––Downscale the long side to N px
qualityinteger–Quality 1-100 (jpeg/webp)
source_url––Public file URL (the server downloads it); preferred for hosted clients
target_formatstringyesTarget format
upload_id––upload_id from create_upload (after the file PUT)
NameTypeReqDescription
bytes_out–––
expires_at––When the links expire (UTC)
filesarray––
handle––Pass to conversion_status while status=running
pages––Number of rendered pages (pdf_to_images only)
poll_after_s–––
quota–yes–
statusstringyes–
toolstringyes–

No examples provided.

images_to_pdf ~183

Combine existing images into one PDF (one image per page), page_size A4/Letter or the image size. Input: source_urls[] or upload_ids[], up to 20 files, each up to 20 MB. Output: download links (resource_link, valid for 10 min; deleted once all files of the job are downloaded) and a preview of the first image. If not done within 60 s, returns status=running and a handle: call conversion_status(handle). Rate-limited per day; call quota_status for remaining calls.

NameTypeReqDescription
langstring–Language for human-readable messages; pass the user's language
page_size––Page size; if omitted, the image size is used
source_urls––Public image URLs, in page order
upload_ids––Image upload_ids from create_upload, in page order
NameTypeReqDescription
bytes_out–––
expires_at––When the links expire (UTC)
filesarray––
handle––Pass to conversion_status while status=running
pages––Number of rendered pages (pdf_to_images only)
poll_after_s–––
quota–yes–
statusstringyes–
toolstringyes–

No examples provided.

pdf_to_images ~271

Convert an existing PDF to images (one file per page): format png/jpeg/webp, dpi 72-300, first_page/last_page. PDF up to 20 MB and up to 20 pages. Input: exactly one of source_url (public URL, the server downloads it), upload_id (create_upload, then PUT) or data_base64 (up to 512 KB). Output: download links (resource_link, valid for 10 min; deleted once all files of the job are downloaded) and a preview of the first image. If not done within 60 s, returns status=running and a handle: call conversion_status(handle). Rate-limited per day; call quota_status for remaining calls.

NameTypeReqDescription
data_base64––File as base64, only for small files (up to 512 KB)
dpiinteger–Resolution 72-300 dpi
first_page––First page (from 1)
formatstring–Page image format
langstring–Language for human-readable messages; pass the user's language
last_page––Last page
source_url––Public file URL (the server downloads it); preferred for hosted clients
upload_id––upload_id from create_upload (after the file PUT)
NameTypeReqDescription
bytes_out–––
expires_at––When the links expire (UTC)
filesarray––
handle––Pass to conversion_status while status=running
pages––Number of rendered pages (pdf_to_images only)
poll_after_s–––
quota–yes–
statusstringyes–
toolstringyes–

No examples provided.

quota_status ~73

Show the current access tier and the remaining calls for each tool. Tiers: L0 anonymous (shared per platform for Claude and ChatGPT), L1 personal token, L2 App-Kit account (OAuth). Does not consume quota.

NameTypeReqDescription
langstring–Language for human-readable messages; pass the user's language
NameTypeReqDescription
quota–yes–
tierstringyes–
toolsarrayyes–
upgrade_urlstringyes–

No examples provided.

seo_audit_fast ~181

Quick SEO audit of a public website (up to 10 pages): score 0-100 by check group, failed checks, top 5 losses. The site root is audited: URL path and query are dropped (https://example.com/page?x=1 -> https://example.com/). Waits up to 60 s for the result, sending progress. If not done by then, returns status=running and a handle: call seo_audit_status(handle) every poll_after_s seconds while status=running. Rate-limited per day; call quota_status for remaining calls. One domain: up to 5 audits per day.

NameTypeReqDescription
langstring–Language for human-readable messages; pass the user's language
urlstringyesPublic website URL, e.g. https://example.com (the site root is audited)
NameTypeReqDescription
checksarray–Failed checks only (up to 100)
checks_failed_total–––
domain–––
handle––Pass to seo_audit_status while status=running
modestringyes–
poll_after_s–––
quota–yes–
report_link––PDF report link; not provided by this server (null)
score–––
stage––queued → crawl → analyze → report → done
statusstringyes–
top_lossesarray–Up to 5 checks with the largest score loss

No examples provided.

seo_audit_status ~93

Status and result of an SEO audit by the handle from seo_audit_fast. Does not consume quota. While status=running, call again after poll_after_s seconds. A handle is valid for 60 min and only for the caller who started the audit.

NameTypeReqDescription
handlestringyeshandle returned by an SEO audit tool
langstring–Language for human-readable messages; pass the user's language
NameTypeReqDescription
checksarray–Failed checks only (up to 100)
checks_failed_total–––
domain–––
handle––Pass to seo_audit_status while status=running
modestringyes–
poll_after_s–––
quota–yes–
report_link––PDF report link; not provided by this server (null)
score–––
stage––queued → crawl → analyze → report → done
statusstringyes–
top_lossesarray–Up to 5 checks with the largest score loss

No examples provided.

text_check ~180

Check a text: metrics (filler words, spam, keyword stuffing), readability, stop phrases, grammar. Input: text up to 20000 characters, lang (language of the text) ru or en. Returns passed (blocking thresholds), metrics by layer, verdicts (blocking=false means a recommendation), top_issues (up to 5 main issues) and locations: issue positions (offset/length) in the submitted text. The text is not stored. Rate-limited per day; call quota_status for remaining calls.

NameTypeReqDescription
langstring–Language of the checked text
layers––Layers: metrics, readability, phrases, grammar (all by default)
response_langstring–Language for human-readable messages; pass the user's language
textstringyesText to check, up to 20000 characters
NameTypeReqDescription
langstringyes–
layersobjectyesMetrics by layer (numbers and statuses only, no text fragments)
locationsarray–Up to 10 issue positions (grammar, stop phrases): offset/length in the submitted text
passed–yesWhether the text passed all blocking thresholds
quota–yes–
top_issuesarrayyesUp to 5 main issues, blocking failures first
verdictsarrayyes–

No examples provided.

Install

How do I install the App-Kit MCP server?

App-Kit is a hosted endpoint at https://mcp.app-kit.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.app-kit.dev

# add to Claude Code
claude mcp add --transport http app-kit-dev-mcp 'https://mcp.app-kit.dev/mcp'
Common questions

What is the App-Kit MCP server?

App-Kit is an MCP server listed in the public MCP registry as io.github.app-kit-dev/mcp. SEO audit (400 checks), text readability and grammar check, PDF to images, image conversion. This page covers its hosted endpoint (https://mcp.app-kit.dev/mcp).

Is the App-Kit MCP server safe to use?

App-Kit scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the App-Kit MCP server expose?

App-Kit exposes 10 tools: text_check, seo_audit_fast, seo_audit_status, pdf_to_images, images_to_pdf, and 5 more. Their descriptions and schemas cost roughly 1,783 tokens of context every time the server is loaded.

Does the App-Kit MCP server require authentication?

No. We connected to App-Kit without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the App-Kit MCP server still maintained?

App-Kit is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.