inktomd MCP Server
io.github.hadirizvi093/inktomd-mcphadirizvi093streamable-httpv1.0.0Scanned
Convert files, URLs, and documents to clean, AI-ready Markdown via MCP.
9 tools: 7 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
7 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the inktomd MCP Server can do
The inktomd MCP Server is published by the GitHub account hadirizvi093. It has 9 tools. It can create or change data (7 tools: convert_url, convert_file, convert_youtube, convert_arxiv and 3 more), but cannot delete data. 2 tools only read.
1 tool reads private data (list_supported_formats); 1 tool brings in text other people can write (list_supported_formats); 4 tools can send data out of your system (convert_url, convert_youtube, convert_arxiv and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
9 tools
Changes things 7Claude Code: ask
convert_arxivConvert any ArXiv research paper to clean structured Markdown.Can send data outNo findings
Why it is in this group
- The name "convert_arxiv" says "convert": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Convert any ArXiv research paper to clean structured Markdown. Accepts both abstract page URLs (arxiv.org/abs/PAPER_ID) and direct PDF links (arxiv.org/pdf/PAPER_ID). Returns the full paper content with headings, sections, and content preserved — uses significantly fewer tokens than the PDF format for AI analysis.
convert_batchConvert multiple URLs to Markdown in a single call.Can send data outNo findings
Why it is in this group
- The name "convert_batch" says "convert": a word for a change.
What it can reach
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Convert multiple URLs to Markdown in a single call. Maximum 10 URLs per batch. Each URL is converted independently. Args: urls: List of URLs to convert. Maximum 10. Each must start with http:// or https:// Returns: All converted Markdown documents combined, clearly separated with headers
convert_fileConvert a local file to clean AI-ready Markdown.No findings
Why it is in this group
- The name "convert_file" says "convert": a word for a change.
Description, as the server wrote it Convert a local file to clean AI-ready Markdown. Supports PDF, Word (.doc/.docx), Excel (.xls/.xlsx), PowerPoint (.ppt/.pptx), EPUB, HTML, CSV, JSON, XML, Jupyter notebooks (.ipynb), Email files (.eml/.msg), ZIP archives (.zip), and 7-Zip archives (.7z). Provide the absolute file path. Maximum file size: 20MB.
convert_urlConvert any URL to clean AI-ready Markdown.Can send data outNo findings
Why it is in this group
- The name "convert_url" says "convert": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Convert any URL to clean AI-ready Markdown. Supports webpages, YouTube videos, ArXiv papers, Wikipedia articles, Substack newsletters, RSS feeds, Google Docs, GitHub pages, and more. Returns Markdown with up to 63% fewer tokens than the raw source HTML.
convert_with_metadataConvert a file or URL to Markdown and return both content and structured metadata.No findings
Why it is in this group
- The name "convert_with_metadata" says "convert": a word for a change.
Description, as the server wrote it Convert a file or URL to Markdown and return both content and structured metadata. Metadata includes title, estimated token counts for all major models, word count, character count, and reading time. Args: source: Either a URL (starting with http/https) or absolute file path source_type: Either "url" or "file". Default: "url" Returns: Markdown content with a metadata header block containing all stats
convert_youtubeExtract the full transcript from any public YouTube video as clean Markdown.Can send data outNo findings
Why it is in this group
- The name "convert_youtube" says "convert": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Extract the full transcript from any public YouTube video as clean Markdown. Works with standard watch links (youtube.com/watch?v=) and short links (youtu.be/). The video must have captions enabled — including auto-generated captions. Returns the transcript as flowing Markdown paragraphs, not raw caption fragments.
prepare_for_ragConvert a file or URL to Markdown, then split it into optimally-sized chunks ready for insertion into a vector database or RAG pipeline.No findings
Why it is in this group
- The description's first verb is "convert": a word for a change.
Description, as the server wrote it Convert a file or URL to Markdown, then split it into optimally-sized chunks ready for insertion into a vector database or RAG pipeline. Returns a JSON array of chunks with token counts, making this the single tool needed to go from raw document to RAG-ready data. Args: source: Either a URL (starting with http/https) or absolute file path source_type: Either "url" or "file". Default: "url" chunk_size: Target token count per chunk. Default: 512. Recommended range: 256-1024 overlap: Token overlap between consecutive chunks to preserve context. Default: 50 Returns: JSON array of chunks, each with: chunk_id, text, token_count, char_count
Only reads 2Show 2 read-only tools
count_tokensCount the exact number of tokens in a text string for a specific AI model.No findings
Why it is in this group
- The name "count_tokens" says "count": a word for reading.
Description, as the server wrote it Count the exact number of tokens in a text string for a specific AI model. Uses tiktoken for OpenAI models and estimates for others. Args: text: The text to count tokens for model: The AI model to count tokens for. Options: gpt-4o, gpt-4o-mini, gpt-4.1, claude-sonnet, claude-haiku, gemini-pro, gemini-flash, llama-4, deepseek-v3, mistral-large. Default: gpt-4o Returns: Token count information including count, context window, and fit status
list_supported_formatsList all file formats and URL types that inktomd supports for conversion to Markdown.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_supported_formats" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "file": it reads files.
- untrusted-inputThe description's first sentence says "list" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it List all file formats and URL types that inktomd supports for conversion to Markdown. Use this to check whether a specific file type or URL source is supported before attempting conversion.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 untrusted-input tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__inktomd__list_supported_formats"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:05 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.inktomd.com/mcp: tools/list returned 9 tools to an anonymous client, including convert_url (write), convert_file (write), convert_youtube (write), convert_arxiv (write), convert_batch (write) and 2 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http inktomd https://mcp.inktomd.com/mcpclaude mcp add --transport http inktomd https://mcp.inktomd.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__inktomd__list_supported_formats",
"mcp__inktomd__count_tokens"
],
"ask": [
"mcp__inktomd__convert_url",
"mcp__inktomd__convert_file",
"mcp__inktomd__convert_youtube",
"mcp__inktomd__convert_arxiv",
"mcp__inktomd__convert_batch",
"mcp__inktomd__convert_with_metadata",
"mcp__inktomd__prepare_for_rag"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as inktomd. Review it before you use it.
Capability tags behind 5 rules
- mcp__inktomd__convert_url outbound
- mcp__inktomd__convert_youtube outbound
- mcp__inktomd__convert_arxiv outbound
- mcp__inktomd__list_supported_formats private-data, untrusted-input
- mcp__inktomd__convert_batch outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.hadirizvi093/inktomd-mcp/verify?hash=a0023236945daef819eb9cd2c163a2a4b766910677de4e78686b5107ed25dfc6" | jq -e '.changed == false'Pinned hash a0023236945d, from Nov 20, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.hadirizvi093/inktomd-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.hadirizvi093/inktomd-mcp)Source: MCP Registry. Synced Oct 21, 2026, 18:35 UTC.
inktomd MCP Server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the inktomd MCP Server safe?
- No scan can promise that. What its definitions show: 9 tools, 7 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the inktomd MCP Server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the inktomd MCP Server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the inktomd MCP Server have?
- 9 tools: 7 write, 2 read. convert_url, convert_file, convert_youtube, convert_arxiv, convert_batch, convert_with_metadata, prepare_for_rag, list_supported_formats and 1 more.
Does the inktomd MCP Server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the inktomd MCP Server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): convert_url, convert_youtube, convert_arxiv and convert_batch.
Has the inktomd MCP Server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.