Skip to content
flatmark logo

flatmark MCP server

Which servers in the official MCP registry are flatmark's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to flatmark

Whose server it is
  • Registry namedev.flatmark/markdown-converterverified in the MCP registry

The registry name sits under flatmark.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools3
  • Server calls itselfflatmark
  • Server version1
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 496 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Convert PDF and Word files to Markdown; Queue scanned PDFs for OCR conversion; Let AI agents convert documents through MCP.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "Convert PDF and Word files to Markdown", the likely first call is convert_document.
  • For "Queue scanned PDFs for OCR conversion", the likely first call is submit_conversion_job.
  • For "Let AI agents convert documents through MCP", the likely first call is convert_document.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer510 ms
  • Space in an agent's context≈ 1,091 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · Convert PDF and Word files to Markdown
  • can do · Queue scanned PDFs for OCR conversion
  • can do · Let AI agents convert documents through MCP

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers3 tools · read 2026-10-26
  • convert_document

    Convert a document up to 8 MB to Markdown and return it directly. Pass the file as base64 in `content_base64`, or as a download link in `file`, and its name in `filename`. The extension decides the type: .pdf, .docx, .pptx, .xlsx, .html…

  • submit_conversion_job

    Queue a document up to 25 MB and 200 pages for conversion with OCR and tables. Pass the file as base64 in `content_base64`, or as a download link in `file`, and its name in `filename` (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt)…

  • get_conversion_job

    Check a queued conversion job you submitted. Returns `job_id` and `status` (`queued`, `running`, `succeeded` or `failed`). A succeeded job includes the `markdown` when it is under 100 KB, otherwise a `result_url` to download it (also…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "markdown-converter": {
      "type": "http",
      "url": "https://api.flatmark.dev/mcp/"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http flatmark https://api.flatmark.dev/mcp/

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.flatmark.dev/mcp/ as a custom connector in the settings.

OpenAPI spec

9 paths, read 2026-10-26. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.