Content Tools

flatmark.dev

Converts uploaded documents to Markdown, supporting queued jobs up to 25 MB and 200 pages with OCR and table extraction.

1 endpoint3 known toolsFirst detected September 29, 2026Last detected October 6, 2026

ENDPOINT 1

https://api.flatmark.dev/mcp

No auth detected

Capabilities

experimentalloggingprompts.listChangedresources.listChangedtools.listChangedextensions.io.modelcontextprotocol/ui

Convert a document up to 8 MB to Markdown and return it directly.

Inferred read-only

Queue a document up to 25 MB and 200 pages for conversion with OCR and tables.

Inferred read-only

Check a queued conversion job you submitted.

Inferred read-only

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.flatmark]
url = "https://api.flatmark.dev/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: flatmark
Remote MCP URL: https://api.flatmark.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "flatmark": {
      "url": "https://api.flatmark.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "flatmark": {
      "type": "http",
      "url": "https://api.flatmark.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "flatmark",
  "transport": "streamable-http",
  "url": "https://api.flatmark.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

BuiltWith Trust API v2 evidence for flatmark.dev was fetched 2026-10-01T23:44:52.314Z.

Trust status Neutral

flatmark.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.