Koskamo

flatmark MCP

An official MCP server provided by flatmark that allows AI agents to convert various document formats (PDF, Word, PowerPoint, Excel, HTML) into Markdown. It supports direct conversion for smaller files and an asynchronous OCR queue for large or scanned files, facilitating document ingestion for RAG pipelines.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

flatmark MCP logo, by flatmarkVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by flatmark
You need:send an `X-API-Key` header (create keys after signing in)
MCP endpoint (Streamable HTTP)
https://api.flatmark.dev/mcp/
Vendor documentation

What its tools do

3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (2)

Can change data (1)

3 of 3 have a description · 3 of 3 declare behavior hints · 3 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to flatmark.dev ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Convert PDF, Word, PowerPoint, Excel, and HTML files to Markdown
  • Process large or scanned PDFs using an asynchronous OCR queue
  • Extract document structure as JSON for RAG ingestion
  • Integrate document conversion into AI agent workflows via Claude Code or Cursor

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: dev.flatmark/markdown-converter@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
flatmark 1
MCP protocol negotiated in check
2025-11-25
Tools
3 advertised
Resources
0 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  },
  "logging": {},
  "prompts": {
    "listChanged": true
  },
  "resources": {
    "subscribe": false,
    "listChanged": true
  },
  "extensions": {
    "io.modelcontextprotocol/ui": {}
  },
  "experimental": {}
}

Tools

3 advertised

convert_document — Convert a document to Markdown in one call
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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, .htm or .txt. Returns `markdown` and `meta` (`filename`, `length` in characters). PDFs come back as plain text without headings and without OCR. For scans, tables and page numbers, use `submit_conversion_job`. Works without an API key at the anonymous rate limit. Credits: 1 per call.

convert_document input schema
{
  "type": "object",
  "required": [
    "filename"
  ],
  "properties": {
    "file": {
      "type": "object",
      "default": null,
      "required": [
        "download_url",
        "file_id"
      ],
      "properties": {
        "file_id": {
          "type": "string",
          "description": "An identifier for the file. ChatGPT sets it; other clients may pass any label, such as the file name."
        },
        "file_name": {
          "type": "string"
        },
        "mime_type": {
          "type": "string"
        },
        "download_url": {
          "type": "string",
          "description": "A public https URL of the file."
        }
      },
      "description": "The file as a download link, instead of `content_base64`. In ChatGPT, pass the user's uploaded file here. Other clients can set `download_url` to a public https URL."
    },
    "filename": {
      "type": "string",
      "description": "The file name with its extension (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). The extension decides how the file is read."
    },
    "content_base64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The file content, base64-encoded. Up to 8 MB before encoding."
    }
  },
  "additionalProperties": false
}
convert_document output schema
{
  "type": "object",
  "additionalProperties": true
}
convert_document annotations
{
  "title": "Convert a document to Markdown in one call",
  "readOnlyHint": true,
  "openWorldHint": true
}
submit_conversion_job — Queue a document for conversion with OCR and tables
Advertised by the server during the last successful anonymous check.
Open-world

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). Returns `job_id`, `status` and `result_url`. Call `get_conversion_job` with the `job_id` until `status` is `succeeded` or `failed`. A conversion may take up to about 2 minutes. Optional `webhook_url`: a public http or https URL that receives a POST with the job's final state. The request carries `X-Appkit-Signature: sha256=<hex>`, an HMAC-SHA256 of the raw body keyed with the returned `webhook_secret` (shown only once). 3 delivery attempts. Requires an API key. The credits are refunded if the job fails. The uploaded file is deleted when the job finishes. Results are kept for 7 days after submission. Credits: 10 per call.

submit_conversion_job input schema
{
  "type": "object",
  "required": [
    "filename"
  ],
  "properties": {
    "file": {
      "type": "object",
      "default": null,
      "required": [
        "download_url",
        "file_id"
      ],
      "properties": {
        "file_id": {
          "type": "string",
          "description": "An identifier for the file. ChatGPT sets it; other clients may pass any label, such as the file name."
        },
        "file_name": {
          "type": "string"
        },
        "mime_type": {
          "type": "string"
        },
        "download_url": {
          "type": "string",
          "description": "A public https URL of the file."
        }
      },
      "description": "The file as a download link, instead of `content_base64`. In ChatGPT, pass the user's uploaded file here. Other clients can set `download_url` to a public https URL."
    },
    "filename": {
      "type": "string",
      "description": "The file name with its extension (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). The extension decides how the file is read."
    },
    "webhook_url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional. A public http or https URL that receives the job's final state."
    },
    "content_base64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The file content, base64-encoded. Up to 25 MB before encoding."
    }
  },
  "additionalProperties": false
}
submit_conversion_job output schema
{
  "type": "object",
  "additionalProperties": true
}
submit_conversion_job annotations
{
  "title": "Queue a document for conversion with OCR and tables",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
get_conversion_job — Check a queued conversion
Advertised by the server during the last successful anonymous check.
Advertised read-only

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 free). A failed job includes `error`, one sentence with the reason. Results are deleted 7 days after submission. An expired result is reported in `error`. Requires an API key. Credits: free. This tool is not metered.

get_conversion_job input schema
{
  "type": "object",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "The `job_id` returned by `submit_conversion_job`."
    }
  },
  "additionalProperties": false
}
get_conversion_job output schema
{
  "type": "object",
  "additionalProperties": true
}
get_conversion_job annotations
{
  "title": "Check a queued conversion",
  "readOnlyHint": true,
  "openWorldHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1852 ms
95th percentile latency
1852 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1852 ms · metadata changed · 3 tool(s), 0 resource(s), 0 resource template(s), 0 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http flatmark-mcp https://api.flatmark.dev/mcp/

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add flatmark-mcp --url https://api.flatmark.dev/mcp/

Cursor

Merge this server into .cursor/mcp.json in your project, then enable flatmark-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "flatmark-mcp": {
      "url": "https://api.flatmark.dev/mcp/"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "flatmark-mcp": {
      "type": "streamableHttp",
      "url": "https://api.flatmark.dev/mcp/",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start flatmark-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "flatmark-mcp": {
      "type": "http",
      "url": "https://api.flatmark.dev/mcp/"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http flatmark-mcp https://api.flatmark.dev/mcp/

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://api.flatmark.dev/mcp/

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "flatmark-mcp": {
      "serverUrl": "https://api.flatmark.dev/mcp/"
    }
  }
}

Let your agent find its tools

Find servers like flatmark MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 8,317

Do you run flatmark MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing