Integration

ConvertHub integration

ConvertHub converts files between 800+ format pairs (images, documents, spreadsheets, e-books, audio, video and more), including OCR of images and scanned PDFs to text or searchable PDF. An agent can convert a stored file, a public URL or base64 content and wait for the result (a download link valid 24 hours), send files over 50 MB as chunks, read, cancel and early-delete jobs, check which conversions are supported, and read the account's credits. Conversions charge credits from a paid developer plan (most cost 1, complex pairs, large files and OCR more). The base64 download mode is not exposed (use the download link). Authentication is an API key created in the ConvertHub API dashboard, sent as a Bearer token.

Connect ConvertHub How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in ConvertHub.Built from the 16 ConvertHub tools below, on the connection you add once.

What you can do with ConvertHub

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Conversion, 3 operations

convert_base64_fileConvert base64 filePOSTAgents: ask firstConverts base64 file content (up to 50 MB decoded; filename gives the source format) to target_format. For a stored file use convert_file. Charges credits. Waits for the job and returns the finished result; gives up after 10 minutes.
convert_fileConvert filePOSTAgents: ask firstConverts a stored file (at most 50 MB; bigger files use start_chunked_upload) to target_format; result.download_url is valid 24 hours. Charges credits (OCR costs more). Waits for the job and returns the finished result; gives up after 10 minutes.
convert_file_from_urlConvert file from urlPOSTAgents: ask firstConverts the public file at file_url (up to 2 GB) to target_format; result.download_url is valid 24 hours. Charges credits (OCR costs more). Waits for the job and returns the finished result; gives up after 10 minutes.

Converted file, 2 operations

delete_job_fileDelete job fileDELETEAgents: ask firstPermanently deletes a completed job's converted file and its cached data before the automatic 24-hour expiry. Cannot be undone; only completed jobs can be deleted.
get_job_downloadGet job downloadGETAgents: ask firstReturns the temporary download_url (valid 24 hours after the conversion), file name, format and size of a completed job's converted file. A job still running answers JOB_NOT_COMPLETED.

Job, 2 operations

cancel_jobCancel jobDELETEAgents: ask firstCancels a conversion job that is still queued or processing; its status becomes cancelled. To remove a finished job's file, use delete_job_file.
get_jobGet jobGETAgents: ask firstReturns a conversion job's state (queued, processing, completed, failed or cancelled), its error when failed, and once completed result.download_url (valid 24 hours).

Upload session, 2 operations

complete_chunked_uploadComplete chunked uploadPOSTAgents: ask firstStep 3 of 3: assembles the uploaded chunks and runs the conversion set at start_chunked_upload; result.download_url is valid 24 hours. Charges credits. Waits for the job and returns the finished result; gives up after 10 minutes.
start_chunked_uploadStart chunked uploadPOSTAgents: ask firstStep 1 of 3 for a file over 50 MB: opens an upload session (session_id) and fixes its conversion (target_format, options). Then call upload_chunk once per chunk and complete_chunked_upload.

Account, 1 operation

get_accountGet accountGETAgents: ask firstReturns the account's remaining credits and its plan (name, monthly credits, price, largest accepted file in bytes and MB). Needs an active developer membership.

Conversion map, 1 operation

get_conversion_mapGet conversion mapGETAgents: ask firstReturns every supported format with its MIME type and category, and the full map of which formats each source format converts to.

Conversion support, 1 operation

check_conversionCheck conversionGETAgents: ask firstTells whether sourceFormat converts to targetFormat (supported true or false), with each format's MIME type and category when it does. Use it to validate a pair before converting.

Format, 1 operation

list_formatsList formatsGETAgents: ask firstLists every supported file format grouped by category (image, document, audio, video and others), each with its extension and MIME type.

Format conversion, 1 operation

list_format_conversionsList format conversionsGETAgents: ask firstLists every target format one source format converts to (extension and MIME type of each), with the source format's MIME type and category. An unknown format answers FORMAT_NOT_SUPPORTED.

Health, 1 operation

get_healthGet healthGETAgents: ask firstReturns the ConvertHub API's health status, its version, the server time, and how many formats and format pairs it supports.

Upload chunk, 1 operation

upload_chunkUpload chunkPOSTAgents: ask firstStep 2 of 3: sends ONE chunk into an upload session. Pass the whole file as chunk with this part's first_byte and last_byte (inclusive): only that slice is sent. chunkIndex 0, 1, 2... matches the slices.

Use ConvertHub from Claude Code, Cursor or Codex

Connect ConvertHub in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its ConvertHub operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect ConvertHub

Create your workspace
Sign up free. Nothing to install.
Connect ConvertHub once
Add your ConvertHub connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.