PipedreamHQ / PipedreamHQ/pipedream
cleverhumanizer.ai
- Dominant language
- JavaScript
- Stars
- 11.7k
- Forks
- 5.8k
- Avg merge
- 3d 10h
- Merged PRs (30d)
- 102
Description
Name of app / service[Clever AI Humanizer](https://cleverhumanizer.ai/) (via a custom [Pipedream MCP Gateway](https://pipedream.com/docs/connect/mcp))Link to developer documentation[Pipedream MCP Integration Guide](https://pipedream.com/docs/connect/mcp/users)Model Context Protocol (MCP) Core SpecificationIs lack of support preventing you from moving forward, or do you have a workaround?No, a functional workaround is actively in place. While Clever AI Humanizer does not offer a native API or official Claude connector, we are successfully bypassing this limitation by using a custom Pipedream HTTP workflow to intercept texts, scrape or route the humanized variations, and stream the results back to Claude using the remote Pipedream MCP endpoint (https://remote.mcp.pipedream.net/v3).Are there specific actions or triggers you'd like to see for this app? Please let us know here or use the Action and Trigger issue templates to open requests for each!Action: humanize_text – Takes a block of AI-generated prose or text and routes it to the humanizer workflow to strip out typical AI markers, returning a refined, natural-sounding response.Action: set_tone_mode – A configuration parameter action allowing the agent to choose between different humanizing modes such as "Casual", "Simple Formal", or "Academic".Trigger: on_text_ready – A webhook trigger inside Pipedream that fires as soon as the rewritten humanized block is processed and ready to be delivered back into the active Claude chat window.
Contributor guide
Research direction
Start by reviewing the Pipedream MCP Integration Guide and the MCP Core Specification, then examine how the existing custom HTTP workflow uses the remote Pipedream MCP endpoint. Done means providing the requested humanize_text and set_tone_mode actions plus the on_text_ready trigger for Clever AI Humanizer, with results returned to Claude.
Written by the indexing model from the issue text.
Assessment
- Domain
- api
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100