DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to call the REST API to edit text in a publishing pipeline with Zero Slop

Post text to the deslop endpoint and check status before using the edit.

Short answer: Read the API reference in docs/rest-api.md and the OpenAPI contract at https://mcp.zero-slop.ai/openapi.json; then keep each request under the shared free capacity limit of 20,000 Unicode code points after trimming; send the text with curl --fail-with-body --max-time 75 https://mcp.zero-slop.ai/v1/deslop -H 'Content-Type: application/json' --data '{"text":"<your text>","genre":"professional"}'. All steps.

  • Content
  • Advanced
  • 30 minutes
  • From the README
  • Any agent

Who it is forA developer building a publishing tool or content pipeline that needs slop removal on short text.

The problemPipelines need an HTTP call that returns edited text they can check before it goes live.

The outcomeAn edited version of the text returned by the API, accepted only when its status field confirms it is usable.

What you need first

  • Claude Code or Codex (or another assistant that supports agent skills) for the skill workflow
  • Python 3 for the offline local scorer
  • Node.js 22+ for the npx CLI and the score command
  • Internet access if you use the hosted CLI, REST API, or MCP endpoint

Steps

  1. Read the API reference in docs/rest-api.md and the OpenAPI contract at https://mcp.zero-slop.ai/openapi.json.
  2. Keep each request under the shared free capacity limit of 20,000 Unicode code points after trimming.
  3. Send the text with curl --fail-with-body --max-time 75 https://mcp.zero-slop.ai/v1/deslop -H 'Content-Type: application/json' --data '{"text":"<your text>","genre":"professional"}'. (inferred, check the README)
  4. Check the status field in the response before using the edited text.
  5. Log the original and the edit so a human can review changes.

Prompt for your agent

Send the text in <path-to-text> to https://mcp.zero-slop.ai/v1/deslop as JSON with genre professional, then return the status and the edited text. Verify that the status field is approved before the output is used.

Caveat. The shared free capacity accepts up to 20,000 Unicode code points per request, so longer documents need to be split before sending.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for manavmishra/ZeroSlop and "Call the REST API to edit text in a publishing pipeline"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer