Skip to content
Agentmart
Submit a tool

Pain in the Agent

Remove text watermarks, humanize and check AI writing with your Pain in the Agent account.

Connector by krllagent · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Desktop. Read the repository before you give any tool access to your data.

Download the bundle

MCP bundle (.mcpb): open it with Claude Desktop.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Remove text watermarks, humanize and check AI writing with your Pain in the Agent account.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
3 read · 2 write · 2 delete
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Downloaded binary

Tools by what they do 7

Read from the source code; the running server may list different tools.

Read 3 · Look things up without changing anything.

  • get_limits
  • get_result
  • get_rewrite

Write 2 · Create, change, send or run things.

  • start_ai_detection
  • start_watermark_comparison

Delete 2 · Delete, drop, revoke or wipe things.

  • start_humanize
  • start_rewrite

Network hosts it talks to 1

  • github.com · found in install command

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • get_limitsRead the account allowanceread-only

    Read the account's character allowance shared with the website and the remote MCP: characters used and remaining in the paid month, the per-text limit and when the month ends. Does not use characters. Running requests reserve their characters until they finish.

  • get_resultRead a text tool resultread-only

    Read progress or a result by run_id for any text tool. Never starts model work or uses characters.

  • get_rewriteRead rewrite progress or resultread-only

    Read a previous run by its run_id. Never starts or retries model work and never uses characters. A pending result includes a suggested polling interval. Keep the existing process open while it works.

  • start_ai_detectionCheck for AI writing

    Score prose with a trained AI detector (0-100) and highlight AI-writing patterns with quoted passages. At least 80 words; fullest coverage for English. Results do not prove authorship. Free: counts toward the separate daily limit of checks, not the character allowance. Without a plan it takes texts of up to 1,000 characters; with the plan, up to 10,000. Stores the text. Read with get_result.

  • start_humanizeHumanize and remove the watermark

    Humanize AI text and remove its statistical watermark by replacing the wording throughout, with source checks and before-and-after AI scores. A successful run uses the input character count from the account's monthly plan. Stores the submitted text and returns a run_id; read it with get_result. Complete watermark removal cannot be verified.

  • start_rewriteRemove a text watermark

    Rewrite 100–10,000 characters to remove a statistical text watermark: one rewrite by one model that is instructed to keep the meaning, structure and formatting. A successful changed result uses the input character count from the account's monthly plan; a rewrite that fails its checks is not charged. Returns a run_id promptly. Keep the MCP process open and call get_rewrite after 15 seconds. Complete removal cannot be verified. Use only for text the user asked to process.

  • start_watermark_comparisonCompare a source and rewrite

    Compare source_text and candidate_text for meaning changes. This does not detect ChatGPT, Claude or Gemini watermarks. Free: counts toward the separate daily limit of checks, not the character allowance. Without a plan it takes texts of up to 1,000 characters; with the plan, up to 10,000. Stores both texts. Read with get_result.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Oct 21, 2026 (8 days ago)
Last release
Oct 21, 2026 (8 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.krllagent/painintheagent-mcp
Version
0.3.2
Auth
No auth
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Cite this page

Pain in the Agent MCP server. Agent Mart. https://agentmart.dev/connectors/krllagent-painintheagent-mcp (last updated 2026-10-24)