# Pain in the Agent (mcpb · painintheagent-mcp-0.2.0.mcpb)

Humanize, rewrite and analyze prose with one shared Pain in the Agent account allowance.

- Trust score: 50/100 (low)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- mcpb · `painintheagent-mcp-0.2.0.mcpb`: 50/100 (this document), [markdown](https://verifymcp.io/servers/krllagent-painintheagent-mcp/https-github-com-krllagent-painintheagent-mcp-releases-download-v0-2-0-paininthe.md), [page](https://verifymcp.io/servers/krllagent-painintheagent-mcp/https-github-com-krllagent-painintheagent-mcp-releases-download-v0-2-0-paininthe)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/krllagent/painintheagent-mcp/releases/download/v0.2.0/painintheagent-mcp-0.2.0.mcpb`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 13/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
  - No install/post-install scripts declared.
  - Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 711 tokens (~101/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 85% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

- Download bundle: `https://github.com/krllagent/painintheagent-mcp/releases/download/v0.2.0/painintheagent-mcp-0.2.0.mcpb`

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-21 (score 50, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 49, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 48, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-10 (score 44)

First indexed and scored.

## MCP tools (7)

### `start_rewrite` (~149 tokens)

Start a text watermark rewrite

Rewrite 100–10,000 characters through Pain in the Agent, with fidelity checks. Sends text to the hosted service; successful runs use the shared free account quota. Returns a run_id promptly. Keep the MCP process open and call get_rewrite after 15 seconds. No private-key watermark guarantee. Use only for text the user asked to process.

Input parameters:

- `run_id` (string): Optional lowercase UUID for idempotency. Reusing the same ID and input cannot start another model run.
- `slop_removal` (boolean): Also remove formulaic AI phrasing. Off by default.
- `text` (string, required): The complete text to rewrite. Do not include secrets or unrelated files.

### `get_rewrite` (~74 tokens)

Read rewrite progress or result

Read a previous run by its run_id. Does not start or retry model processing and does not consume rewrite quota. A pending result includes a suggested polling interval. Keep the existing process open while it works.

Input parameters:

- `run_id` (string, required): The run_id returned by start_rewrite. Reuse it to retrieve that run.

### `get_limits` (~43 tokens)

Read the shared free account limits

Read this account's character limit and monthly successful-run usage, shared with the website. Does not rewrite text or consume rewrite quota. Running requests also reserve slots until they finish.

### `start_humanize` (~106 tokens)

Humanize AI writing

Make targeted style edits with source checks. Optional watermark_removal adds deep rewriting. Uses one shared run, stores submitted text, and returns a run_id. Read with get_result. No private watermark guarantee.

Input parameters:

- `run_id` (string): The run_id returned by start_rewrite. Reuse it to retrieve that run.
- `text` (string, required): 100–10,000 Unicode characters of prose the user asked to process.
- `watermark_removal` (boolean)

### `start_watermark_comparison` (~100 tokens)

Compare a source and rewrite

Compare source_text and candidate_text for meaning changes. Uses one shared run and stores both supplied texts. This does not detect Claude or Gemini private watermarks. Read with get_result.

Input parameters:

- `candidate_text` (required)
- `run_id` (string): The run_id returned by start_rewrite. Reuse it to retrieve that run.
- `source_text` (string, required): 100–10,000 Unicode characters of prose the user asked to process.

### `start_ai_detection` (~97 tokens)

Check AI writing signals

Inspect at least 80 words of English or Russian prose for AI-like writing patterns. Shows quoted evidence, not a calibrated authorship probability. Uses one shared run and stores the text. Read with get_result.

Input parameters:

- `run_id` (string): The run_id returned by start_rewrite. Reuse it to retrieve that run.
- `text` (string, required): 100–10,000 Unicode characters of prose the user asked to process.

### `get_result` (~54 tokens)

Read a text tool result

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

Input parameters:

- `run_id` (string, required): The run_id returned by start_rewrite. Reuse it to retrieve that run.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/krllagent-painintheagent-mcp/https-github-com-krllagent-painintheagent-mcp-releases-download-v0-2-0-paininthe#diagnostics

## Score history

- 2026-09-21: 50
- 2026-09-20: 49
- 2026-09-19: 49
- 2026-09-18: 48
- 2026-09-17: 44
- 2026-09-16: 44
- 2026-09-15: 44
- 2026-09-14: 44
- 2026-09-13: 44
- 2026-09-12: 44
- 2026-09-11: 44
- 2026-09-10: 44

## Common questions

### What is the Pain in the Agent MCP server?

Pain in the Agent is an MCP server listed in the public MCP registry as io.github.krllagent/painintheagent-mcp. Humanize, rewrite and analyze prose with one shared Pain in the Agent account allowance. This page covers its MCPB bundle (https://github.com/krllagent/painintheagent-mcp/releases/download/v0.2.0/painintheagent-mcp-0.2.0.mcpb).

### Is the Pain in the Agent MCP server safe to use?

Pain in the Agent scores 50 out of 100 on VerifyMCP. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Pain in the Agent MCP server expose?

Pain in the Agent exposes 7 tools: start_rewrite, get_rewrite, get_limits, start_humanize, start_watermark_comparison, and 2 more. Their descriptions and schemas cost roughly 623 tokens of context every time the server is loaded.

### What licence is the Pain in the Agent MCP server under?

Pain in the Agent declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/krllagent/painintheagent-mcp
- Website: https://painintheagent.com/integrations/
- Changelog RSS feed: https://verifymcp.io/servers/krllagent-painintheagent-mcp/https-github-com-krllagent-painintheagent-mcp-releases-download-v0-2-0-paininthe.xml
- Changelog JSON feed: https://verifymcp.io/servers/krllagent-painintheagent-mcp/https-github-com-krllagent-painintheagent-mcp-releases-download-v0-2-0-paininthe.json
- HTML version of this page: https://verifymcp.io/servers/krllagent-painintheagent-mcp/https-github-com-krllagent-painintheagent-mcp-releases-download-v0-2-0-paininthe