{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_pv7f5r6wu84t","handle":"humanizer-mcp","url":"https://wellknown.network/agents/humanizer-mcp","links":{"self":"https://wellknown.network/agents/humanizer-mcp/record.json","html":"https://wellknown.network/agents/humanizer-mcp","markdown":"https://wellknown.network/agents/humanizer-mcp/record.md","api":"https://wellknown.network/api/v1/agents/humanizer-mcp","status":"https://wellknown.network/api/v1/agents/humanizer-mcp/status","claim":"https://wellknown.network/agents/humanizer-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/humanizer-mcp/claim.json","badge":"https://wellknown.network/agents/humanizer-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/humanizer-mcp/history","tools":"https://wellknown.network/api/v1/agents/humanizer-mcp/tools"},"ard":{"identifier":"urn:air::server:humanizer-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"humanizer-mcp","summary":"MCP server for analyzing and humanizing AI-generated text to bypass AI detection.","description":"# humanizer-mcp\n\n[![PyPI version](https://img.shields.io/pypi/v/humanizer-mcp.svg)](https://pypi.org/project/humanizer-mcp/)\n[![npm version](https://img.shields.io/npm/v/humanizer-mcp.svg)](https://www.npmjs.com/package/humanizer-mcp)\n[![Python versions](https://img.shields.io/pypi/pyversions/humanizer-mcp.svg)](https://pypi.org/project/humanizer-mcp/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![CI](https://github.com/aousabdo/humanizer-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/aousabdo/humanizer-mcp/actions/workflows/ci.yml)\n\nAn MCP (Model Context Protocol) server that measures AI-detection risk in a piece of text and tells you — line by line — what to change. Works with Claude Code, Claude Desktop, and any MCP-compatible client.\n\n> **Just want to use it?** Go to **[humanizer.analyticadss.com](https://humanizer.analyticadss.com)** — copy the URL, paste it into Claude's Connectors, done. The rest of this README is for developers and people self-hosting.\n\nRather than running your prose through a black-box \"humanizer,\" this server analyzes it against known detection signals (vocabulary, burstiness, contraction usage, paragraph uniformity, em dashes, first-person voice) and returns a structured report with a 0–100 risk score and a concrete rewrite plan. The actual rewriting is left to the LLM that's driving the conversation — which is the point: a planner, not a laundering service.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `humanizer_humanize_text` | **Returns the rewritten text.** Applies vocabulary swaps, phrase removal, contractions, em-dash cleanup, plus before/after scores. The LLM caller polishes for context. |\n| `humanizer_analyze_ai_tells` | Full analysis with risk score, fix recommendations, *and* a mechanical rewrite as a starting point. |\n| `humanizer_quick_vocab_scan` | Fast word- and phrase-level scan with replacement suggestions. |\n| `humanizer_get_rewrite_instructions` | Step-by-step rewrite …","publisher":null,"homepage":"https://github.com/aousabdo/humanizer-mcp","repository":"https://github.com/aousabdo/humanizer-mcp/blob/main/CHANGELOG.md","version":"0.2.0","license":"MIT","protocols":["mcp"],"tags":["ai-detection","anthropic","claude","fastmcp","humanizer","llm","mcp","model-context-protocol","text-analysis"],"pricing":null,"endpoints":[{"url":"pypi:humanizer-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":1,"provenance":"derived"}],"categories":["dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"humanizer-mcp","registry":"pypi","observedAt":"2026-11-09T07:25:05.419Z","publishedAt":"2026-04-27T19:57:42.784521Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"humanizer-mcp","url":"https://pypi.org/project/humanizer-mcp/","firstSeenAt":"2026-09-09T17:21:35.817Z","fetchedAt":"2026-11-09T07:23:16.115Z","normalizedAt":"2026-11-09T07:23:16.115Z"}]},"firstSeenAt":"2026-09-09T17:21:35.817Z","updatedAt":"2026-11-09T07:25:05.420Z"}