竞品内容 Pattern 雷达 · AI 答案里的重复说法 — Claude Code MCP server
Examines AI answers and rival copy to detect repeated phrases, quoted sources, and formulaic text. Helpful for auditing LLM response uniformity.
Open on GitHubWhat 竞品内容 Pattern 雷达 · AI 答案里的重复说法 does
The pattern-radar server processes raw text answers from JSON arrays or geo-monitor records. It relies on character-level n-grams, expanding high-frequency fragments outward into full terms. Alongside repeated wording, the engine tracks brand share, extracts cited web domains, and calculates pairwise response similarity.
Thresholds derive from a null-hypothesis simulation. The tool scrambles characters across the corpus while preserving length and character counts, picking the p95 baseline to eliminate accidental patterns. It runs with zero external Python dependencies in read-only mode, ignoring template placeholder domains automatically.
Corpora under 12 samples trigger an immediate rejection, preventing skewed metrics from tiny datasets. The logic does not perform semantic clustering, meaning synonymous expressions with different characters remain unmerged.
What it helps with
- Find recurring formulaic phrases across generated model answers
- Extract cited domains to determine primary information sources
- Measure duplicate rate and wording fixation for identical prompts
- Track competitor brand visibility and positioning within LLM output
Example prompts for the agent
- Use pattern-radar to analyze recurring phrasing in our collected answer dataset
- Run self_check via pattern-radar before running the main analysis
- Call explain_method to view the statistical thresholds and corpus boundaries
How to install 竞品内容 Pattern 雷达 · AI 答案里的重复说法
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about 竞品内容 Pattern 雷达 · AI 答案里的重复说法
How to install 竞品内容 Pattern 雷达 · AI 答案里的重复说法?
Set up the remote endpoint in your MCP configuration under pattern-radar using https://savantcat.cn/mcp-radar. For offline execution, launch python server.py directly from the repository.
What does this MCP server do?
It detects recurring phrasing, extracts cited domains, and measures how repetitive answers are across a collection of AI responses.
What input constraints apply to the analysis?
The engine rejects datasets with fewer than 12 answers to prevent false signals. It works on exact character matching without semantic merging, and current baselines target short Chinese texts.
