sentence_analysis

MCP tool from Writing Tools MCP by wdm0006

(list): Per-sentence analysis with z-scores

How to use it

sentence_analysis is exposed by the Writing Tools MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the sentence_analysis tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Writing Tools MCP

$uvx --from git+https://github.com/wdm0006/writing-tools-mcp writing-tools-mcp

FULL WRITING TOOLS MCP LISTING

Other tools in Writing Tools MCP (12)

baseline

(str, optional, default="browncorpus"): Baseline corpus name for comparison.

doc_burstiness

(float null): Burstiness score (standard deviation of sentence perplexities); null when fewer than two sentences were scored, since the standard deviation is undefined there

doc_ppl

(float null): Document-level perplexity score; null when no sentence could be scored

flags

(dict): AI detection flags with confidence and explanations

keyword

(str): The keyword or phrase to search for.

language

(str, optional, default="en"): Language code (only "en" supported currently).

level

(str, optional): Granularity of analysis. Options:

remove_stopwords

(bool, optional, default=True): Whether to exclude common English stopwords (e.g., 'the', 'a', 'is').

sentences

(list): Sentence-level perplexity scores

text

(str): The input text.

top_n

(int, optional, default=10): The number of top keywords to return.

z_scores

(dict): Z-scores of features against the baseline