BitsBound MCP Serverofficial
A
licenseA
qualityD
maintenanceEnables AI-powered contract analysis with partner-level redlines and real OOXML Track Changes for Claude Desktop and Claude.ai.
12
284 npm
MIT
martins-humaniser
by MPavion
Related Servers
Alternatives to martins-humaniser
No user-submitted related servers found.
Related Servers
docuprivadoofficial
AlicenseNot gradedqualityAmaintenanceEnables Claude Desktop to redact and count personal data in PDFs and images, strip hidden metadata from photos, anonymize Word and text files, prepare watermarked ID copies, and compare contract versions using only user-approved local folders. All processing runs offline on the user's computer, creating new copies instead of modifying or deleting the originals.Apache 2.0- AlicenseNot gradedqualityDmaintenanceConnects Claude Desktop to Google Docs and Google Drive, enabling comprehensive document reading, writing, formatting, structuring, and complete Drive file management including shared drives support through OAuth 2.0 authentication.5 npm3MIT
mcp-upstageofficial
AlicenseBqualityAmaintenanceEnables AI assistants to extract and structure content from documents (PDFs, images, Office files) via Upstage AI's APIs, with seamless Claude Desktop integration.213MIT- AlicenseNot gradedqualityDmaintenanceEnables Claude Desktop to search and query personal document collections (PDF, Word, Markdown, text) using semantic search and conversational AI with full context preservation across exchanges.MIT
- AlicenseAqualityCmaintenanceClarity and memory for Claude. Persistent memory, intelligent context ranking, safety modes, and session checkpoints for Claude Desktop & Claude Code in a single install.2061 npm1MIT
TDQS
A3.6/5.0
Scored across 14 tools
Disambiguation4/5
Most tools occupy clearly distinct slots: extract vs save vs humanize_text vs humanize_file vs lint vs assess are separable, and the text/file suffix pattern makes the scope explicit. The one real collision is humanizer_compare versus humanizer_assess_pair, which both take an original and a rewrite and both report before/after scores plus a fact-faithfulness check; the descriptions differentiate them (deterministic lint vs blind model rubric) but an agent could easily grab the wrong one.
Naming Consistency5/5
Every tool uses the same humanizer_ prefix plus snake_case, and almost all follow a verb_noun shape (get_rules, lint_text, save_document, learn_from_edit, assess_file). The few noun-only names (status, voice_profile) are natural reads of read-only probes and do not break the pattern.
Tool Count4/5
Fourteen tools sits comfortably in the sensible range for a document-rewriting pipeline, and each one maps to a real pipeline stage. It is slightly heavy because the assess_* and humanize_* families triple up across text/file/pair, which produces redundancy around the compare/assess_pair overlap.
Completeness4/5
The lifecycle is largely covered end to end: read a document, inspect and load rules, rewrite inline or as a file, lint, assess, verify facts, save, then learn from hand edits and profile the author's voice. Gaps are minor: learned rules can only be removed phrase-by-phrase (no way to list or drop a whole learned rule), and there is no tool to manage or reset the voice sample folder.