proofread-mcp
Related Servers
Alternatives to proofread-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceEnables US case law search, citation parsing, practice management via Clio, and federal court filings through PACER.-
- AlicenseNot gradedqualityDmaintenanceValidates legal citations against the CourtListener database to detect hallucinated citations in legal documents.5MIT
- FlicenseNot gradedqualityBmaintenanceDeterministic legal citation verification for AI-generated legal briefs. Three-layer verification: CourtListener database lookup, quote-match against primary source, and LLM edge-case verification. Free tier available.-
- AlicenseNot gradedqualityDmaintenanceEnables Claude Code to index and semantically search through PDFs, code, and documents with exact citations and zero hallucinations.MIT
- FlicenseAqualityDmaintenanceEnables Claude Desktop to search the CanLII Canadian legal database and retrieve the full text of matching legal documents.1-
- AlicenseNot gradedqualityCmaintenanceEnables secure access to legal documents from Clio via Claude Desktop, with local processing and semantic search to ground AI responses in actual documents.12 npm29Mozilla Public 2.0
TDQS
Scored across 6 tools
Tools form two near-identical pairs: check_citations/check_document (text vs file) and resolve_citation/resolve_citations (single vs batch). The descriptions explicitly direct usage and distinguish them, so ambiguity is low but not zero.
Most tools follow a clear verb_noun snake_case pattern: check_citations, check_document, resolve_citation, resolve_citations, render_report. 'coverage' breaks the pattern by being a bare noun, though it is still readable and consistent in style.
Six tools is well-scoped for the server's purpose: checking prose, checking a file, single lookup, batch lookup, coverage information, and report rendering. No tool is redundant padding and nothing essential seems missing.
The core workflow of checking citations, resolving individual citations, and rendering reports is complete. Minor gaps exist: deep-support checking is opt-in/quota-limited, and resolve_citations output cannot be passed directly to render_report.