mlava

6 mods across 2 repositories, 9 stars between them.

scholar-sidekick

01

mlava/scholar-sidekick-mcp

Plugin Claude Code

Citation-integrity tooling for Claude Code: catch AI-fabricated citations, check retractions and open access, and format or export any scholarly identifier.

8 9d ago A tokens not measured original MIT

scholar-sidekick

02

mlava/scholar-sidekick-mcp

Plugin Claude Code

Catch AI-fabricated citations: verifyCitation cross-checks a claimed title against the real record at its identifier, detecting the dominant real-DOI + invented-title pattern (Topaz et al., Lancet 2026) that simple DOI resolution cannot catch. Also checks retraction and open-access status, and resolves eight…

8 9d ago A tokens not measured original MIT

scholar-sidekick

03

mlava/scholar-sidekick-mcp

Skill Claude CodeCodex

This skill should be used when the user mentions a scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcode, WHO IRIS URL) and wants structured metadata, a formatted citation, a bibliography export file, a retraction check, an open-access check, or verification that a claimed citation is real (not…

8 9d ago A 153 tokens original MIT

mlava/scholar-sidekick-mcp

MCP server Claude CodeCodexCursor +2

Catch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles. Runs locally from the scholar-sidekick-mcp npm package.

8 9d ago A tokens not measured original MIT

agent-ready

05

mlava/agent-ready-mcp

Skill Claude CodeCodex

This skill should be used when the user wants to check how readable a website is to AI agents (ChatGPT, Claude, Perplexity, Google Gemini, MCP clients). Activates for "scan this site for AI readability", "check my llms.txt", "audit our agent-readability", "is my MCP server card valid", "what's our Vercel Agent…

1 10d ago A 122 tokens original MIT

agent-ready-mcp

06

mlava/agent-ready-mcp

MCP server Claude CodeCodexCursor

Scan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests. Runs locally from the agent-ready-mcp npm package. Needs 1 environment variable to run.

1 10d ago A tokens not measured original MIT