"Shell" matching MCP servers:

Audits AI-bot visibility: robots.txt per-bot for 22 AI user-agents (GPTBot/ClaudeBot/PerplexityBot/etc), Cloudflare flags, JSON-LD, sitemap, llms.txt, SPA shell, plus cross-model brand mentions via Perplexity + OpenRouter. 0-100 score. SSRF-guarded, spend-capped.

MCP security server with 7 tools: command safety check, prompt injection detection (32+ rules, zh+en), PII/sensitive data scanning, file path protection, tool policy enforcement, response auditing, and security status. 8-layer defense, zero dependencies.

A read-only MCP server that exposes AI Disk Doctor Core's scan, model inventory, and history tools via local stdio, with no mutation or shell capabilities.

Exposes each stage of the Champollion sulcal embedding pipeline as MCP tools, enabling agents to run, monitor, and debug the pipeline without manual shell commands.

A fully local persistent memory layer for LLM coding agents (Claude Code, Codex, Gemini CLI, OpenCode). A shell wrapper intercepts tool invocations, fires hooks on every tool call, then runs a 3-layer pipeline (extract → compress to ≤500-token digest → merge into project memory doc) at session end. The next session gets prior context injected automatically.

Bareun (바른) is a Korean natural-language engine. This MCP server lets any MCP-compatible client hand Korean text to a dedicated Korean engine instead of guessing: analyze_syntax (morphological analysis with 47 POS tags and beta homograph sense disambiguation), analyze_syntax_raw (raw model output), tokenize, correct_grammar (spelling and spacing correction), and list_pos_tags. Hosted at https://ap

Enables Claude Code to delegate tasks to free OpenRouter models as callable tools while keeping the Anthropic endpoint for the orchestrator, with optional sandboxed file and shell access.

Provides Korean spell checking and grammar correction via a single tool. It integrates into MCP clients like Cursor or Claude Desktop.

This MCP server bridges Claude Code with the Antigravity CLI (agy), allowing Claude to delegate tasks to Google Gemini models via configurable difficulty tiers. It verifies the actual backend model for every call, provides separate tools for safe ask/research vs. shell exec, and supports long-running background jobs.