Search

An MCP server for reading, explaining, and editing Line 6 Helix Stadium (.hsp) presets. Independent/unofficial; not affiliated with Line 6 or Yamaha Guitar Group.

Read-only MCP server for verified book recommendations and reading lists.

Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation

Verified migration maps for AI agents: what breaks between library versions and how to fix it

Local-first DOCX formatter for academic papers with a content-fingerprint integrity guard.

MIND Protocol MCP server — policy runtime and proof layer for autonomous agents

MCP wrapper around Apache Tika for document parsing and metadata extraction.

An MCP server for the Shopline Open API, providing AI-callable tools for e-commerce analysis and operations.

MCP server controlling Microsoft Outlook desktop via the Win32 COM API

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

The local, zero-cost merge queue for parallel Claude Code agents. Plugs into Claude Code's native worktree isolation; one build at a time, one landing at a time, zero races.

Tock (exploretock.com) MCP server for Claude — developed and maintained by AI (Claude Code)

Cloud-authenticated Model Context Protocol server for a Proof workspace. Logs into the user's Proof account and lets any MCP client (Claude Desktop, Claude Code, Cursor, custom agents) read and write the same workspace the webapp uses. Ideation, Agent, an

Unified SmartMemory MCP server — tiered tools, local + remote backends

https://github.com/erinheit451/supplement-advisor-mcp

Fully local semantic memory for AI agents: search your notes and session logs from any MCP client, with embeddings served by Ollama

Model Context Protocol (MCP) server for Garmin Connect

MCP server that exposes the CuratedMCP catalog — search risk-classified MCP servers, check verification status, and pull risk/capability details, from inside any MCP client.

Use the best model for every task — automatically. Multi-provider LLM router for Claude Code. Picks the right model based on what you are doing: coding, writing, reasoning. 25+ platforms (DeepSeek, Qwen, GLM, Gemini, Claude, GPT), one API key. Save 40-70%

MCP server exposing the deterministic engineering layer of code review as tools for host agents (Claude Code, Codex, Devin). The server never calls an LLM.