Every server below was scanned with the same deterministic engine that powers the MCP Trust Checker CLI and free API. The A–F Trust Score answers one question — how safe is this server for you to adopt: it starts from the threat score of its published code, then adjusts down for the capability blast radius, how strongly the publisher is verified, and how much of the package the scan could actually see. No pay-to-list, no self-reported ratings, and every point is itemised with its evidence.
Local MCP server bridge for Paste — give Claude Desktop, Claude Code, Cursor, Codex, and other AI tools access to your Mac clipboard history and pinboards.
Space Bus — workspace agent bus for OpenCode. One control agent tasking per-project agents over the OpenCode server API, with an MCP facade for Claude Desktop.
Agent-friendly MCP wrapper for x402engine with automatic capped USDC payments on Base and Solana
Use your Claude Pro/Max subscription on your Obsidian vault. MCP connector that reads your markdown and proposes writes back, with all inference paid for by your existing subscription.
Local-first security check MCP server for AI coding agents — finds hardcoded secrets, exposed .env files, secrets in git history, and vulnerable dependencies in your workspace, entirely on your machine.
OKF-compatible memory for AI coding agents — identity, work-ledger and kanban in one plain-markdown bundle, git-native, zero-infra.
Use as many MCP servers as you want while minimizing context usage. A code mode MCP server gateway driven with Lua 🌙
MCP Server for Slima - AI Writing IDE for Novel Authors. Connect your books with Claude, ChatGPT, Gemini, Cursor, and any MCP-compatible AI tool.
Dazzle CLI — cloud stages for AI agents and live streaming
MCP server for Runrun.it API - Tasks, Comments, Projects
Veris — Behavioral Verification Infrastructure. MCP-native verification intelligence layer for autonomous coding agents.
aiglare: audit AI/LLM features in any JS/TS codebase for governance guardrails. Finds where model output reaches users or side-effects without confidence handling, fallbacks, validation, or human-in-the-loop.
MCP server that keeps the books for your personal and business finances using double-entry accounting — import bank CSVs, categorize spending, reconcile, and generate US Schedule C tax reports, all driven from your LLM.
Heimdall — a security scanner for Model Context Protocol (MCP) servers. Vet a server, or a whole agent config, before your agent trusts it.
The shape-shifting MCP hub — shapeshift() into 130,000+ MCP servers at runtime. One entry point, no restarts, 7 registries.
MCP server for Paragraph — expose your publication to AI agents
MCP server exposing PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents.
Provides Terraform cost, lint, security, and cloud best-practice guidance.
Persistent memory MCP server for AI coding agents
Safe MCP server for Plastic SCM and Unity Version Control (cm 10.0.16.6656+, UVCS 11.x) source-control workspaces.
Standalone Model Context Protocol (MCP) server for Ag-Bash — a sandboxed bash environment with 70 agentic tools (run_bash, semantic code edit/diff/analyze, WASM Python/JS, task & worktree management) over stdio JSON-RPC.
MCP Server for AI code quality automation
[](https://badge.fury.io/js/@pokutuna%2Fmcp-chrome-tabs)
MCP server for Dev Proxy that enables AI assistants to interact with Dev Proxy.