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.
Contextual blast-radius scoring for shell commands an AI agent is about to run
Automate Blender workflows with external Python control, background operation, and LLM integration
Control Blender from Claude and other LLMs through the Model Context Protocol
MCP server that gives vision and image generation capabilities to text-only LLMs, running 100% locally
The External Brain for AI Coding Agents — see what your LLM can't see. Provides instant, structured intelligence about your entire codebase without reading files into the AI's context window.
MCP-native release confidence control plane for web apps
A local-first multi-source RAG MCP server — search across Obsidian vaults, Git repos, and PDFs from Claude / Cursor / Claude Desktop.
Privacy-first SQL compiler and MCP server — deterministic semantic layer for agentic database workflows
Context engineering for AI agents — persistent memory, knowledge graph, affect tracking, and MCP server. Single SQLite file, zero LLM cost.
Persistent memory MCP server for AI agents — 13 tools, semantic search, knowledge graph, on-device SQLite
Brainstem — local-first knowledge backend for AI agents. Connect any MCP host (Claude Code, Cursor) to an Obsidian-compatible wiki with indexed retrieval, token-budgeted recall, and secure ingestion.
Stop Claude from using banned brand terms. Automatic brand voice enforcement for Claude Code — PostToolUse hook, MCP server, and CI pipeline check.
MCP for Unity Server: A Unity package for Unity Editor integration via the Model Context Protocol (MCP).
Local MCP broker for sharing upstream MCP servers across MCP clients
Multi-client debug-probe broker MCP server — session lifecycle, probe operations, ITM/SWO trace, and lane supervision over three concurrent transports
MCP server for browser automation with Set of Marks (SoM) - AI agents can see and interact with web pages using numbered element IDs
Guard your dependency bumps: an MCP server that tells your AI agent exactly which parts of YOUR code break when you upgrade a dependency, and verifies AI-written code against the API that's actually installed — by static analysis, never by running third-party code.
Knowledge-lifecycle MCP: distill agentsync + context-keeper events into memory, recall across projects, promote local -> team -> org
A server that exports Camel toolkits as MCP-compatible tools
MCP server for Canadian federal government data — bilingual, multi-source, AI-ready.
MCP server for persisting learnings from Copilot conversations - no API key required
Unified web, code, and webpage search for MCP agents and terminal workflows
Declarative MCP server for the Cartograph widget library
Persistent memory, self-evolving playbooks, and sandboxed REPL for AI agents