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.
Parallel Codex MCP server with live task monitoring, batch wait, and full flag parity
Lightweight semantic code search engine — hybrid vector + FTS + AST graph + regex fusion + MCP server
Policy-as-code enforcement for AI agents with MCP, CEL, Git hooks, SARIF, and static-analysis guardrails.
Workspace-confined coding tools exposed as an MCP server.
Multi-agent orchestration with loop prevention, contribution scoring, and MCP integration
AI co-pilot for VFX artists using ComfyUI: 134 MCP tools across 6 swappable LLM providers (incl. any OpenAI-compatible endpoint), zero-LLM artist recipes, a default-deny safety gate, reversible LIVRPS edits, EXR-aware vision, workflow.lock provenance, and durable cross-session learning.
MCP server for compliance-trestle OSCAL framework
Cross-platform MCP server for computer automation and control
Enhanced MCP server for computer control: mouse, keyboard, screenshots, OCR, UI automation, region capture, accessibility-aware app launching. Fork of computer-control-mcp with major perception and automation improvements.
Model Context Protocol Server via Cross-Platform (Mac & Windows) Split Screen Functions
Production-ready MCP server providing AI-powered web browsing automation using Gemini 2.5 Computer Use API
Multi-model panel orchestration engine with an MCP adapter. The engine (consult.*) is MCP-free and usable as a library; the MCP adapter (consult.mcp.*) is an optional extra.
MCP server that hosts isolated Strands AI agents in Docker containers
Context Lens - Give your LLM glasses to understand meaning, not just read words. Semantic search for AI assistants.
Local-first CLI and MCP server for AI coding context — minimum useful context, maximum agent performance
Unified local search and indexing for Claude and other AI tools
Token-level context compression for LLM and agent workflows.
ContextForge AI Gateway — an AI gateway, registry, and proxy for MCP, A2A, and REST/gRPC APIs. Exposes a unified control plane with centralized governance, discovery, and observability. Optimizes agent and tool calling, and supports plugins.
Universal AI memory layer - cross-client, cross-repo context management with RAG
Durable, hybrid (structural + semantic) memory for AI agents and humans. Local-first, zero external services. Guided `cos setup` wizard + Sim-OS. v0.9: import ChatGPT/Claude history, export rules to CLAUDE.md/AGENTS.md/Cursor, RaaS usage metering, monetization-map builder.
Model Context Protocol server for Coros with first-class running workout authoring, scheduling, and editing on top of training data, sleep, HRV, and activity exports.
MCP server for querying and managing Azure Cosmos DB
Search and browse Claude conversation history with hybrid search (FTS + Spotlight + vector embeddings)
Claude Code MCP server for C++ debugging with GDB and clangd