MCP Trust Registry

Add server →

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.

24,032 servers 30,260 packages scanned 23 categories what changed → ecosystem stats → security signals →
Codemore Source verified npm
A
codemore

The static analyzer your AI agent reads — finds production-blocking bugs in vibe-coded apps (CLI, GitHub Action, MCP server).

Developer Tools Score 93/100 18 findings 428/wk Cap. High
Omniboard npm
A
@omniboard/mcp

Omniboard.dev MCP server that exposes agentic check runs and run progress for local agents.

Developer Tools Score 93/100 2 findings 427/wk Cap. High
System Brain npm
A
system-brain-mcp

MCP server that gives your coding agent a queryable, honest view of your own system — where code actually deploys, what's fabricated, what's open, whether the feedback loop closes, and what the evidence says to do next.

Developer Tools Score 93/100 3 findings 424/wk Cap. High
Webclaw 2 implementations
A
best: @webclaw/mcp

Zero-install launcher for the webclaw MCP server: web extraction and anti-bot access for AI agents. Runs `npx @webclaw/mcp`.

Browser Automation Best score 93/100 1 finding 424/wk Cap. High
Wenlan Source verified npm
A
wenlan-mcp

Local-first memory layer for AI agents - MCP server

Learning & Documentation Score 93/100 3 findings 422/wk Cap. High
Ituran npm
A
ituran-mcp

Stdio MCP server exposing the Ituran Global V2 API as MCP tools. Mints and refreshes its own access tokens via identity-server-v1 from credentials in env vars; tokens never reach the LLM.

Other Score 93/100 1 finding 415/wk Cap. High
Package Registry npm
A
package-registry-mcp

MCP server for searching and getting up-to-date information about NPM, Cargo and NuGet packages.

Other Score 93/100 1 finding 414/wk Cap. High
Lasso npm
A
lasso-mcp

Claude Code 的全交互对外抓手 MCP —— 搜/抓/登录态抓/控桌面,四通道+多引擎 fallback+AES cookie+markdown 抽取。All-in-one interaction MCP for Claude Code.

Web, Search & Scraping Score 93/100 12 findings 412/wk Cap. High
Memesh Source verified npm
A
@pcircle/memesh

MeMesh — Local memory for Claude Code and MCP coding agents. One SQLite file, zero cloud required.

Security & Testing Score 93/100 15 findings 409/wk Cap. High
Google Surf npm
A
google-surf-mcp

MCP server for Google search via warm Chrome profile. No API key.

Web, Search & Scraping Score 93/100 3 findings 408/wk Cap. High
Squish npm
A
@getsquish/squish

Give AI random access to video: timestamped contact sheets + zoom into any start/end range, on-device. CLI + MCP server (getsquish.app).

Design & Media Score 93/100 1 finding 406/wk Cap. High
Secure Env Elicit npm
A
@grec0/mcp-secure-env-elicit

MCP wrapper that launches other MCP servers with secret env vars collected interactively via elicitation — placeholders in config, values held AES-encrypted in memory, never on disk.

Security & Testing Score 93/100 3 findings 405/wk Cap. High
Omnifocus Mcp Enhanced npm
A
omnifocus-mcp-enhanced

🚀 NEW: Native Custom Perspective Access! Enhanced MCP server with OmniFocus custom perspective support, hierarchical task display, AI-optimized tool selection, and comprehensive task management

Productivity & Workflow Score 93/100 2 findings 404/wk Cap. High
Callmux npm
A
callmux

Multiplexer for MCP tool calls — parallel execution, batching, caching, and pipelining for any MCP server

AI & Agents Score 93/100 1 finding 403/wk Cap. High
Repoctx Source verified npm
A
@nugehs/repoctx

repoctx: local repo discovery, indexing, catalog search, and agent harnesses.

Developer Tools Score 93/100 6 findings 403/wk Cap. High
Writepanda npm
A
@writepanda/mcp

Model Context Protocol server for PandaStudio. Exposes the desktop video editor's automation surface to Cursor, Continue, Cline, Claude Desktop, and any MCP-compliant client.

Design & Media Score 93/100 5 findings 398/wk Cap. High
Mobile Agent npm
A
mobile-agent-mcp

Drive iOS sims, Android emulators, and USB devices via MCP or shell. Maestro flows, screenshots, logs, adb, simctl. MCP + CLI.

Security & Testing Score 93/100 2 findings 397/wk Cap. High
Vectros Ai npm
A
@vectros-ai/mcp-server

MCP server exposing Vectros hybrid search, structured records, and in-perimeter RAG/document-ask to MCP-aware desktop agents (Claude Desktop, Cursor, Code, Cline, Continue, VS Code).

Web, Search & Scraping Score 93/100 10 findings 395/wk Cap. High
Dot Ai npm
A
@vfarcic/dot-ai

AI-powered development productivity platform that enhances software development workflows through intelligent automation and AI-driven assistance

AI, Memory & Reasoning Score 93/100 5 findings 392/wk Cap. High
Zeph To npm
A
@zeph-to/mcp-server

Zeph MCP server — AI agent notifications, prompts, and input via MCP protocol

Developer Tools Score 93/100 1 finding 390/wk Cap. High
Orchestrate npm
A
mcp-orchestrate

MCP server that routes a coding task to a user-configured model tier (light/standard/heavy) with capability filtering and provably-safe cross-backend fallback. Backend-agnostic; you configure every model.

Developer Tools Score 93/100 1 finding 386/wk Cap. High
Sceneview npm
A
sceneview-mcp

MCP server for SceneView — cross-platform 3D & AR SDK for Android and iOS. Give Claude the full SceneView SDK so it writes correct, compilable code.

Developer Tools Score 93/100 3 findings 385/wk Cap. High
Livepilot npm
A
livepilot

Agentic production system for Ableton Live 12 — 467 tools, 56 domains, 44 semantic moves. Device atlas (5264 devices, 120 enriched, 7 indexes), Splice intelligence (gRPC + GraphQL describe-a-sound + preview + collections + presets), 9-band spectral percep

Productivity & Workflow Score 93/100 4 findings 381/wk Cap. High
Mcpgrade npm
A
mcpgrade

Lighthouse for MCP servers — lint your MCP server for agent usability, not just spec compliance

Developer Tools Score 93/100 1 finding 380/wk Cap. High