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.

24,030 servers 30,256 packages scanned 23 categories what changed → ecosystem stats → security signals →
Jprofiler npm
A
@ej-technologies/jprofiler-mcp

MCP server wrapper for JProfiler - Java profiling with AI agent integration

AI, Memory & Reasoning Score 93/100 4 findings 138/wk Cap. High
Expo Local Docs npm
A
expo-local-docs-mcp

MCP server for Expo documentation - reads local .mdx files for blazing fast performance. Works out of the box with zero configuration.

Learning & Documentation Score 93/100 1 finding 137/wk Cap. High
Clarifyprompt npm
A
clarifyprompt-mcp

Context-aware MCP prompt compiler with a composable pipeline: clarify_with_user → ground_prompt OR optimize_prompt → critique_prompt, all in one call via compose_prompt. Persistent memory, knowledge packs, explicit token-budget curation, reflective learni

Other Score 93/100 2 findings 136/wk Cap. High
Stellify npm
A
@stellisoft/stellify-mcp

MCP server for Stellify - AI-native code generation platform

Developer Tools Score 93/100 9 findings 136/wk Cap. High
Bash 3 implementations
A
best: bash-mcp

Simple bash command execution MCP server for Claude

Developer Tools Best score 93/100 7 findings 134/wk Cap. High
Chrome 4 implementations
A
best: chrome-mcp

Model Context Protocol (MCP) server for controlling Google Chrome browser on macOS. Enables AI assistants like Claude to automate Chrome via DevTools Protocol.

Browser Automation Best score 93/100 4 findings 133/wk Cap. High
Squish Memory npm
A
squish-memory

AI memory system for coding agents. Local-first MCP runtime with connectors (Google Drive, GitHub, Slack, Notion), knowledge graphs, decay scoring, and multi-tier deployment. Free locally, paid Cloud for sync and teams.

AI, Memory & Reasoning Score 93/100 12 findings 133/wk Cap. High
X402 Trust npm
A
x402-trust-mcp

MCP server for x402 endpoint trust & reliability data. Free ecosystem stats, leaderboard, trust preview, and watch polling; paid per-endpoint trust scores, bulk scoring, endpoint history, and 30-day watches over x402, with optional auto-pay. Backed by x40

API Development Score 93/100 6 findings 133/wk Cap. High
Strava Mcp Unofficial npm
A
strava-mcp-unofficial

Unofficial local-first Strava MCP server for AI training and performance agents.

Developer Tools Score 93/100 1 finding 132/wk Cap. High
Tdmcp npm
A
@dpantani/tdmcp

tdmcp — the TouchDesigner MCP server. Build real TouchDesigner visual systems from plain language with Claude, Cursor, or Codex (Model Context Protocol).

Design & Media Score 93/100 4 findings 132/wk Cap. High
Check npm
A
@golproductions/check-mcp

Less hallucinations. A command firewall for AI agents: validates every shell command before execution, so fabricated commands are denied before they run.

Security & Testing Score 93/100 1 finding 131/wk Cap. High
Kanban Lite npm
A
kanban-lite

Kanban board manager - VSCode extension, CLI, MCP server, and standalone web app

Productivity & Workflow Score 93/100 18 findings 131/wk Cap. High
Erdl npm
A
@openoba-ai/erdl-mcp

ERDL rules as an MCP Server — deterministic rules that give your Agent muscle memory

Developer Tools Score 93/100 3 findings 130/wk Cap. High
KubeView npm
A
kubeview-mcp

Read-only server enabling code-driven AI analysis of Kubernetes clusters.

Cloud & DevOps Score 93/100 7 findings 130/wk Cap. High
Agent Coord npm
A
agent-coord-mcp

File-backed MCP server for coordinating multiple AI coding agents (Claude Code, Cursor, Cline, etc.). Local stdio or networked over Streamable HTTP.

Data Science & ML Score 93/100 10 findings 129/wk Cap. High
Tracepulse npm
A
tracepulse

Runtime feedback MCP server for AI coding agents. ViewGraph sees the UI - TracePulse feels the backend.

Developer Tools Score 93/100 15 findings 129/wk Cap. High
Logbook npm
A
@cocaxcode/logbook-mcp

Developer logbook MCP server. Notes, TODOs, reminders, code TODOs over an Obsidian vault. 5 consolidated MCP tools + native CLI. Auto-wikilinks, layered config, Orama search. Works with Claude, Cursor, Windsurf, Copilot, Gemini, Codex.

Productivity & Workflow Score 93/100 1 finding 128/wk Cap. High
Oss Autopilot npm
A
@oss-autopilot/mcp

MCP server for OSS Autopilot — exposes PR tracking, issue discovery, and contribution management as MCP tools

Other Score 93/100 5 findings 128/wk Cap. High
Puppeteer Real Browser 2 implementations
A
best: puppeteer-real-browser-mcp-server

Detection-resistant browser automation aimed at safely driving real browsers.

Browser Automation Best score 93/100 2 findings 128/wk Cap. High
Smart Terminal npm
A
smart-terminal-mcp

MCP PTY server providing AI agents with real interactive terminal access

Developer Tools Score 93/100 8 findings 128/wk Cap. High
Tokenhub npm
A
tokenhub-mcp

A token-disciplined developer MCP hub with a tiny always-loaded surface and deferred internal capabilities.

Developer Tools Score 93/100 6 findings 128/wk Cap. High
Obsidian Mcpx npm
A
obsidian-mcpx

Extended MCP server wrapping the Obsidian CLI — 82 tools for full vault control

Productivity & Workflow Score 93/100 2 findings 127/wk Cap. High
Sonarlint Source verified npm
A
@nielspeter/sonarlint-mcp-server

MCP server providing SonarLint code analysis for Claude Desktop and other MCP clients

Developer Tools Score 93/100 2 findings 127/wk Cap. High
Chain Of Thought npm
A
mcp-chain-of-thought

Chain of Thought is a tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavi

AI, Memory & Reasoning Score 93/100 2 findings 126/wk Cap. High