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.

24,082 servers 30,376 packages scanned 23 categories what changed → ecosystem stats → security signals →
Rn Debug npm
A
rn-debug-mcp

RN Debug MCP server

Developer Tools Score 93/100 2 findings 1.2k/wk Cap. High
Getmarrow npm
A
@getmarrow/mcp

Runtime control, proof, and fleet intelligence for MCP-compatible AI agents.

AI & Agents Score 93/100 2 findings 1.2k/wk Cap. High
External Agents Source verified npm
A
@mrrlin-dev/external-agents

MCP server routing workloads across 20+ LLM providers with round-robin dispatch, cooldown-aware fallback, and quota-aware cost control.

Developer Tools Score 93/100 12 findings 1.2k/wk Cap. High
Secure 2 implementations
A
best: mcp-secure-server

Secure-by-default MCP server with 5-layer validation for defense-in-depth protection

Security & Testing Best score 93/100 6 findings 1.2k/wk Cap. High
Win Cli npm
A
@simonb97/server-win-cli

MCP server for Windows CLI interactions

Other Score 93/100 9 findings 1.2k/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 1.2k/wk Cap. High
Euclid 3 implementations
A
best: @euclid-tools/euclid

Deterministic math tools for LLMs — an MCP server and Claude Code plugin powered by mathjs

Developer Tools Best score 93/100 1 finding 1.2k/wk Cap. High
Skyramp npm
A
@skyramp/mcp

Skyramp MCP (Model Context Protocol) Server - AI-powered test generation and execution

Data Science & ML Score 93/100 11 findings 1.1k/wk Cap. High
Pnp Cli Microsoft365 npm
A
@pnp/cli-microsoft365-mcp-server

Model Context Protocol (MCP) server for CLI for Microsoft 365 that allows to use natural language to manage your Microsoft 365 tenant.

Other Score 93/100 4 findings 1.1k/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 1.1k/wk Cap. High
Google Health Mcp Unofficial npm
A
google-health-mcp-unofficial

Unofficial local-first Google Health API v4 MCP server for AI health, sleep and activity agents.

Data Science & ML Score 93/100 1 finding 1.1k/wk Cap. High
Webcake Landing npm
A
webcake-landing-mcp

MCP server exposing Webcake landing-page element schemas + AI usage hints, and persisting LLM-generated page sources to a Webcake backend.

Developer Tools Score 93/100 3 findings 1.1k/wk Cap. High
Lean Ctx Bin Source verified npm
A
lean-ctx-bin

LeanCTX — the Context OS for AI coding agents. One local binary that compresses, remembers, routes, and verifies every token between your code and the model. No Rust required.

Productivity & Workflow Score 93/100 4 findings 1.0k/wk Cap. High
Noteplan npm
A
@noteplanco/noteplan-mcp

MCP server for NotePlan note and task management

AI & Agents Score 93/100 14 findings 938/wk Cap. High
Warden Source verified 3 implementations
A
best: @icoretech/warden-mcp

Vaultwarden/Bitwarden MCP server backed by Bitwarden CLI (bw).

Security & Testing Best score 93/100 3 findings 904/wk Cap. High
Nsauditor Ai npm
A
nsauditor-ai

Modular AI-assisted network security audit platform — Community Edition

Security & Testing Score 93/100 10 findings 902/wk Cap. High
Xreport npm
A
@xqa.io/xreport

XREPORT by XQA — All-in-One Enterprise Test Reporter for Playwright, WebdriverIO (WDIO), Jasmine, Cypress, Jest, Vitest & Mocha. Local audit evidence, quality gates, control tagging, flaky detection, run history, traces, AI + MCP. Zero Java. From xqa.io.

Developer Tools Score 93/100 1 finding 894/wk Cap. High
Sub Agents npm
A
sub-agents-mcp

MCP server for delegating tasks to specialized AI assistants in Cursor, Claude Code, Codex, Gemini, GLM, Grok, and OpenCode

AI & Agents Score 93/100 1 finding 893/wk Cap. High
Agent npm
A
@reclaimprotocol/agent

Reclaim Protocol's tools for agents — Reclaim Protocol lets your app verify **data points** about its users — a follower count, an account balance, an order history. This package gives your AI coding agent the tools to **find, build, test and fix the _dat

Developer Tools Score 93/100 12 findings 886/wk Cap. High
My Pi npm
A
my-pi

Composable pi coding agent with MCP, LSP, prompt presets, and local eval telemetry

Developer Tools Score 93/100 1 finding 867/wk Cap. High
Contextstream npm
A
@contextstream/mcp-server

MCP server that gives AI coding assistants persistent memory, semantic code search, a dependency graph, grounded Q&A, and team context (GitHub/Slack/Notion) — works with Claude Code, Cursor, VS Code Copilot, Windsurf, Cline, and any Model Context Protocol

AI, Memory & Reasoning Score 93/100 1 finding 852/wk Cap. High
Squirrelscan Source verified npm
A
squirrelscan

Website QA tool built for coding agents. 260+ rules across SEO, performance, security, accessibility & agent experience, from the CLI, cloud, or MCP.

Developer Tools Score 93/100 3 findings 835/wk Cap. High
Reelier npm
A
reelier

Agents make claims, Reelier writes receipts - record an agent workflow once, replay it deterministically at 0 tokens, and get an asserted receipt on every run.

Other Score 93/100 1 finding 827/wk Cap. High
Abap npm
A
abap-mcp

MCP server for SAP ABAP: offline static analysis (abaplint), ABAP Cloud / Clean Core readiness checks, and RAP scaffolding — no SAP system or credentials required.

Developer Tools Score 93/100 2 findings 820/wk Cap. High