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 →
Security Detections npm
A
security-detections-mcp

Advanced MCP server for security detections with Detection Engineering Intelligence, Knowledge Graph (Tribal Knowledge), Elicitation, and Resource Subscriptions

Security & Testing Score 93/100 3 findings 191/wk Cap. High
Latitudesh npm
A
latitudesh

> Model Context Protocol (MCP) server for the [Latitude.sh API](https://www.latitude.sh/docs/api-reference)

Cloud & DevOps Score 93/100 1 finding 190/wk Cap. High
Clear Thought Onepointfive npm
A
@waldzellai/clear-thought-onepointfive

Clear Thought MCP server with modular architecture - 38 reasoning operations for systematic thinking

Developer Tools Score 93/100 3 findings 188/wk Cap. High
Dep Tracer npm
A
@nexus2520/dep-tracer-mcp-server

MCP server that maps function and component dependencies in Haskell and ReScript codebases — built to help LLMs trace affected code flows for test generation.

Developer Tools Score 93/100 3 findings 187/wk Cap. High
I1n npm
A
i1n

Localization as code — CLI and SDK for i1n

Developer Tools Score 93/100 1 finding 187/wk Cap. High
Agent npm
A
@bvcc/agent-mcp

Model Context Protocol server exposing a BVCC Agent Wallet to AI runtimes (Claude Code, Cursor, Claude app). Tools are generated from the @bvcc/agent-sdk capability catalog.

Security & Testing Score 93/100 3 findings 186/wk Cap. High
Expo Docs npm
A
expo-docs-mcp

Model Context Protocol server for Expo documentation

Learning & Documentation Score 93/100 3 findings 186/wk Cap. High
Reflex Browser npm
A
reflex-browser

Token-efficient browser automation for AI agents. Local MCP server + CLI: compressed page snapshots, batched actions, forensic failures.

Developer Tools Score 93/100 8 findings 186/wk Cap. High
Vibedrift Cli npm
A
@vibedrift/cli

Ship agentic. Stay coherent. Self-checking code integrity for AI coding agents, in the loop via MCP.

Developer Tools Score 93/100 8 findings 185/wk Cap. High
Smart Crawler npm
A
mcp-smart-crawler

Uses Playwright to crawl web content for AI models.

Web, Search & Scraping Score 93/100 1 finding 184/wk Cap. High
Grupr npm
A
@grupr/mcp-server

Model Context Protocol server for the Grupr Agent-Hub — drives a Grupr agent from Claude Desktop, Cursor, or any MCP-compatible client

API Development Score 93/100 3 findings 183/wk Cap. High
Drawlatch npm
A
@wolpertingerlabs/drawlatch

Encrypted MCP proxy with mutual authentication. Local MCP server forwards requests through an encrypted channel to a remote secrets-holding server.

Developer Tools Score 93/100 4 findings 182/wk Cap. High
Agent Search npm
A
agent-search-mcp

Free multi-engine web search across seven engines (DuckDuckGo, Sogou, Bing, Baidu, Brave, Tavily, Exa) with waterfall progressive search, multi-source verification, and content enrichment; no API keys needed.

Web, Search & Scraping Score 93/100 14 findings 181/wk Cap. High
Burn npm
A
burn-mcp-server

Burn MCP — give your AI agent a reading workflow. 26 tools to search, triage, burn, vault, and analyze your saved articles. Works with Claude, Cursor, Windsurf.

Learning & Documentation Score 93/100 1 finding 181/wk Cap. High
Sign Cli Source verified npm
A
@drbaher/sign-cli

Signing CLI for AI agents and ops people who want a verifiable audit trail. Runs fully offline with a built-in PAdES signer (no signup, no third-party provider) — or routes through Dropbox Sign / DocuSign / SignWell. Per-signer tokens, declarative policie

Business & CRM Score 93/100 5 findings 180/wk Cap. High
Weapp Agent npm
A
@chaixueyuan/weapp-agent-mcp

Agent-first MCP server for WeChat Mini Program debugging, automation, and lightweight testing

Security & Testing Score 93/100 2 findings 179/wk Cap. High
Rpgmaker Mv 2 implementations
A
best: rpgmaker-mv-mcp

RPG Maker MV Ultimate — AI copilot (MCP) for RPG Maker MV: generate maps, edit the database and events, and understand your project — validate broken references, explain why an event never fires, critique maps, and search by meaning.

Lifestyle & Local Best score 93/100 1 finding 178/wk Cap. High
Tastehub Ckb npm
A
@tastehub/ckb

Code intelligence for AI assistants (MCP), CLI, and HTTP API - symbol navigation, impact analysis, architecture

Web, Search & Scraping Score 93/100 1 finding 178/wk Cap. High
Mobai npm
A
mobai-mcp

MCP server for MobAI - AI-powered mobile device automation

Security & Testing Score 93/100 3 findings 176/wk Cap. High
Codex Computer Use npm
A
codex-computer-use-mcp

Expose the official macOS Computer Use tools directly to Pi and MCP clients without a nested model.

Developer Tools Score 93/100 1 finding 175/wk Cap. High
Memoir Cli Source verified npm
A
memoir-cli

Private, portable AI memory: synced across every coding tool and machine, end-to-end encrypted, free. One memory for Claude Code, Cursor, Copilot, Gemini + more — MCP-native, zero-knowledge, open source.

AI, Memory & Reasoning Score 93/100 17 findings 175/wk Cap. High
Better Bear 2 implementations
A
best: better-bear

MCP server for Bear notes — read, search, create, edit, tag, and manage notes via CloudKit

Data Science & ML Best score 93/100 1 finding 174/wk Cap. High
Datanexusmcp npm
A
@datanexusmcp/mcp-server

DataNexus MCP — AI-Ready public data intelligence. 55 tools: CVE risk verdicts, SBOM licence policy, frontend security (manifest audit, CI scanner, typosquatting), licence compatibility, nonprofit 990 trends, SBOM monitoring, federal contracts, NPI lookup

Data Science & ML Score 93/100 1 finding 174/wk Cap. High
Projectmind 2 implementations
A
best: @nodemint/projectmind

Persistent, compact project memory for AI coding agents — an npm library, CLI, and MCP server that stores a small structured map of your repo so agents stop re-reading the codebase every session.

Developer Tools Best score 93/100 2 findings 173/wk Cap. High