"Trusted Shops" matching MCP servers:

Enables AI agents to interact with the npm registry, covering package intel, dist-tags, trusted publisher configuration, access and team governance, tokens, security advisories, and publishing, with read-only tools by default.

Enables agents to search a lightweight catalog, inspect permissions, lazily start trusted MCP servers, and call child tools without keeping all schemas in context. It also loads approved skills on demand and routes third-party additions through a human approval queue.

Coordination protocol for parallel coding agents, built above Git. The MCP server exposes the full 17-tool lifecycle over stdio: register agents, publish intents with semantic scopes and declared operations, claim work, check for conflicts before code is written, publish ChangeSets, run trusted named verification checks, and record accepted work. Deterministic rules raise findings when two agents'

Gaia MCP enables AI agents to discover, evaluate, and install trusted skills from the Gaia Skill Tree, providing evidence-backed recommendations and safe workspace integration.

Audits local package folders to generate publish-readiness reports and previews of NPM tarball contents. It helps developers identify and resolve configuration issues like missing types or broken exports before releasing code.

Enables an AI agent to inspect and analyze a local SQLite shop database through read-only, single-query SELECT operations, with schema inspection and paginated querying.

A version-aware Kubernetes documentation assistant that connects LLMs to trusted, real-time Kubernetes docs to reduce hallucinations and ensure accurate, version-specific responses.

Enables checking trust of MCP tools before installation, listing trusted tools, and scoring MCP stacks via the Veragent trust registry.

An MCP server providing curated Swift and SwiftUI best practices from leading iOS developers, including patterns and real-world code examples from Swift by Sundell, SwiftLee, and other trusted sources.

Lets MCP agents drive VS Code's integrated browser tab that the user shares with them: opening pages, taking accessibility snapshots and screenshots, clicking, typing, scrolling, dragging and reading console and network activity with real trusted input. It also maps a picked element back to the source file, line and column that rendered it, so an agent receives the same selection the developer clicked.

Enables MCP clients to drive developer workflows through APIs and CLIs, with explicit workspace or trusted-workstation launch modes, bounded command previews, multi-repository rules discovery, and an on-demand skills/recipes entry point. It lets agents review changes, run commands, and load only the smallest relevant rule or skill while reporting evidence and unverified steps.

A Model Context Protocol server for secure, sandboxed file operations and project scaffolding with built-in search and regex capabilities. It is optimized for Windows environments and features configurable access controls to restrict operations to specific directories.

Enables LLM agents to perform local development and automation over MCP STDIO, including project context retrieval, file read/write and patching, shell/Python execution, Git inspection, work-state tracking, and validation. It runs as a local Python process with Dev and Safe execution modes and audit logging for trusted single-developer environments.

A lightweight local MCP server that gives MCP hosts read-only tools for health checks, grounded web research, chat over trusted sources, and generation of portable client config snippets. It also exposes the aw* bootstrap plan and backend-switching plan so builders can bootstrap, switch coding backends, and package integrations from Codex, Claude, or any MCP client.

Enables deploying standalone MCP connectors, discovering them through a validated catalog, and running an optional trusted polyglot runtime for the DX Heroes MCP Gateway.

Enables AI agents to read-only query a SQLite database, inspect schema and table summaries, and execute SELECT queries with pagination through MCP.

Enables trusted local AI agents to create, inspect, edit, save, reopen, and export isolated headless KiCad 9 PCB board files, including native design-rule-check reports, through typed MCP tools. Operations are bounded to native pcbnew and kicad-cli calls within a single explicit trusted workspace, with no arbitrary script execution, live PCB Editor control, or IPC access.

Semantic navigator for MCP tools that finds relevant tools by natural language intent, reducing token usage by 95%.

Provides a local, queryable mirror of changelogs from Anthropic and related AI dev tools, enabling agents to discover cross-product workflows and sync updates via MCP.

Exposes native iPhone device services and UI automation through MCP, enabling agents to inspect and control trusted iPhones via a unified interface.