Live survey286 models · 13 providers · 17,592 auditsAudited Using Git Worktrees · SAFE →What changedHow we verifyllms.txt

MCP servers · publisher

MCP servers by peakmojo

peakmojo publishes 3 MCP servers in the atlas. 1 are SAFE, 0 CAUTION and 2 BLOCK. Each was read in full before it was listed.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “MCP servers by peakmojo”. Retrieved 28 Oct 2026. https://modelsatlas.com/mcp/peakmojo

Verdicts · 3 servers

✓SAFE1!CAUTION0✕BLOCK2

Transports

  • stdio, runs locally2
  • Streamable HTTP, remote0
  • SSE, legacy remote0
  • Not declared1

A server can list more than one transport.

3 servers by peakmojo

1–3 of 3 · ranked by trust score, then stars

HubSpot

peakmojo/mcp-hubspot

✓SAFE B

A Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data, providing built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.

★ 1296 writestdio

Applescript

peakmojo/applescript-mcp

✕BLOCK D

MCP server that execute applescript giving you full control of your Mac

★ 4651 writestdio

Agentic Client

peakmojo/agentic-mcp-client

✕BLOCK D

A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.

★ 423 read

More from peakmojo

peakmojo as a publisher →

Questions

Which peakmojo MCP server has the best trust score?
HubSpot (peakmojo/mcp-hubspot) and Applescript (peakmojo/applescript-mcp), ranked by trust score and then stars.
Are peakmojo's MCP servers read-only?
1 of 3 declare only read tools; 0 expose at least one destructive tool; 0 build their tool list at runtime, so we cannot read it from the source.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.