malamutemayhem/unclick
by Various
The universal remote for AI: one MCP install gives agents 450+ callable endpoints across 60+ integrations, plus persistent cross-session memory. Works with Claude, ChatGPT, Cursor,
MCP
malamutemayhem/unclick
Added 15 June 2026
Overview
Unclick is an MCP server that exposes over 450 callable endpoints across 60+ integrations, giving AI agents a single interface to interact with external services. It also provides persistent cross-session memory, and works with any MCP client including Claude, ChatGPT, and Cursor.
Best for
Best for
Developers building multi-tool AI agents who want a single integration point for many external services.
Use cases
- Connect an AI agent to dozens of APIs through one MCP install
- Give agents persistent memory across chat sessions
- Extend tools like Claude or Cursor with 450+ callable actions
Notes
Unclick is an MCP server that exposes over 450 callable endpoints across 60+ integrations, giving AI agents a single interface to interact with external services. It also provides persistent cross-session memory, and works with any MCP client including Claude, ChatGPT, and Cursor.
4 stars on GitHub. Last updated 2026-06-15. Licensed AGPL-3.0.
Use cases
- Connect an AI agent to dozens of APIs through one MCP install
- Give agents persistent memory across chat sessions
- Extend tools like Claude or Cursor with 450+ callable actions
Pros
- Massive library of pre-built integrations reduces custom coding
- Single MCP install replaces many separate tool configurations
- Cross-session memory enables long-running agent workflows
Cons
- Dependency on MCP protocol limits use to compatible clients
- 450+ endpoints may introduce complexity in discovery and selection
- Third-party integrations may have inconsistent reliability or rate limits
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Massive library of pre-built integrations reduces custom coding
- Single MCP install replaces many separate tool configurations
- Cross-session memory enables long-running agent workflows
Cons
- Dependency on MCP protocol limits use to compatible clients
- 450+ endpoints may introduce complexity in discovery and selection
- Third-party integrations may have inconsistent reliability or rate limits
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.