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.