local-swarm-mcp

jhonsferg/local-swarm-mcp
★ 2 stars Go AI/LLM Updated today
MCP server that delegates mechanical tasks to local OpenAI-compatible inference backends (llama.cpp, Ollama, etc.) and provides context-management tools (compaction, scratch store, token estimation).
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "local-swarm-mcp": {
      "command": "go",
      "args": [
        "run",
        "github.com/jhonsferg/local-swarm-mcp@latest"
      ]
    }
  }
}

README Excerpt

<p align="center"> <a href="https://github.com/jhonsferg/local-swarm-mcp/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/jhonsferg/local-swarm-mcp/actions/workflows/ci.yml/badge.svg"></a> <a href="https://github.com/jhonsferg/local-swarm-mcp/blob/main/LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-blue.svg"></a>

Tools (20)

cancel_taskclassify_task_riskclose_sessioncompact_contextcreate_sessiondelegate_taskestimate_tokenshealth_checklist_available_agent_toolslist_backend_hostslist_backendslist_downstream_mcp_serverslist_sessionslist_tasksregister_backend_hostregister_downstream_mcp_serverscratch_deletescratch_getscratch_listscratch_set

Topics

ai-agentsgolangllama-cppllmlocal-firstmcpmodel-context-protocolollamatool-calling