offload
Hand heavy read-only work to a background agent CLI (Antigravity) and read back a short report.
Open the source (opens github.com) https://github.com/tailucanh/offload-mcp-server
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.tailucanh.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
offload-mcp-server@0.4.2
From the server's entry in the official MCP Registry
Related
-
lm
MCP serversConnect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
@houtini/lm@3.3.4 -
Squire
MCP serversCLI-first remote runtimes for validation and offload tasks, exposed over MCP stdio.
ghcr.io/reidgoodbar/squire-mcp:0.6.5 -
lethe
MCP serversContext GC for LLM agents: offload large tool outputs and recall them to save tokens.
lethe-llm-context@0.6.2 -
Cheaplane
MCP serversOffload grunt work from your premium agent to cheap models — auto-routing and billing isolation.
cheaplane@0.2.1 -
AgentPool
MCP serversSee each coding-agent subscription's live limits and offload work to one with headroom.
agentpool-cli@0.1.13 -
ollama-handoff
MCP serversOffload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
ollama-handoff@0.1.2