Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
offload
MCP serversHand heavy read-only work to a background agent CLI (Antigravity) and read back a short report.
offload-mcp-server@0.4.2 -
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 -
claude-token-saver-mcp
MCP serversMCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens
claude-token-saver-mcp@0.3.2 -
Log10x MCP
MCP serversRank log patterns by volume and cost, then compact, tier down or offload the excess over each cap
log10x-mcp@1.30.106
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.