This is ephemeral cloud storage designed specifically for AI agent workflows. It gives you a simple key-value store with a 2-hour TTL, perfect for when you need Claude to stash context between conversations, pass data between different tools in a chain, or quickly dump outputs without cluttering your local filesystem. Think of it as a scratchpad in the cloud. No authentication complexity, no permanent storage to manage. You'd reach for this when building multi-step workflows where agents need to hand off state, or when you want to cache expensive API responses temporarily without spinning up your own Redis instance.
Public tool metadata for what this MCP can expose to an agent.
create_objectSave objects to ephemeral cloud storage - Store your reasoning state, large JSON structures, or any data to get a shareable URL. Perfect for: caching contexts before token limits, bridging multi-agent workflows, storing intermediate results, sharing data between sessions, or t...4 paramsSave objects to ephemeral cloud storage - Store your reasoning state, large JSON structures, or any data to get a shareable URL. Perfect for: caching contexts before token limits, bridging multi-agent workflows, storing intermediate results, sharing data between sessions, or t...
datavalueintentstringagent_idstringttl_secondsnumberget_objectRetrieve data from cloud storage using its ID.1 paramsRetrieve data from cloud storage using its ID.
object_idstringOPI_API_URLdefault: https://0pi.devAPI endpoint for 0pi service
OPI_LOG_DIRdefault: ./logsDirectory for conversation logs
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent