**Context filesystem server/client for LLM agents** — MCP-compatible, multi-tenant, zero-dependency dashboard
ContextFS gives LLM agents a persistent, structured filesystem they can read from, write to, and search — without giving them direct access to your machine.
It exposes a standard MCP (Model Context Protocol) surface over SSE or stdio, so any MCP-compatible LLM client (Claude Desktop, Cursor, custom agents) can use it out of the box.
A machine/process that physically executes tool calls. Connects to the server via WebSocket.
A logical tenant (agent, user, project). Has its own API key, workspace, skills, and memory.
A directory scoped to a virtual client. All file operations are sandboxed within it.
Server executes tools in-process — no WS client needed. Ideal for single-machine use.
npx contextfs server --local --mcp sse
# Create a virtual client
curl -s -X POST http://localhost:3010/api/virtual-clients \
-H 'Content-Type: application/json' \
-d '{"name":"my-agent"}' | jq .
# → copy "id" and "apiKey"
# Open dashboard
open http://localhost:3010
# Chat
CONTEXTFS_VC_ID= CONTEXTFS_VC_KEY= OPENROUTER_API_KEY=sk-or-... \
npx contextfs chat --mcp-server http://localhost:3010