data-ai MCP Server
🐕 Self-hosted security-first AI agent · 22 providers · 11 chat channels · WebUI · 3-level memory · cron · heartbeat · skills · MCP
Discovered via agent-topic:ai-agent and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
HTTP fetch with SSRF protection, DNS rebinding defense, and redirect validation
`DEEPSEEK_API_KEY`
WebUI (Starlette + native WebSocket), cron service
Try
Brave, Tavily, SearXNG, Jina, or DuckDuckGo (fallback, no key needed)
`ANTHROPIC_API_KEY`
Core agent loop, message bus, channel integrations
~120 MB
ShibaClaw
Shell commands with 20+ deny-pattern guards, encoding normalization, and CVE scanning
Schedule one-time or recurring jobs (cron expressions, intervals, ISO dates, timezone-aware)
`OPENAI_API_KEY`
`MINIMAX_API_KEY`
Native WebSocket (`/ws` on WebUI, port `19998` on gateway)
Ranked search over session history (TF-IDF + recency + importance scoring)
`GROQ_API_KEY`
Technology
Uvicorn → Starlette (ASGI)
PKCE browser flow, stores returned API key in provider config
Idle
Nanobot
Optional background worker for a focused task; reports back to the main session when done
¹ Setting `GEMINI_API_KEY` in the environment is sufficient — no stored key required. The Google OpenAI-compatible endpoint is pre-configured. ### Gateway / Proxy OpenRouter · AiHubMix · SiliconFlow · VolcEngine · BytePlus — auto-detected by key prefix or `api_base`. ### Local Ollama (`http://localhost:11434`) · LM Studio · llama.cpp · vLLM · any OpenAI-compatible endpoint(`http://localhost:1234/v1`) > **Note for Docker users:** If you run ShibaClaw via Docker Compose, `localhost` points inside the container itself. To connect to a local server running on your host machine (like LM Studio or Ollama on Windows/Mac), use: > `http://host.docker.internal:1234/v1` (or `11434` for Ollama). On native Linux, use `http://172.17.0.1:port`. ### OAuth
Vanilla JS · Marked.js · Highlight.js
Connect any MCP server (stdio, SSE, or streamable HTTP) — tools auto-registered as `mcp_<server>_<tool>`
JSONL append-only per session (cache-friendly for LLM prompt prefixes)
What it does
Cross-channel messaging with media attachments
`MOONSHOT_API_KEY`
Setup
Env Variable
Role
~120 MB