data-ai MCP Server
Open-source multi-agent AI assistant powered by LangGraph, FastAPI & Next.js — 16+ agents, Human-in-the-Loop, MCP integration, voice TTS, RAG, 500+ metrics, 6 languages.
Discovered via github-topic:mcp and last synced 4mo ago.
1. Install the package
npm install lia
http://localhost:3000
1.1.6
1.9+
1.2.15
Accessible UI primitives
Provider
### Enterprise Observability - **Prometheus**: 500+ custom metrics (agents, LLM, infrastructure) - **Grafana**: 20 production-ready dashboards - **Langfuse**: LLM-specific tracing with prompt versions - **Loki**: Structured JSON logs with PII filtering - **Tempo**: Distributed cross-service tracing ### Cost Tracking & Billing
1.0+
High
Export
C[Response Node] B -->
latest
ExecutionPlan generation
< 500ms
PII filtering, data minimization
LIA Solution
Tool filtering
Trigger
20 dashboards
0.135.3
Bayesian learning
Version
2.12.5
Description
19.2.4
Any local model (dynamic discovery)
< 2s
$50 / 1M chars
GPT-5.4, GPT-5.4-mini, GPT-5.2, GPT-5.1, GPT-5, GPT-5-mini/nano, GPT-4.1, GPT-4.1-mini/nano, GPT-4o, o1, o3-mini
Role
Implementation
Free
**deepseek-v4-flash, deepseek-v4-pro** (V4 family — thinking-mode toggle, v1.19.1+), deepseek-chat (V3, legacy), deepseek-reasoner (R1, legacy)
< 500ms
$100 / 1M chars
3.12+
5.9.3
500+ metrics
Description
$50 / 1M chars
16.5.1
LLM observability
2.0.49
Documents
4.2.1
Structured JSON logs
Models
qwen3-max, qwen3.5-plus, qwen3.5-flash
sonar-small/large-128k-online
Status
24+
Claude Opus 4.6/4.5/4, Claude Sonnet 4.6/4.5/4, Claude Haiku 4.5
Aggregated logs
Value
Trigger
Usage
Gemini 3.1/3/2.5 Pro, Gemini 3/2.5/2.0 Flash
Distributed tracing
Premium
URL
Routing decision
Capabilities
Sections
G[Task Orchestrator] F -->
R3[ReAct Execute Tools] R2 -->
16 + pgvector
7.3.0