Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"alpha-avatar-plugins-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# AlphaAvatar MCP Plugin A high-performance **Model Context Protocol (MCP) orchestration layer** for **AlphaAvatar**. This plugin provides a **unified, parallel, and latency-optimized interface** for discovering and invoking tools exposed by one or more MCP servers — without relying on LiveKit’s native MCP tool injection chain. > We intentionally disable LiveKit’s native “inject each MCP tool into Agent as separate tool” mechanism. > > Why? > > * Too many tools degrade Agent reasoning performance. > * Serial tool calls increase latency. > * Tool explosion harms LLM decision quality. > > Instead, we provide a **single unified MCP interface** that: > > * Supports tool discovery > * Enables parallel execution > * Coordinates multi-server workflows > * Improves overall Agent tool-call performance --- # Overview The MCP Plugin acts as a **Tool Orchestrator Middleware** between AlphaAvatar Agents and external MCP servers. It enables: * 🔍 Tool discovery across heterogeneous MCP servers * ⚡ Parallel tool execution (concurrent dispatch) * 🧠 Workflow coordination across multiple servers * 🔗 Unified abstraction for diverse capabilities (RAG, search, automation, data APIs, etc.) Unlike traditional tool injection approaches, this design: * Prevents exponential tool growth inside the Agent * Reduces reasoning noise * Avoids serial execution bottlenecks * Improves scalability for multi-server MCP deployments --- # Core Architecture ```text AlphaAvatar Agent │ ▼ MCPHost (Unified Tool) │ ├── search_tools() └── call_tools() │ ├── MCP Server A ├── MCP Server B └── MCP Server C ``` The Agent only sees **one tool: `MCP`**. Internally, MCPHost: 1. Discovers relevant tools 2. Validates schemas 3. Dispatches calls in parallel 4. Aggregates structured responses --- # Performance Design Philosophy ## ❌ What We Avoid * Injecting hundreds of tools into the Agent *…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.