MCP Dev Summit Bengaluru 2026

**Space Limited - First Come, First Served.  Please bring a fully charged laptop to the workshop**

A single coding agent is useful. Real engineering work spans multiple machines and repos, and coordination breaks the moment two agents cooperate. What does it take to build an MCP server that manages a fleet lifecycle from one conversation and enforces quality on output?

This workshop uses apra-fleet (Apache 2.0) as a worked example of pushing MCP into distributed agent coordination, with tool schemas encoding a doer-reviewer pattern and review gates.

Part 1, Server architecture: Transport selection (stdio vs HTTP) for long-running fleets, a strategy pattern abstracting SSH and local execution behind one tool surface, provider adapters for Claude, Gemini, and Codex, and git-backed session state for checkpointing.

Part 2, Fleet in action: A live sprint. Fleet registration, credential provisioning, task decomposition, doer-reviewer assignment, and parallel execution through review gates, via MCP tool calls.

Part 3, Failure modes: Agent crashes, SSH drops, reviewer rejections. Real failures triggered on stage, recovered from exact breakpoints using git state.

You'll leave with concrete patterns for building MCP servers that coordinate distributed agents, not just expose tools.