# Encore, MCP, and AI agents

DevFeed: [Encore, MCP, and AI agents](<https://devfeed.tech/articles/encore-mcp-and-ai-agents-17821.md>)

Original publisher: [Read original article](<https://encore.dev/blog/mcp-deep-dive>)

Author: Ivan Cernja

Published: 2026-03-19T00:00:00Z

Content type: tutorial

Language: en

Sources: [Encore Updates](<https://devfeed.tech/sources/encore-updates.md>)

Topics: [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [MCP Server](<https://devfeed.tech/topics/mcp-server.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [Traces](<https://devfeed.tech/topics/traces.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [database](<https://devfeed.tech/tags/database.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [trace](<https://devfeed.tech/tags/trace.md>)

## AI overview

The article explains how Encore's MCP server gives AI coding tools structured access to a running application's schemas, service graph, traces, pub/sub topology, cache configuration, infrastructure, documentation, and testing information. It describes how this context can help agents understand existing backend structure and reduce guesswork when implementing or verifying changes.

## Source excerpt

How to give your agent full context over your running application.