You are building developer productivity tools using the Claude Agent SDK. The agent helps engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate code, and automate repetitive tasks. It uses the built-in tools (Read, Write, Bash, Grep, Glob) and integrates with Model Context Protocol (MCP) servers.

Your productivity agent connects to three MCP servers: an issue tracker (search_issues, get_issue, create_comment), a documentation wiki (search_docs, get_page, list_spaces), and a database explorer (run_query, get_schema, list_databases). When engineers ask cross-system questions like "What database tables are affected by the authentication refactor in PROJ-1234?", monitoring shows the agent makes 8-10 sequential tool calls, frequently issues exploratory calls because it lacks visibility into what content each server contains, and exhausts context space before completing complex investigations.

What architectural change best leverages MCP capabilities to address these issues?