Skip to main content
Unblocked MCP tools are actively evolving. Tools and their descriptions may change over time.
research_task investigates a broad topic and synthesizes what it finds into a structured briefing — a narrative that connects code changes to the PRs, discussions, and decisions behind them. Unlike individual lookups that answer one question at a time, research builds a complete picture across multiple sources before your agent takes action.

Why research over multiple lookups

Individual lookups answer isolated questions. research_task synthesizes across sources so your agent gets it right the first time:
  • Connects code changes to the PRs, discussions, and decisions that drove them.
  • Identifies patterns across multiple files and services.
  • Surfaces context from messaging platforms, issue trackers, and docs that isolated code search misses.
  • Produces a coherent narrative rather than fragments, so your agent can plan against the full landscape.
Investing in research before implementation reduces rework. The briefing gives your agent the full context of prior decisions, patterns, and pitfalls upfront.

When your agent uses it

  • Investigating unfamiliar subsystems or feature areas, such as how the notification pipeline works end-to-end.
  • Questions that span multiple systems, teams, or sources.
  • Scoping an integration, migration, or refactor, such as evaluating the impact of upgrading from React 17 to 18.
  • When it has already tried several lookups without converging on an answer.
  • At the start of a planning task, in parallel with code exploration.

When your agent uses something else