## The problem

Calling the `company_research_exa` tool from the Exa MCP server in Claude Code returns 112k+ characters of JSON (overview, financials, workforce, salaries), which blows the context window and makes the result unusable in agentic workflows. The oversized payload comes from uncapped per-result character counts combined with too many results by default. Agents consuming this tool get flooded with text they cannot fit into context.

## What fixed it

Exa fixed this server-side: `company_research_exa` now caps each result at 7000 characters (`maxCharactersPerResult`) and defaults to 3 results (`numResults`). If you still need more results, ask your agent to pass explicit parameters, e.g. `numResults: 10` with `maxCharactersPerResult: 2000`, trading result count against per-result length. The maintainer confirmed the change via the linked commit.