using-heavy-mcps

SKILL.md

When working with MCPs that return large payloads—like Sanity queries with full document content or Brain vault searches with entire file contents—you can route these calls through mcporter outside of chat, trim the output with jq, and feed only the compact result back to the model. This avoids the 20–40k token bloat that comes from loading full responses into context.

mcporter responses include built-in helpers that can replace jq for simple extractions. Choose based on your needs:

mcporter returns results wrapped in a CallResult object with helper methods:

mcporter と jq を使用して、Sanity や Brain vault などの重い MCP によるトークンの肥大化を軽減します。チャットの外で出力をフィルタリングおよび圧縮して、重要なデータのみをモデルにフィードバックします。 ソース: nweii/agent-stuff。

原文を見る