MCP-Recall is an open-source developer tool designed to solve context window bloat in heavy Model Context Protocol (MCP) workflows. By automatically compressing tool outputs—reducing payloads like 94 KB down to just 3.5 KB (a ~96% reduction)—MCP-Recall prevents tool responses from overflowing your LLM session context.
Instead of discarding full response data, MCP-Recall persists the complete, uncompressed tool outputs into an SQLite database for subsequent retrieval when needed. This architecture enables developers and AI agents to handle up to 30x more tool calls per session during resource-intensive tasks. Created by Jonathan Tomek, the project is open-source and accessible via GitHub and NPM.
MCP-Recall is an open-source tool for developers working with the Model Context Protocol (MCP). It compresses tool outputs to save context window space and persists full response data to SQLite for retrieval.
It compresses large output payloads—achieving reductions of around 96% (such as scaling 94 KB down to 3.5 KB)—allowing your session context to stay lean while saving full outputs in a local database.
By dramatically reducing context consumption per response, MCP-Recall allows heavy MCP workloads to execute up to 30x more tool calls within a single session.
MCP-Recall is available as an open-source repository on GitHub and can be installed via NPM.
0 community reviews for MCP-Recall
Help the community by sharing your experience. Your review helps others make better decisions.
