mcp-recall Your context window is finite. MCP tool outputs aren't. mcp-recall bridges the gap. MCP tool outputs — Playwright snapshots, GitHub issues, file reads — can consume tens of kilobytes of context per call. A 200K token context window fills up in 30 minutes of active MCP use. mcp-recall intercepts those outputs, stores them in full locally, and delivers compressed summaries to Claude instead. When Claude needs more detail, it retrieves exactly what it needs via FTS search — without re-running the tool. Sessions that used to hit context limits in 30 minutes routinely run for 3+ hours.
| Stars | 7 |
| Forks | 1 |
| Language | TypeScript |
| Category | MCP 服务器 |
| License | MIT |
| Quality Score | 43.2/100 |
| Last Updated | 2026-05-10 |
| Created | 2026-03-01 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~193k |
Explore other popular mcp 服务器 tools:
mcp-recall is mcp-recall compresses MCP tool outputs (94 KB → 3.5 KB · 96%) and stores full results in SQLite for retrieval — up to 30x more tool calls per session for heavy MCP workloads.. It is categorized as a MCP 服务器 with 7 GitHub stars.
mcp-recall is primarily written in TypeScript. It covers topics such as bun, claude, claude-code.
You can find installation instructions and usage details in the mcp-recall GitHub repository at github.com/sakebomb/mcp-recall. The project has 7 stars and 1 forks, indicating an active community.
mcp-recall is released under the MIT license, making it free to use and modify according to the license terms.