Mcp Recall

mcp-recall

[](https://github.com/sakebomb/mcp-recall/actions/workflows/ci.yml) [](https://www.npmjs.com/package/mcp-recall) [](https://www.npmjs.com/package/mcp-recall)     [](CONTRIBUTING.md)

**Your context window is finite. MCP tool outputs aren't. mcp-recall bridges the gap.**

MCP tool outputs — Playwright snapshots, GitHub API responses, Linear queries — 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.


---

The full context stack

Context pressure builds at four distinct layers. Native Claude tooling now covers most of them for **built-in** tools — but leaves **MCP** tool output largely unhandled. That's the gap mcp-recall fills.

flowchart TD
    A(["Claude session begins"]) --> B

    B["① Tool definitions loaded into context\n~500 tokens × every connected tool"]
    B -->|"Claude Code Tool Search · Switchboard\ndefer unused schemas"| C

    C["② Claude calls tools in sequence"]
    C -->|"Code Mode · FastMCP 3.1\nrun script in sandbox, no intermediate results"| D

    D["③ MCP tool