sakebomb

MCP Recall — Development skill for Claude Code

Development community

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.

How to install MCP Recall

This entry records only its repository, not the path inside it, so there is no exact command to give. Open sakebomb/mcp-recall and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What MCP Recall does

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.

Alternatives in Development

Ccusage — CLI for analyzing Claude Code/Codex usage from local JSONL files 11.8k ★
Claude Context Mode — An MCP server that sits between Claude Code and these outputs 5.3k ★
Arrecall — AgentRecall on-demand recall — surface past fixes, decisions, and patterns mid-session without leaving your fl 370 ★

README

mcp-recall

[![CI](https://github.com/sakebomb/mcp-recall/actions/workflows/ci.yml/badge.svg)](https://github.com/sakebomb/mcp-recall/actions/workflows/ci.yml) [![npm](https://img.shields.io/npm/v/mcp-recall.svg)](https://www.npmjs.com/package/mcp-recall) [![npm downloads](https://img.shields.io/npm/dw/mcp-recall.svg)](https://www.npmjs.com/package/mcp-recall) ![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg) ![Runtime: Bun](https://img.shields.io/badge/runtime-Bun-f472b6.svg) ![TypeScript](https://img.shields.io/badge/TypeScript-strict-3178c6.svg) ![Claude Code Plugin](https://img.shields.io/badge/Claude%20Code-plugin-orange.svg) [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](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.

![mcp-recall demo](demo/demo.gif)

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