# Claude Recall

> Use this tool when you need to provide AI agents with persistent memory across sessions, enabling them to store, retrieve, and utilize context from previous interactions. Claude Recall solves the problem of session-based data loss, allowing for more informed and personalized responses through its semantic similarity matching and full-text search capabilities. It is ideal for use cases requiring data privacy, as all data remains local with no outbound network calls.

Canonical page: https://skillsregistry.net/skills/claude-recall  
JSON: https://api.skillsregistry.net/v1/skills/claude-recall

## Description

Claude Recall is a local MCP server that gives AI agents persistent memory across Claude Code sessions. The server exposes 33 tools for storing, tagging, searching, and retrieving session context using full-text and semantic similarity matching. All data remains bound to localhost with no outbound network calls or telemetry. Installed as an npm package with one-command setup via Claude Code's plugin system.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/claude-recall)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "claude-recall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/claude-recall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/claude-recall/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt