# cache-manager-mcp

> cache-manager-mcp — datawithdanny-cache-manager-mcp. Use this tool when you need to manage and track token usage across multiple AI agent chats, requiring features like prompt time-to-live (TTL) tracking, memory handoffs, and cost insights. It solves problems of token expiration, memory loss, and cost optimization in multi-chat scenarios. The cache-manager-mcp tool accepts input parameters like token values, TTL settings, and memory data, and outputs cost insights and optimized token usage over the MCP protocol.

Canonical page: https://skillsregistry.net/skills/datawithdanny-cache-manager-mcp  
JSON: https://api.skillsregistry.net/v1/skills/datawithdanny-cache-manager-mcp

## Description

Save tokens across AI agent chats with prompt TTL tracking, handoff memories, and cost insights — over MCP.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/datawithdanny/cache-manager-mcp)

## 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": "datawithdanny-cache-manager-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/datawithdanny-cache-manager-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/datawithdanny-cache-manager-mcp/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