# latchkey

> latchkey — sanjoydat1-latchkey. Use this tool when you need to securely manage AI agent access to specific tools and capabilities. Latchkey solves the problem of controlling and limiting AI agent interactions by issuing time-boxed and scope-limited grants, ensuring authorized and restricted tool usage. It takes in capability requests and outputs authorized tokens, making it ideal for use cases requiring fine-grained access control and secure authorization.

Canonical page: https://skillsregistry.net/skills/sanjoydat1-latchkey  
JSON: https://api.skillsregistry.net/v1/skills/sanjoydat1-latchkey

## Description

Capability-token gate for AI agents. Mint time-boxed, scope-limited grants that authorize specific tool calls.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/z360ow6htb)
- **Repository:** <https://github.com/SanjoyDat1/latchkey>

## 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": "sanjoydat1-latchkey"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sanjoydat1-latchkey` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sanjoydat1-latchkey/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