# AgentMint

> Use this tool when you need to securely authorize AI agents with cryptographic controls, solving problems of unauthorized access and prompt injection. AgentMint provides scoped delegation and checkpoint escalation with Ed25519 signed receipts, ensuring secure communication and authentication. Ideal for use cases requiring high-security boundaries, such as sensitive data processing or high-stakes decision-making.

Canonical page: https://skillsregistry.net/skills/agentmint-agentmintmcp  
JSON: https://api.skillsregistry.net/v1/skills/agentmint-agentmintmcp

## Description

Cryptographic authorization for AI agents. Scoped delegation, checkpoint escalation, Ed25519 signed receipts. Block prompt injection at the tool boundary.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** finance
- **Updated:** 2026-06-11

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/agentmint/agentmintmcp)

## 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": "agentmint-agentmintmcp"
    }
  }
}
```

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