# agentkeys-mcp

> Use this tool when you need to securely manage API credentials and make proxied API calls, keeping sensitive information hidden from AI agents. It solves the problem of protecting secrets and credentials from exposure, enabling secure interactions with external APIs. The tool accepts API credentials as input and outputs proxied API calls, making it ideal for use cases where security and secrecy are paramount.

Canonical page: https://skillsregistry.net/skills/agentkeys-io-agentkeys-mcp  
JSON: https://api.skillsregistry.net/v1/skills/agentkeys-io-agentkeys-mcp

## Description

Enables AI agents to securely manage API credentials and make proxied API calls through AgentKeys, keeping secrets hidden from the agent.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/cbx82vmqjh)
- **Repository:** <https://github.com/agentkeys-io/agentkeys-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": "agentkeys-io-agentkeys-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/agentkeys-io-agentkeys-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/agentkeys-io-agentkeys-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