# Pincer-MCP

> Pincer-MCP — vouchlyai-pincer-mcp. Use this tool when you need to securely integrate AI agents with large language model (LLM) APIs, protecting sensitive API keys from exposure. Pincer-MCP enables secure API calls using ephemeral proxy tokens, solving key management and security risks. It provides a secure gateway interface for AI agents to access LLM APIs like Gemini, OpenAI, and Claude.

Canonical page: https://skillsregistry.net/skills/vouchlyai-pincer-mcp  
JSON: https://api.skillsregistry.net/v1/skills/vouchlyai-pincer-mcp

## Description

A security-hardened MCP gateway that enables AI agents to call LLM APIs (Gemini, OpenAI, Claude, etc.) using ephemeral proxy tokens, eliminating exposure of real API keys.

## Trust

- **Trust score (0–1):** 0.58
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/u0gr57qw2w)
- **Repository:** <https://github.com/VouchlyAI/Pincer-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": "vouchlyai-pincer-mcp"
    }
  }
}
```

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