Pincer MCP Server

Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture

Remote serverstreamable-http

What is the Pincer MCP server?

Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture. Exposed over MCP by the pincer mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

Its toolset

Everything the assistant can do here goes through one of these:

  • gemini_generate — Secure Google Gemini API calls
  • openai_chat — Chat completions with OpenAI GPT models (gpt-4o, gpt-4-turbo, gpt-3.5-turbo, etc.)
  • openai_list_models — List all available OpenAI models
  • openai_compatible_chat — Chat completions with any OpenAI-compatible API (Azure OpenAI, Ollama, vLLM, etc.)
  • openai_compatible_list_models — List models from custom OpenAI-compatible endpoints
  • claude_chat — Chat completions with Anthropic Claude models (Claude 3.5 Sonnet, Opus, Haiku)
  • openrouter_chat — Unified API access to 100+ models from multiple providers (OpenAI, Anthropic, Google, Meta, etc.)
  • openrouter_list_models — List all available models across OpenRouter providers
  • openwebui_chat — OpenAI-compatible interface for self-hosted LLMs
  • openwebui_list_models — Discover available models on an OpenWebUI instance
  • gpg_sign_data — Sign data or files using a GPG/PGP private key stored in Pincer's vault. (Keyless Execution — agent never sees the key)
  • gpg_decrypt — Decrypt PGP-encrypted data using a vault-stored private key

Configuration

You will need one environment variable: PINCER_PROXY_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Node.js 18+ - macOS, Windows, or Linux with native keychain support

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pincer's toolset — gemini_generate, openai_chat, openai_list_models and 11 more — is a fair guide to whether it matches your workflow. It is maintained by VouchlyAI; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pincer's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Pincer.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the pincer mcp server does with a few real requests.

Available tools

ToolWhat it does
gemini_generateSecure Google Gemini API calls.
openai_chatChat completions with OpenAI GPT models (gpt-4o, gpt-4-turbo, gpt-3.5-turbo, etc.).
openai_list_modelsList all available OpenAI models.
openai_compatible_chatChat completions with **any** OpenAI-compatible API (Azure OpenAI, Ollama, vLLM, etc.).
openai_compatible_list_modelsList models from custom OpenAI-compatible endpoints.
claude_chatChat completions with Anthropic Claude models (Claude 3.5 Sonnet, Opus, Haiku).
openrouter_chatUnified API access to 100+ models from multiple providers (OpenAI, Anthropic, Google, Meta, etc.).
openrouter_list_modelsList all available models across OpenRouter providers.
openwebui_chatOpenAI-compatible interface for self-hosted LLMs.
openwebui_list_modelsDiscover available models on an OpenWebUI instance.
gpg_sign_dataSign data or files using a GPG/PGP private key stored in Pincer's vault. *(Keyless Execution — agent never sees the key)*
gpg_decryptDecrypt PGP-encrypted data using a vault-stored private key.
PrerequisitesThe Prerequisites tool exposed by this server.
InstallationThe Installation tool exposed by this server.

How to install the Pincer MCP server

{
  "mcpServers": {
    "pincer": {
      "command": "npx",
      "args": ["-y", "pincer-mcp"],
      "env": {
        "PINCER_PROXY_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Node.js 18+ - macOS, Windows, or Linux with native keychain support
VariableDescriptionRequired
PINCER_PROXY_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Pincer to gemini generate.
  • Use Pincer to openai chat.
  • Use Pincer to openai list models.

Frequently asked questions

It connects Pincer to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (gemini_generate, openai_chat, openai_list_models, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Pincer directly.