MCP.Market

Pincer MCP server

by VouchlyAI·io.github.VouchlyAI/pincer·v0.1.5·6 stars
No reviews yet

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

C65/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C65/100

full report

Adoption
New

6 stars28 downloads/wk

Reviews

Write one

Nobody has reviewed Pincer yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Pincer tools (10)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • claude_chat

    Chat completions using Anthropic's Claude models. Supports Claude 3.5 Sonnet, Claude 3 Opus, Haiku, and more. Uses Messages API with separate system parameter.

  • gemini_generate

    Generate content using Google's Game Gemini AI models. Supports Flash and Pro variants.

  • openai_chat

    Chat completions using OpenAI API. Supports GPT models including gpt-4o, gpt-4-turbo, gpt-3.5-turbo, and more.

  • openai_compatible_chat

    Chat completions using any OpenAI-compatible API endpoint. Perfect for Azure OpenAI, local Ollama, vLLM servers, or other OpenAI-spec providers. Requires OPENAI_COMPATIBLE_URL env var or 'url' parameter.

  • openai_compatible_list_models

    List all available models from an OpenAI-compatible endpoint. Use this to discover which models are available. Requires OPENAI_COMPATIBLE_URL env var or 'url' parameter.

  • openai_list_models

    List all available models from OpenAI. Use this to discover which models are available before making chat requests.

  • openrouter_chat

    Chat completions using OpenRouter's unified API. Access 100+ models from multiple providers (OpenAI, Anthropic, Google, Meta, Mistral, etc.) through a single endpoint. Model names are provider-prefixed (e.g., 'openai/gpt-4', 'anthropic/claude-3-5-sonnet').

  • openrouter_list_models

    List all available models from OpenRouter. Returns 100+ models from multiple providers including OpenAI, Anthropic, Google, Meta, and more.

  • openwebui_chat

    Chat completions using OpenWebUI API. Supports any OpenWebUI instance (hosted or self-hosted) with OpenAI-compatible chat API.

  • openwebui_list_models

    List all available models from OpenWebUI instance. Use this to discover which models are available before making chat requests.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

no findings
  • Code scan36 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 222 days ago4/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 65/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Pincer compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
65/100
higher than 25% of 4,460 AI and agents servers
Tools
10
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
6
more than 80% of 2,711 AI and agents servers
Downloads a week
28
more than 14% of 1,538 AI and agents servers with a package

What its tools let an agent do: 2 read · 8 create

Install Pincer in Claude Code, Cursor or VS Code

Runs npx -y pincer-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add pincer -- npx -y pincer-mcp
Add to Cursor

What the publisher says

From the Pincer repository's README, as published. We do not edit it. Read it on GitHub

Pincer MCP 🦀

Pincer-MCP is a security-hardened Model Context Protocol (MCP) gateway that eliminates the "Lethal Trifecta" vulnerability in agentic AI systems. By acting as a stateless intermediary, Pincer ensures agents never see your real API keys.

🔒 The Problem

Current AI agents store long-lived API keys in plain-text .env files or local databases. If compromised via prompt injection or host intrusion, attackers gain direct access to your:

  • Database passwords
  • Third-party API keys

✨ The Solution: Proxy Token Architecture

Pincer implements a "blindfold" security model:

  1. Agent knows: Only a unique proxy token (pxr_abc123...)
  2. Pincer knows: Mapping of proxy tokens → real API keys (encrypted in OS keychain)
  3. Agent never sees: The actual credentials
sequenceDiagram
    participant Agent
    participant Pincer
    participant Vault (OS Keychain)
    participant External API

    Agent->>Pincer: tools/call + proxy_token: pxr_abc123
    Pincer->>Vault: Decrypt real API key
    Vault-->>Pincer: gemini_api_key: AIzaSy...
    Pincer->>External API: API call with real key
    External API-->>Pincer: Response
    Pincer->>Pincer: Scrub key from memory
    Pincer-->>Agent: Response (no credentials)

📦 Available Tools

  • 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.).
  • openailistmodels: List all available OpenAI models.
  • openaicompatiblechat: Chat completions with any OpenAI-compatible API (Azure OpenAI, Ollama, vLLM, etc.).
  • openaicompatiblelist_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.).
  • openrouterlistmodels: List all available models across OpenRouter providers.
  • openwebui_chat: OpenAI-compatible interface for self-hosted LLMs.
  • openwebuilistmodels: Discover available models on an OpenWebUI instance.
  • gpgsigndata: 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.

🔑 GPG Key Management

# Generate a new GPG keypair (private key stored in vault)
pincer key generate --name "Release Signing" --email dev@example.com

# Import an existing PGP private key
pincer key import ./my-key.asc --passphrase "my-passphrase"

# List all stored GPG keys
pincer key list

# Export public key (safe to share)
pincer key export <key-id>

# Authorize an agent for signing
pincer agent authorize mybot gpg_sign_data --key <key-id>

(More callers coming soon!)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Pincer: common questions

Is Pincer MCP server safe?
With care: it is graded C, so read the findings first (65/100). Read the Pincer safety report
How do I install Pincer?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Pincer need an API key?
Yes. The registry entry asks for PINCER_PROXY_TOKEN.
Is Pincer maintained?
The last commit was 259 days ago (2026-02-18). The latest release is v0.1.5.
What can I use instead of Pincer?
Servers from other publishers that do the same job: llmtrim MCP server, HOL Guard MCP server and Commonly MCP server.
How does Pincer compare with other AI and agents MCP servers?
safety score 65/100 (higher than 25% of 4,460 AI and agents servers); tools 10 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Pincer

Same job from other publishers: the closest match first, then the best rated.

  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Commonly
    Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.
    A
  • mcptoon
    MCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).
    A
  • VisualTorch
    Render PyTorch architecture diagrams and animated GIF reveals from trusted model source.
    A