Pincer runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 18 Feb 2026.
Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture
Nothing serious here today
Today is the operative word: we check Pincer every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pincer -e 'PINCER_PROXY_TOKEN=<PINCER_PROXY_TOKEN>' -- npx -y pincer-mcp{
"mcpServers": {
"pincer": {
"command": "npx",
"args": [
"-y",
"pincer-mcp"
],
"env": {
"PINCER_PROXY_TOKEN": "<PINCER_PROXY_TOKEN>"
}
}
}
}[mcp_servers.pincer]
command = "npx"
args = ["-y", "pincer-mcp"]
env = { PINCER_PROXY_TOKEN = "<PINCER_PROXY_TOKEN>" }{
"mcpServers": {
"pincer": {
"command": "npx",
"args": [
"-y",
"pincer-mcp"
],
"env": {
"PINCER_PROXY_TOKEN": "<PINCER_PROXY_TOKEN>"
}
}
}
}{
"servers": {
"pincer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"pincer-mcp"
],
"env": {
"PINCER_PROXY_TOKEN": "<PINCER_PROXY_TOKEN>"
}
}
}
}Put your own value in place of
<PINCER_PROXY_TOKEN> (Proxy token for agent authentication (generated via 'pincer agent add')).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
OPENWEBUI_URL (Optional: Base URL for OpenWebUI instance), OPENAI_COMPATIBLE_URL (Optional: Base URL for OpenAI-compatible instance), AUDIT_LOG_PATH (Optional: Custom path for audit logs (default: ~/.pincer/audit.jsonl)).
Alternatives to Pincer
same job, measured the same wayCordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.
Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend
Scans an MCP server for security gaps before your agent connects. Free tier, no signup.
Security, cost, and health governance proxy for MCP infrastructure
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Pincer — questions
Answers built from our own checks of this server.