PentestLLM

Yetkili sızma testleri, red team çalışmaları ve CTF çalışmaları için PentestLLM anahtarınızla MCP araçları olarak güvenlik için ayarlanmış ve sansürsüz modeller: sohbet edin, karşılaştırın, arayın, gömme ve yeniden sıralama yapın.

Barındırılan MCP Sunucusu

npx add-mcp 'https://api.pentestllm.ai/mcp'

Claude Code, Codex, Cursor ve daha fazlasına kurulur

Dokümantasyon

Connect in two minutes.

Create a key in the console, set the base URL, pick a model id from the Models page. Three settings, any client.

  • Base URL: https://api.pentestllm.ai/v1
  • Key: sk-ptl-live-… Created in the console, shown once
  • Model: glm-5.3-uncensored Any id from the Models page

OpenAI SDK, Python

from openai import OpenAI

client = OpenAI(base_url="https://api.pentestllm.ai/v1", api_key="sk-ptl-live-…")
reply = client.chat.completions.create(
    model="glm-5.3-uncensored",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True,
)
for chunk in reply:
    print(chunk.choices[0].delta.content or "", end="")

OpenAI SDK, Node

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.pentestllm.ai/v1", apiKey: "sk-ptl-live-…" });
const stream = await client.chat.completions.create({
  model: "glm-5.3-uncensored",
  messages: [{ role: "user", content: "Hello" }],
  stream: true,
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");

Anthropic SDK

Every model answers the Messages API at the same host, so Claude Code and anything built on the Anthropic SDK runs an uncensored build with ANTHROPIC_BASE_URL set to https://api.pentestllm.ai and your key.

import anthropic

client = anthropic.Anthropic(base_url="https://api.pentestllm.ai", api_key="sk-ptl-live-…")
msg = client.messages.create(model="glm-5.3-uncensored", max_tokens=1024, messages=[{"role": "user", "content": "Hello"}])
print(msg.content[0].text)

MCP server

https://api.pentestllm.ai/mcp is an MCP server over the same key: every model becomes a tool in Claude Code, Cursor or any MCP client (chat, compare on several models at once, search, embed, rerank, transcribe, and image, video and speech generation), billed like any other request. The catalog, price estimate and daily check tools need no key.

SillyTavern

API: Chat Completion. Source: Custom (OpenAI-compatible). Custom endpoint: https://api.pentestllm.ai/v1. API key: your key. Then Connect and pick the model from the list it loads. Context Size and reply length for each build are on its model page; the SillyTavern walkthrough shows each screen.

Janitor AI and other proxies

API: Proxy. URL: https://api.pentestllm.ai/v1/chat/completions. Key: your key. Model: the id from the Models page. Any client that takes a custom OpenAI URL works the same way. The Janitor AI proxy guide walks through each field and the errors people hit; HammerAI, RisuAI, KoboldAI Lite, Agnai, Novelcrafter and Xoul have their own pages under guides.

OpenCode and Cline

Add an OpenAI-compatible provider with base URL https://api.pentestllm.ai/v1 and your key, then name the model id. Coding builds such as the uncensored GLM flash code model are on the Models page.

Headers on every answer

x-uplink-request-id identifies the request for support, x-uplink-charge carries the settled charge, and streaming answers end with the usage block. A request that fails before the model answers is not charged.