PentestLLM

● Active

io.github.uplinkswitch/pentestllm

Uncensored models for authorized security testing, prices readable without a key

Connect this server

One click to install, or copy the config below. Suits: Cursor · HTTP clients.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "pentestllm": {
      "url": "https://api.pentestllm.ai/mcp"
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --transport http pentestllm https://api.pentestllm.ai/mcp
VS Code
code --add-mcp '{"name":"pentestllm","type":"http","url":"https://api.pentestllm.ai/mcp"}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Security & Identity
Version
0.1.0
Registry
active
Published
11/15/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: PentestLLM is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit 7 days ago (Nov 15, 2026), 0 open issues.
Official registry
Active
Published as io.github.uplinkswitch/pentestllm in the official MCP registry, version 0.1.0.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
Hosted by the publisher
Your client talks to api.pentestllm.ai: prompts and tool arguments leave your machine for that host.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 09:09 UTCStatus history & uptime →
● Working82 msprotocol 2025-06-18v2026-10-19toolsprompts

The endpoint answered the MCP handshake as "PentestLLM" and listed 15 tools. Answering since Nov 18, 2026.

Context cost ≈ 4.3k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 15 tools.

Tools (15)

  • list_models3 params

    Every chat, embedding, rerank and transcription model on PentestLLM with its id, type, the routes and tools that take it, our price (per million tokens, or per audio minute for transcription), the developer's list price where recorded, the wire formats it answers (openai, anthropic, gemini) and its specs. Image, video, speech, music and 3D models are in list_media_models. No key needed. Live from GET /v1/catalog.

    Show parameters
    • typestringOnly models of this type. Default: every text model.
    • developerstringOnly models from this developer (Anthropic, OpenAI, Google, DeepSeek...).
    • searchstringA substring of the model id or name (opus, deepseek, uncensored...).
  • list_media_models2 params

    Every media model on PentestLLM with its id, kind, endpoint, unit and price per image, second, generation or minute at each setting, next to the developer's price where recorded. No key needed. Live from GET /v1/catalog/media.

    Show parameters
    • kindstringOnly models of this kind.
    • searchstringA substring of the model id or name (nano-banana, veo, kling...).
  • media_model1 param

    Everything generate needs to call one image, video, speech, music or 3D model: each setting under params with its type, the values it takes, its range and its default, and the price per unit at each setting under pricing. No key needed. Live from GET /v1/catalog/media.

    Show parameters
    • modelstringrequiredA media model id from list_media_models (nano-banana-2, kling-3.0-pro, seedance-2, elevenlabs-v3, image-upscaler...).
  • estimate5 params

    The cost of a request on every chat model (or the ids given), cheapest first, with the developer's list cost and the saving. Give input_tokens, or a prompt / messages to count from. With the caller's key, prices are the key's own (price locks included). Live from POST /v1/estimate.

    Show parameters
    • input_tokensintegerPrompt tokens. Give this or a prompt / messages to count from.
    • output_tokensintegerCompletion tokens. Default 1000.
    • promptstringText to estimate the prompt tokens from, instead of input_tokens.
    • messagesarrayChat messages to estimate from, instead of input_tokens.
    • modelsarrayModel ids to price. Default: every chat model, cheapest first.
  • media_quote2 params

    What generate would charge for exactly these settings, at the key's own rates: the units billed, the charge, and the developer's own price for the same request where one is on record. The settings are checked as a real request's would be, so a wrong value fails here, not at the model. Nothing runs and nothing is charged. Needs the key. Live from POST /v1/generations/quote.

    Show parameters
    • modelstringrequiredA media model id from list_media_models.
    • inputobjectrequiredThe model's settings, as media_model lists them under params: prompt, size or aspect_ratio, resolution, duration, image_urls, text, voice... A setting left out
  • proof1 param

    Whether each model is still the model it says it is: every day one fixed prompt goes to every model and the verdict per model is stable, changed, failed or unchecked, with the time of the last check and how long the answer has been unchanged. No key needed. Live from GET /v1/proof.

    Show parameters
    • modelstringOne model id. Default: every model.
  • chat7 params

    Sends messages to any chat model id through POST /v1/chat/completions and returns the answer, the token usage and what the request cost. system adds instructions, image_urls lets a model that sees images look at them (a file generate made works), web_search lets the model search while it answers. Billed to the key in the MCP request's Authorization header (Bearer sk-ptl-live-...); without one it fails.

    Show parameters
    • modelstringrequiredA chat model id from list_models.
    • messagesarrayrequiredThe conversation, OpenAI chat format.
    • systemstringInstructions placed ahead of the conversation as a system message.
    • image_urlsarrayImage URLs attached to the last user message, for the chat models that take images (input_modalities in list_models). A file generate made works.
    • web_searchbooleanTrue: the model may search the web while it answers (billed per search, the price in GET /v1/catalog server_tools).
    • max_tokensintegerCap on completion tokens.
    • temperaturenumber
  • compare7 params

    Sends the same conversation (or one prompt) to 2 to 5 chat model ids at once through POST /v1/chat/completions and returns every answer side by side with its token usage, cost and time, plus the total. For a second opinion from another model, or to pick the model that answers a kind of question best. Completions are capped at max_tokens each (default 1024). Each model is billed to the key in the MCP request's Authorization header; a model that fails is reported and not charged.

    Show parameters
    • modelsarrayrequired2 to 5 chat model ids from list_models, asked at the same time.
    • promptstringOne user message, in place of messages.
    • messagesarrayThe conversation, OpenAI chat format.
    • systemstringInstructions placed ahead of the conversation as a system message.
    • image_urlsarrayImage URLs attached to the last user message, for the chat models that take images (input_modalities in list_models). A file generate made works.
    • max_tokensintegerCap on completion tokens per model. Default 1024.
    • temperaturenumber
  • search3 params

    One web search through POST /v1/search: titles, URLs, snippets and publish dates, up to 10 results, optionally only from the last day, week, month or year. Billed as one search to the key in the MCP request's Authorization header (the price in GET /v1/catalog server_tools); a search that fails is not charged.

    Show parameters
    • querystringrequiredWhat to search for, up to 400 characters.
    • max_resultsinteger1 to 10 results. Default 5.
    • freshnessstringOnly pages published inside this window.
  • embed2 params

    Embeds one text or up to 64 through POST /v1/embeddings with an embedding model id from list_models (type embedding) and returns one vector per text, in order, with the token usage and the charge. Billed to the key in the MCP request's Authorization header.

    Show parameters
    • modelstringrequiredAn embedding model id from list_models (type embedding).
    • inputrequiredOne text, or up to 64 texts, to embed.
  • rerank4 params

    Orders up to 100 documents by relevance to a query through POST /v1/rerank with a rerank model id from list_models (type rerank): each result's index into documents, its score and its text, best first. Billed per input token to the key in the MCP request's Authorization header.

    Show parameters
    • modelstringrequiredA rerank model id from list_models (type rerank).
    • querystringrequiredWhat the documents are ranked against.
    • documentsarrayrequiredUp to 100 texts to rank.
    • top_nintegerHow many to return, best first. Default: all.
  • transcribe5 params

    Turns the speech in an audio or video file at an https URL (25 MB at most; a file generate made works) into text through POST /v1/audio/transcriptions, or into English with translate. Use a transcription model id from list_models (type transcription). Billed per second of audio to the key in the MCP request's Authorization header; a request that fails is not charged.

    Show parameters
    • modelstringrequiredA transcription model id from list_models (type transcription).
    • audio_urlstringrequiredAn https URL of the audio or video file: mp3, mp4, m4a, wav, webm, ogg, flac or aac, 25 MB at most. A file generate made works.
    • languagestringThe spoken language as an ISO-639-1 code (en, es, zh...), when known.
    • promptstringNames or words to spell right, or the text that came before.
    • translatebooleanTrue: translate the speech into English instead (the models that can).
  • generate4 params

    Runs any media model id from list_media_models with its settings (see media_model) through POST /v1/generations, waits up to wait_seconds for the files, and returns the generation: a link per file (kept 30 days), a finished image inline, and the charge. A video that is still running when the wait ends is returned as it stands; call generation with its id to keep waiting. Charged to the key in the MCP request's Authorization header when the model accepts the task; a failed generation is refunded in full. To go from an image to a video or an edit, pass the image's URL in image_urls.

    Show parameters
    • modelstringrequiredA media model id from list_media_models.
    • inputobjectrequiredThe model's settings, as media_model lists them under params: prompt, size or aspect_ratio, resolution, duration, image_urls, text, voice... A setting left out
    • wait_secondsintegerSeconds to wait for the files before answering with the generation as it stands, 0 to 120. Images usually finish inside the default 60; a video takes minutes, s
    • previewbooleanDefault true: a finished image comes back inline as image content besides its link.
  • generation3 params

    One generation by id: its status, progress, files and charge, waiting up to wait_seconds for it to finish first. Use it after generate answers with a video still running. Needs the key the generation was made with. Live from GET /v1/generations/{id}.

    Show parameters
    • idstringrequiredThe generation id generate answered with (gen_ then 24 hex characters).
    • wait_secondsintegerSeconds to wait for the files before answering with the generation as it stands, 0 to 120. Images usually finish inside the default 60; a video takes minutes, s
    • previewbooleanDefault true: a finished image comes back inline as image content besides its link.
  • generations5 params

    The organization's generations, newest first, each with its status, model, files and charge: the asset library behind generate. Filter by kind, model or status; page with before. Files are kept 30 days. Needs the key. Live from GET /v1/generations.

    Show parameters
    • limitintegerHow many, newest first. Default 20.
    • kindstring
    • modelstringOnly this media model id.
    • statusstring
    • beforeintegerOnly generations created before this Unix time (seconds, or the ms next_before of the last page).

Checked by Serverdex with a plain initialize + tools/list call to api.pentestllm.ai/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 16, 2026
Stars
0
Forks
0
Last push
Nov 15, 2026
License
MIT

TypeScriptai-gatewayclaudecursorimage-generationllmmcpmodel-context-protocolopenai-compatiblestdio-serveruncensored

From the README

UplinkSwitch MCP server An MCP server for UplinkSwitch: every chat, embedding, rerank and transcription model on one API key, with the full price catalog readable before you sign up. The catalog tools need no API key. An agent can list models, compare prices per million tokens and read a model's context window and capabilities before anyone creates an account. Only chat needs a key. Install Or from source: Configure Claude Desktop (claudedesktopconfig.json), Claude Code, Cursor, Windsurf, Zed and any other MCP client: UPLINKSWITCHAPIKEY is only needed for chat. Keys come from . UPLINKSWITCHBASEURL points the server at another host on the same network, default https://api.uplinkswitch.com/v1: The catalog tools work against every one of them without a key, so you can compare the whole network's pricing. Tools Why one key for every model UplinkSwitch is a gateway: the same key and the same base URL reach Claude, GPT, Gemini, Grok, DeepSeek, GLM, Qwen, Kimi and the open-weight models, through the OpenAI, Anthropic and Google wire formats. There is no subscription and no monthly minimum — you buy prepaid credit and pay per token at the published price. • Prices and the full catalog: • OpenAI and Anthropic compatible: https://api.uplinkswitch.com/v1 • The catalog this server reads: • OpenAPI document: Sibling servers Each brand runs its own MCP endpoint on the same protocol.…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://api.pentestllm.ai/mcp

The most-starred Security & Identity servers in the index, with their live-check result.

ServerStarsLast pushLive check
Handsy AI5,215Nov 2026Local / not checked
HOL Guard1,118Nov 2026Local / not checked
SonarQube MCP Server689Nov 2026Local / not checked
MCP Ssh Manager545Nov 2026Local / not checked
Security Detections529Nov 2026Local / not checked

PentestLLM: questions people ask

Is PentestLLM a remote or a local MCP server?
According to its entry in the official MCP registry, PentestLLM ships as a hosted endpoint (streamable-http) that your client connects to by URL.
Does PentestLLM need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is PentestLLM safe to use?
Looks healthy: PentestLLM is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is PentestLLM still maintained?
Active: the repository's last commit 7 days ago. Last push Nov 15, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 16, 2026.
What tools does PentestLLM expose?
15 tools as listed by the server itself during the live check, including list_models, list_media_models, media_model, estimate, media_quote. The full list with parameters is in the Live check section above.
How do I add PentestLLM to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.

More from uplinkswitch

All 5 servers by uplinkswitch →
  1. UnrestrictableUncensored chat and image models on one key, no prompt logs, prices readable without a key
  2. RelaySwitchOne key for coding agents and editors: 350 models, presets and fallbacks, prices readable without a
  3. UncensoredLLMAbliterated and derestricted open-weight models on one prepaid key, prices readable without a key
  4. UplinkSwitch350 chat, image and speech models on one API key, prices readable without a key
Browse all Security & Identity →

Add the badge to your site

Show visitors that PentestLLM is listed here — it’s also the link we check for a free listing.

PentestLLM — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-uplinkswitch-pentestllm?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="PentestLLM — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![PentestLLM — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-uplinkswitch-pentestllm?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/io-github-uplinkswitch-pentestllm) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/io-github-uplinkswitch-pentestllm) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/io-github-uplinkswitch-pentestllm)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/io-github-uplinkswitch-pentestllm"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-github-uplinkswitch-pentestllm"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-github-uplinkswitch-pentestllm"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).