Model Context Protocol

PromptQuorum Speaks MCP

PromptQuorum runs a public, read-only MCP server, so any MCP-compatible AI assistant — Claude, or any other client speaking the open Model Context Protocol — can search the directory and guides, recommend apps for your hardware, and compare tools directly inside your own chat, without you opening a browser tab.

Connect your AI assistant →https://www.promptquorum.com/api/mcp

Total calls, all time

2,557

Calls, last 30 days

1,693

Calls, last 7 days

160

MCP server in numbers

2,557
Tool calls: 6
Times started

Counted since November 6, 2026. Anonymous totals for all AI assistants: no names, no IP addresses, no question text.

Anonymous call counters. No IP address, user agent or other identifier is ever recorded; only the number of calls per tool is counted. Generated Nov 7, 2026, 5:09 PM UTC.

New here? Start with "start"

start is a command of the PromptQuorum MCP server, not of your AI assistant itself. After you have added the server, open a new chat and type start (or /start). Your assistant opens the PromptQuorum menu, asks what you want to do, and can remember your hardware and preferences if you agree. It is the quickest way to get useful answers.

start

How it works

Connect once, then ask in your own words. Your assistant picks the right tool, calls it, and answers with links back to the source pages. You do not need to know tool names — they are listed here so you can see what is possible.

What it can do

Find apps

find_best_apps
Find the best apps for you
Turns a plain-language goal plus your operating system and memory into a ranked shortlist, with reasons and honest trade-offs.
Ask: I have a 24 GB Mac and want to chat with my PDFs without using the terminal.
search_apps
Recommend apps
Recommend local-AI apps from the directory that match a stated goal and hardware.
Ask: Free Windows apps for image generation that run on 8 GB of VRAM.
recommend_stack
Recommend an app stack
Suggests a ready-made combination of apps for a goal, such as Ollama + Open WebUI, together with its hardware floor.
Ask: Which apps should I combine for a private coding assistant with 32 GB of RAM?
find_local_alternative
Find a local alternative
Maps a cloud AI product such as Midjourney or ElevenLabs to local alternatives, and states the gaps honestly.
Ask: What is a local alternative to ElevenLabs?
get_app_alternatives
Find app alternatives
Finds similar apps when one is too hard, too costly or does not fit your machine.
Ask: ComfyUI is too complicated for me — what is easier?
get_app_details
Get directory entry
Fetch license, hardware requirements, platforms, price and URL for one tool.
Ask: What are the license and hardware needs of Ollama?
list_categories
List categories
List directory categories, use cases and operating systems.
Ask: Which app categories exist, and how many apps are in each?
list_local_models
Browse local models
Lists the curated catalog of widely used local models with parameters, download size, capabilities and license, filtered by size class, capability or use.
Ask: Which local models can read images and are smaller than 10 GB to download?

Decide and check

compare_apps
Compare apps
Compare local-AI apps side by side on license, hardware, platforms and price.
Ask: Compare Ollama, LM Studio and Jan for a beginner.
check_hardware_compatibility
Check hardware compatibility
Says whether an app — and optionally a specific model size — fits your platform and memory, and what to try instead if it does not.
Ask: Will ComfyUI run on my Windows laptop with 8 GB of VRAM?
estimate_vram
Estimate VRAM
Estimates the memory a model needs from its size, quantization and context length, and whether it fits what you have.
Ask: How much memory does a 32B model need at Q4 with an 8K context?
recommend_models
Recommend local models
Picks local LLMs from a curated catalog that fit your computer, with the exact Ollama download command and how your chosen app loads models.
Ask: Which local model should I run in Open WebUI on a 24 GB Mac for coding?
explain_license
Explain a license
Explain the core rule of a software license (AGPL-3.0, Apache 2.0, MIT, …) in plain language.
Ask: Can I use an AGPL-3.0 app inside my company's product?

Read and learn

search_promptquorum
Search PromptQuorum
Search local-LLM guides, prompt-engineering articles, and the software directory.
Ask: How do I run Llama on a Mac?
get_article
Get PromptQuorum article
Fetch the full content of one article by cluster and slug.
Ask: Open the full guide you just found.
find_related_content
Find related content
Collects the review, comparison guide, hands-on test and setup articles for an app or topic.
Ask: Show me the review and setup guides for Open WebUI.
list_pages
List readable pages
Lists every page of the site that is not an article, such as the home page, About, the PromptQuorum app page, Security and Privacy, with a short description of each.
Ask: Which pages does PromptQuorum have besides the articles?
get_page
Read a page
Returns the readable text of one page from list_pages, for example the home page, About, Security or Privacy. Use it when a question is about the site itself rather than an article.
Ask: What does the PromptQuorum About page say?
get_hands_on_test
Hands-on test findings
Returns PromptQuorum's own hands-on findings for an app, with evidence labels — or says plainly that it was not tested.
Ask: Did PromptQuorum actually test BoBe, and what went wrong?
get_latest
What's new
Lists recently added apps, updated articles and published hands-on tests, newest first.
Ask: What was added to the directory recently?
list_clusters
List content clusters
List every content section on the site with a short description.
Ask: What topics does PromptQuorum cover?
get_site_stats
Site size and usage
Returns what PromptQuorum is and how big it is: apps tracked, languages, articles, hands-on tests, AI assistant calls and Ask Hans answers. Read-only anonymous totals.
Ask: What is PromptQuorum and how big is it?

Start and your profile

start
Start here
Opens the guided menu: a short privacy question first, then what this connection can do and a numbered list of tasks. Nothing is saved until you say yes.
Ask: Start
set_consent
Save your privacy choice
Records your yes or no. Yes saves a small pseudonymous profile (language and consent record) under a random code; no saves nothing and every directory tool keeps working.
Ask: Yes, save my language and setup.
my_profile
Show my profile
Shows exactly what is stored for your profile code: consent date, consent text version, language, timestamps and expiry.
Ask: What do you have stored about me?
forget_me
Forget me
Deletes your saved profile and consent record immediately. Withdrawing consent is as easy as giving it.
Ask: Forget me and delete my data.
set_language
Set your language
Switches menus and answers to one of nine languages. It is remembered in your profile only if you have one.
Ask: In German, please.

A worked example

Once connected, you ask in everyday language. The assistant calls the tools and answers with links to the sources.

You

I have a Mac with 24 GB of memory. What should I use to chat with my PDFs?

Tool used: recommend_stack

Assistant

For chatting with PDFs, the directory suggests Ollama, which runs the model, together with AnythingLLM, which lets you load your PDFs and ask questions about them. The stack needs about 16 GB of RAM, with a GPU optional, so your 24 GB is enough. Both are free and run on a Mac. The directory has no verified memory figure for each app, so treat 16 GB as a guideline for the whole stack, not a guarantee.

Links the assistant gave

Shortened from a real recommend_stack response. Answers differ between assistants and depend on what the directory contains when you ask.

Resources and prompts

Besides tools, the server offers read-only resources that an assistant can load as background context, and ready-made prompts you can start from. Support depends on your client; the tools work everywhere.

promptquorum://categories

App categories, use cases and operating systems, with counts.

promptquorum://stacks

Common app stacks by goal, with hardware floors.

promptquorum://app/{slug}

One directory entry, by app slug.

promptquorum://article/{cluster}/{slug}

One article, by cluster and slug.

promptquorum://methodology

How to read the data: verified, unknown and estimated.

Ready-made prompts

start

Open the PromptQuorum menu (/start)

recommend_local_ai_stack

Recommend a local AI stack for my hardware

compare_local_ai_tools

Compare local AI tools for a use case

find_offline_alternative

Find a fully offline alternative to a cloud tool

check_commercial_license

Check whether I can use an app commercially

How to read the answers

1Directory data is editorial and can be out of date. Check the official site before you install.
2"Not researched" or "unknown" means PromptQuorum has no verified figure. It does not mean the answer is no, and it does not mean it will work.
3Memory and VRAM figures for models are estimates, not benchmarks, and say nothing about speed.
4Hands-on findings keep their evidence labels (observed, measured, vendor claim, tester view). Apps we did not test are reported as untested.
5License explanations are general information, not legal advice. An app's license is separate from the license of any model you run in it.

Access and limits

Public, read-only and free, with no sign-in. A fair-use limit of 120 requests per minute per IP address applies. Usage counters are aggregate only; for the rate limit, a hashed IP address is kept for one minute and never linked to what you ask.

Live usage

Anonymous call counters. No IP address, user agent or other identifier is ever recorded; only the number of calls per tool is counted. Generated Nov 7, 2026, 5:09 PM UTC.

MCP server usage

Every call to the PromptQuorum MCP server from any AI assistant is counted. Never stored: names, IP addresses, question text. Apps, categories and languages are recorded only when they match a known directory entry or site language.

MCP server usage	Today (UTC)	Yesterday	Last 7 days	Last 30 days	All time
Tool calls	16	49	160	1,693	2,557
Times started	0	0	0	6	6

2026-10-092026-11-07

Tool calls per day, last 30 days

Tools Ask Hans used

Tools Ask Hans used	Today (UTC)	Yesterday	Last 7 days	Last 30 days	All time
get_article	6	6	40	970	1,153
get_app_details	1	1	8	387	461
search_promptquorum	7	7	53	154	614
search_apps	0	0	9	42	158
get_hands_on_test	1	0	2	28	28
recommend_models	0	28	28	28	28
estimate_vram	0	2	2	20	20
list_clusters	0	0	1	10	19
get_latest	0	0	2	9	9
compare_apps	1	1	5	8	18
list_categories	0	0	3	8	16
find_best_apps	0	0	2	8	8
start	0	0	0	6	6
recommend_stack	0	1	2	5	5
check_hardware_compatibility	0	2	2	3	3
find_related_content	0	0	0	2	2
my_profile	0	0	0	2	2
forget_me	0	0	0	1	1
list_local_models	0	1	1	1	1
set_consent	0	0	0	1	1
explain_license	0	0	0	0	4
find_local_alternative	0	0	0	0	0
get_app_alternatives	0	0	0	0	0
get_page	0	0	0	0	0
get_site_stats	0	0	0	0	0
list_pages	0	0	0	0	0
set_language	0	0	0	0	0

Apps researched

Apps researched	Today (UTC)	Yesterday	Last 7 days	Last 30 days
Ollama	2	4	6	6
llama.cpp	1	1	2	2
LM Studio	1	1	2	2
vLLM	1	1	2	2
Open WebUI	0	1	1	1

Directory categories researched

No data yet

Question languages

Question languages	Today (UTC)	Yesterday	Last 7 days	Last 30 days
DE	6	6	12	12

Counted since November 6, 2026. Tools are counted from the first call. Apps, categories and languages show what assistants asked about, so one call can appear in several rows and the tables do not add up to the number of calls. Those tables start on the day counting began.

Raw JSON: /api/mcp-status. Directory data is editorial and may be out of date. PromptQuorum does not verify download links.