Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
23 pay-per-call AI APIs for agents: x402, USDC on Base, no API keys.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://mazzagrp.com/mcpRun this in your terminal
claude mcp add --transport http mazzagrp https://mazzagrp.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mazzagrp": {
"url": "https://mazzagrp.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"mazzagrp": {
"type": "http",
"url": "https://mazzagrp.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://mazzagrp.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
demo_freeOne real LLM answer, no payment — validates the x402 flow before you pay. FREE — no payment required.
event_opsEvent planning & operations for catering/corporate/hospitality agents: run-of-show, staffing, risk, vendor negotiation, budget guardrails. Price: $2.50/call (x402, USDC on Base).
ai_consultationAI consultation with a senior strategist. Price: $5.00/call (x402, USDC on Base).
workflow_automationAI-powered workflow automation design and implementation. Price: $15.00/call (x402, USDC on Base).
chatbotConversational AI chatbot interaction. Price: $1.00/call (x402, USDC on Base).
web_agentAI web agent for autonomous browsing and task execution. Price: $1.80/call (x402, USDC on Base).
simulationAI scenario simulation and modeling. Price: $2.00/call (x402, USDC on Base).
worldbuilderAI worldbuilding for fiction, games, and RPGs. Price: $2.00/call (x402, USDC on Base).
mcp_evalMCP (Model Context Protocol) evaluation and scoring. Price: $2.00/call (x402, USDC on Base).
knowledge_recallMemory recall and context retrieval. Price: $0.20/call (x402, USDC on Base).
autoflowAI-powered automated workflow orchestration. Price: $1.50/call (x402, USDC on Base).
rag_queryRetrieval-augmented generation pipeline. Price: $1.50/call (x402, USDC on Base).
negotiation_advisorAI negotiation assistant and strategy advisor. Price: $1.50/call (x402, USDC on Base).
desktop_assistantDesktop application AI assistant. Price: $1.50/call (x402, USDC on Base).
longform_qaLong-form question answering with deep analysis. Price: $1.00/call (x402, USDC on Base).
text_to_sqlAI-powered SQL query generation and optimization. Price: $1.20/call (x402, USDC on Base).
model_arenaAI model comparison and benchmarking arena. Price: $1.20/call (x402, USDC on Base).
design_recommendationsAI-assisted design recommendations and mockups. Price: $0.80/call (x402, USDC on Base).
temporal_orchestrationTemporal workflow orchestration assistant. Price: $0.80/call (x402, USDC on Base).
puzzle_solverAI puzzle generation and solving. Price: $0.80/call (x402, USDC on Base).
storyforgeAI-powered creative story generation and worldbuilding. Price: $0.60/call (x402, USDC on Base).
sheets_automationAI spreadsheet formula generation and data analysis. Price: $1.00/call (x402, USDC on Base).
character_roleplayAI character generation and development. Price: $0.10/call (x402, USDC on Base).
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain mazzagrp.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 105 ms (HTTP 200)
No sign-in needed
Read 23 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.2.0) reached the registry 3 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Signoff
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
23 AI APIs from mazzagrp.com behind one MCP endpoint. Agents pay per call with x402 v2 / USDC on Base mainnet — no API keys, no signup, no subscription.
/.well-known/x402.json · /.well-known/mcp/server-card.json · agents.mdNothing to install. Point your client at the URL:
{
"mcpServers": { "mazzagrp": { "type": "http", "url": "https://mazzagrp.com/mcp" } } }
Claude Code: claude mcp add --transport http mazzagrp https://mazzagrp.com/mcp Cursor / Grok / any client that takes a URL: paste https://mazzagrp.com/mcp.
Payments are signed by the client's own wallet (the x402 flow returns a 402 with the requirements; your client settles in USDC on Base). The remote server never holds your key.
pip install mazzagrp-mcp
{
"mcpServers": { "mazzagrp": { "command": "mazzagrp-mcp", "env": { "MAZZAGRP_WALLET_KEY": "0xYOUR_PRIVATE_KEY" } } } }
Or with a wallet file: MAZZAGRP_WALLET_PATH=/path/to/wallet.json ({"private_key": "0x...", "address": "0x..."}).
Nota: il pacchetto stdio espone 21 tool con i nomi storici (
recall,rag,
sql, …). Il server remoto — quello a cui punta il registry — ne espone 23 con
nomi più espliciti (
knowledge_recall,rag_query,text_to_sql, …).
Le API sottostanti sono le stesse. Per i client nuovi usa il remoto.
| API path | Price (USDC) | What it does |
|---|---|---|
/api/ping | 0.01 | AI ping — one-sentence answer, validates the payment flow end to end |
/api/character | 0.10 | Character development |
/api/recall | 0.20 | Memory recall / context retrieval |
/api/storyforge | 0.60 | Creative storytelling |
/api/design | 0.80 | Design recommendations |
/api/temporal | 0.80 | Temporal.io workflow design |
/api/puzzles | 0.80 | Puzzle and riddle generation |
/api/chatbot | 1.00 | Conversational AI |
/api/longqa | 1.00 | Long-form Q&A |
/api/sheets | 1.00 | Spreadsheet formulas and analysis |
/api/sql | 1.20 | SQL generation and optimisation |
/api/arena | 1.20 | LLM benchmarking / comparison |
/api/autoflow | 1.50 | Workflow orchestration |
/api/rag | 1.50 | Retrieval-augmented generation |
/api/negotiator | 1.50 | Negotiation strategy |
/api/desktop | 1.50 | Desktop app development guidance |
/api/webagent | 1.80 | Autonomous web agent |
/api/simulation | 2.00 | Scenario simulation |
/api/worldbuilder | 2.00 | Worldbuilding for fiction and games |
/api/mcp-eval | 2.00 | MCP implementation assessment |
/api/event-ops | 2.50 | Event operations (catering, corporate, hospitality) |
/api/consultation | 5.00 | Senior AI strategy consultation |
/api/automation | 15.00 | Full automation workflow design |
Source of truth: /.well-known/x402.json (23 endpoints, generated from the API's own endpoint table).
accepts[0].amount, network eip155:8453).PAYMENT-SIGNATURE header.eip155:8453)0x833589fCD6eDb6E08f4c7C32D4f71b54bdA029130xD98b6969fab0bA4D4BB086fF273ff7CCD284CEe8⚠️ Le versioni precedenti di questo README dicevano "Base Sepolia (testnet)".
Era sbagliato: il servizio è su Base mainnet. Un wallet finanziato su
Sepolia non paga nulla.
demo_free returns one real LLM answer without payment, so an agent can verify the whole flow before funding a wallet.
MIT