Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
MCP for AgentStorefront — discover, price, and subscribe to paid agent services.
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 …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"agentstorefront": {
"command": "npx",
"args": [
"-y",
"@lfidele/agentstorefront-mcp"
]
}
}
}Run this in your terminal
claude mcp add agentstorefront -- npx -y @lfidele/agentstorefront-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"agentstorefront": {
"command": "npx",
"args": [
"-y",
"@lfidele/agentstorefront-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": {
"agentstorefront": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@lfidele/agentstorefront-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.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
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.
Runs on your computer; the tool list appears in your AI app after you install it.
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 with the GitHub account lmaniraruta, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 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 on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.1) reached the registry 5 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, MCP Server Autocad Lisp Helper
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.
High-precision static analysis and debug server for AutoCAD AutoLISP (.lsp) files.
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.
MCP server for AgentStorefront — let your AI agents discover, subscribe to, and call agent services from inside Claude, Cursor, or any MCP-aware client.
AgentStorefront is a marketplace where developers list paid agent services (APIs that are designed to be called by other agents — flight-delay prediction, invoice OCR, niche enrichment, etc.).
This MCP server lets any MCP-aware client (like Claude Desktop or Cursor) discover and use those services autonomously — without leaving the agent loop.
| Tool | Purpose |
|---|---|
list_services | List available services, filtered by category |
search_services | Semantic search: "find me a flight-delay API" |
get_service | Full schema + pricing + SLA for a specific service |
request_quote | Get expected monthly cost for an estimated call volume |
Add to your claude_desktop_config.json:
{
"mcpServers": { "agentstorefront": { "command": "npx", "args": ["-y", "@lfidele/agentstorefront-mcp"] } } }
Restart Claude Desktop. The 4 tools above will appear in the tools panel.
Add to ~/.cursor/mcp.json:
{
"mcpServers": { "agentstorefront": { "command": "npx", "args": ["-y", "@lfidele/agentstorefront-mcp"] } } }
npm install -g @lfidele/agentstorefront-mcp
agentstorefront-mcp # runs on stdio
Once installed, you can ask your MCP client things like:
"Find me a flight-delay prediction API on AgentStorefront that costs less than 5 cents per call."
"What's the pricing if I call the invoice-OCR service 10,000 times a month?"
"List the top 5 data-enrichment services on AgentStorefront."
The agent will use these tools transparently.
| Env var | Default | Purpose |
|---|---|---|
AGENTSTOREFRONT_API_URL | https://api.agentstorefront.app | Override API endpoint (self-hosting / staging) |
GitHub: https://github.com/lmaniraruta/agentstorefront-mcp Issues: https://github.com/lmaniraruta/agentstorefront-mcp/issues
Marketplaces only matter if their supply is discoverable. AgentStorefront's listings are useless to other agents unless those agents can FIND them programmatically.
This MCP turns AgentStorefront into native vocabulary for every Claude/Cursor user. A developer asks Claude "is there an API for X?" → Claude lists AgentStorefront services that match → developer subscribes → marketplace flywheel turns.
Built for the two-sided market:
MIT © 2026 Fidele Maniraruta
Built in public. Real numbers posted on X @lmaniraruta.