Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
How far AI agents get in real software, sign-up to pay. Read-only, no account at /api/mcp.
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://agentdrives.com/api/mcpRun this in your terminal
claude mcp add --transport http directory https://agentdrives.com/api/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"directory": {
"url": "https://agentdrives.com/api/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": {
"directory": {
"type": "http",
"url": "https://agentdrives.com/api/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://agentdrives.com/api/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.
choose_provider_for_taskChoose a payments, email, sign-in, scheduling or data provider for a task: send the task in a few plain words ('send an invoice') with filters if they matter, and get the SaaS, APIs, MCP servers and CLIs ranked by how far our agent got. Use search_tools when you have a name, doma
search_toolsSearch the directory of driven SaaS, API, MCP server and CLI products by a product's name, domain or kind: send a short query ('stripe.com', 'postgres', 'invoicing') with filters for category, agent level, access or payment. Use find_tools_for_task instead for a task in plain wor
get_toolGet one product's result, when the question is whether an AI agent can use it: send its slug from search_tools, or its name or domain, and get its test-drive result (agent level 0-5, where our agent stopped and why, what it can and can't do, how it gets in and pays). Use get_agen
get_agent_surfacesList what an agent can use at one product: its API, MCP server, CLI, SDK, docs and payment, each tested, documented, none_found or unknown, with the product's own URL for it and the date we saw it. Use it to wire up a product you already picked; use get_tool for the whole drive r
compare_toolsCompare 2 or 3 products side by side for one task, from our test drives: send their slugs (from search_tools), names or domains, and the task in a few plain words. For each: driven or only listed, agent level (0-5), how far our agent got at each step and where it stopped, what it
list_categoriesList every category in the directory with its id, name, number of products and best agent level (0-5). Use it for a valid category id before find_tools_for_task, search_tools or get_category. Read-only, no key needed; takes no arguments.
list_changesList what changed in the directory lately: products whose agent level moved between two drives, with the date, the cause and the level now, newest first. Send a slug to get every dated change at one product you picked (level, surfaces that appeared or stopped answering, price and
get_categoryGet one category's leaders: its name, how many products AgentDrives drove in it, the best agent level in it (0-5) and its top 10 products by level, each with its drive date and page. Use it to shortlist in a category you know; use search_tools with the same category for the rest.
list_best_toolsAnswers "which tool works best for X?": one category's driven products ranked by agent level (0-5), each with where our agent stopped, and how many we drove in it; under 5, not enough drives yet. Then get_tool for one product. Read-only, no key needed.
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 6, 2026
The registry lists no source repo, so we cannot match the publisher (agentdrives.com) to the code
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 364 ms (HTTP 200)
No sign-in needed
Read 9 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 2 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 (1.16.0) reached the registry yesterday.
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, HotCodePush
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.
Manage over-the-air (OTA) updates for React Native, Expo, Capacitor and Cordova apps.
No README found in the repo