Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
The output layer for AI agents: turn what an agent produced into a finished file.
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.
BIGAPI_KEYValues marked secret are keys to your account. Never share them or paste them into a chat.
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": {
"bigapi": {
"command": "npx",
"args": [
"-y",
"@bigapi/mcp"
],
"env": {
"BIGAPI_KEY": "your-value"
}
}
}
}Run this in your terminal
claude mcp add bigapi --env BIGAPI_KEY=your-value -- npx -y @bigapi/mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"bigapi": {
"command": "npx",
"args": [
"-y",
"@bigapi/mcp"
],
"env": {
"BIGAPI_KEY": "your-value"
}
}
}
}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": {
"bigapi": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@bigapi/mcp"
],
"env": {
"BIGAPI_KEY": "your-value"
}
}
}
}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 6, 2026
The registry name was verified against the domain bigapi.dev (the registry checks domain ownership)
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.
You need to fill in: BIGAPI_KEY
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 (0.8.2) reached the registry 2 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, dotnet-mcp
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.
MCP server for .NET symbols, XAML, source generators, and restricted workspace edit
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 [bigapi.dev](https://bigapi.dev) – *the output layer for AI agents.*
Your agent produced something. bigapi turns it into a finished file – and reads files back in. Merge, redact, OCR, convert, sign, validate: the operations an LLM cannot do itself, over plain HTTPS, with one key, nothing to install server-side.
$0.01 per operation. 100 free. Free operations and balance never expire. Failed calls are free. Servers in Germany, GDPR, files deleted after delivery. Every operation ships with a published proof that it does what it promises.
Also listed in the official MCP Registry as dev.bigapi/mcp.
The server starts lean: it lists five tools, so your context stays free.
| Tool | What it does |
|---|---|
find_tool | Describe your task in plain words, get the matching operation with a ready-to-run example. Free, no key. |
run_operation | Run any bigapi operation by name, including ones added after your client started. |
enable_tools | Load dedicated tools on demand, e.g. ["pdf_redact","ocr"] or ["all"]. |
get_access / get_balance | Get a free key, check credit. |
All 40+ operations are available from the first second through run_operation; the dedicated tools are a convenience, not a requirement. Want the full list right away? Set BIGAPI_TOOLS=all in the server environment.
Why: every tool definition costs context in your client, and a model choosing between five descriptions picks better than one scanning forty-six.
All 40+ operations go through run_operation (or their own tool after enable_tools). Ask find_tool in plain words instead of memorising this list:
Requires Node 18+. No API key needed up front – the agent can call get_access itself.
claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": { "bigapi": { "command": "npx", "args": ["-y", "@bigapi/mcp"] } } }
Restart Claude Desktop. Then: *"Get bigapi access and render this text as a PDF on my Desktop."*
Same block in the respective MCP settings (.cursor/mcp.json, ~/.codeium/windsurf/mcp_config.json, Cline → MCP Servers → Configure).
"bigapi": { "command": "npx", "args": ["-y", "@bigapi/mcp"], "env": { "BIGAPI_KEY": "bigapi_..." } }
Inputs are local paths (/Users/me/report.pdf, C:\Users\me\scan.pdf). Outputs are written to output_path if given, otherwise to a temp folder (BIGAPI_OUTPUT_DIR to change). Every result includes the cost, what it was charged from, and the remaining balance.
Flat $0.01 per operation – every operation, no exceptions (per page for ocr, office_to_pdf, pdf_to_markdown, pdf_extract_tables, pdf_compare and pdf_redact). Prepaid from $5 – no subscription, no signup, balance never expires, failed calls are free. Machine-readable: get_pricing or GET /v1/pricing.
| Variable | Default | Purpose |
|---|---|---|
BIGAPI_KEY | – | Use this key instead of the stored one |
BIGAPI_CONFIG_DIR | ~/.bigapi | Where get_access stores the key (config.json, mode 600) |
BIGAPI_OUTPUT_DIR | OS temp dir | Default output folder |
BIGAPI_URL | https://api.bigapi.dev | API base (for self-hosting / testing) |
Plain HTTP works everywhere (n8n, Make, Zapier, LangChain, your code):
curl -X POST https://api.bigapi.dev/v1/keys # → key
curl -o out.pdf https://api.bigapi.dev/v1/render \ -H "Authorization: Bearer $KEY" -H "content-type: application/json" \ -d '{"markdown":"# Hello from an agent"}'
OpenAPI: https://api.bigapi.dev/openapi.json · Docs: https://api.bigapi.dev/docs · Guides: https://bigapi.dev/guides/ · llms.txt: https://api.bigapi.dev/llms.txt
MIT