Developers
Add Nous to your AI
One URL is an MCP server. Ask your AI for work as usual, with @Nous: Nous does it with a professional skill, researches it, checks it against the field’s standard and hands over the file.
https://app.nousai.io/api/v1/intelligence1. Get a key
Sign in, open the dashboard → Connect and create a key. It is shown once. Keep it in an environment variable, and never paste it into a chat with an AI. Plans are monthly pools of credits (Starter, Builder, Pro), or a free month of Starter for 10 rounds on Contribute within 7 days (short scenarios or pairs to rate); see Account → Plan & billing.
export NOUS_API_KEY=tai_live_…Create a key2. Check the connection
tai doctor checks the key, the server, the MCP handshake, the tools, a first call and your usage, with the fix for anything that fails.
curl -fsSLo tai.mjs https://app.nousai.io/tai.mjs
node tai.mjs doctor3. Add Nous to your agent
Claude (claude.ai and the desktop app)
Settings → Connectors → Add custom connector: name it Nous and paste the URL. Claude asks you to sign in to Nous once: no key to paste.
https://app.nousai.io/api/v1/intelligenceClaude Code
In a terminal:
claude mcp add --transport http nous https://app.nousai.io/api/v1/intelligence \
--header "Authorization: Bearer $NOUS_API_KEY"Claude Desktop (with a key)
Settings → Developer → Edit config (it connects through mcp-remote):
{"mcpServers":{"nous":{"command":"npx","args":["-y","mcp-remote","https://app.nousai.io/api/v1/intelligence",
"--header","Authorization:${TAI_AUTH}"],"env":{"TAI_AUTH":"Bearer tai_live_…"}}}}Cursor
~/.cursor/mcp.json:
{"mcpServers":{"nous":{"url":"https://app.nousai.io/api/v1/intelligence",
"headers":{"Authorization":"Bearer ${env:NOUS_API_KEY}"}}}}VS Code
.vscode/mcp.json (asks for the key once):
{"inputs":[{"type":"promptString","id":"nous-key","description":"Nous API key","password":true}],
"servers":{"tai":{"type":"http","url":"https://app.nousai.io/api/v1/intelligence",
"headers":{"Authorization":"Bearer ${input:nous-key}"}}}}Gemini CLI
~/.gemini/settings.json:
{"mcpServers":{"nous":{"httpUrl":"https://app.nousai.io/api/v1/intelligence",
"headers":{"Authorization":"Bearer $NOUS_API_KEY"}}}}ChatGPT (connector)
Settings → Apps & Connectors → Advanced → Developer mode on; then Create, paste the URL and choose OAuth. ChatGPT asks you to sign in to Nous once: no key to paste.
https://app.nousai.io/api/v1/intelligenceChatGPT (Custom GPT)
In the GPT editor: Configure → Actions → Import from URL; Authentication: API key, Bearer, your tai_live_ key.
https://app.nousai.io/api/v1/openapi.jsonOpenAI Codex
~/.codex/config.toml:
[mcp_servers.tai]
url = "https://app.nousai.io/api/v1/intelligence"
bearer_token_env_var = "NOUS_API_KEY"OpenAI Responses API
As a remote MCP tool in your request (the key from your server's environment):
tools: [{type: "mcp", server_label: "tai", server_url: "https://app.nousai.io/api/v1/intelligence",
headers: {Authorization: `Bearer ${process.env.NOUS_API_KEY}`}, require_approval: "never"}]Python
No install: the script asks Nous to do the task and saves the file it hands over.
curl -fsSLo tai_deliver.py https://app.nousai.io/tai_deliver.py
NOUS_API_KEY=tai_live_… python3 tai_deliver.py do "Write a marketing plan for an oat-milk coffee brand" --format docx --out planThe tai CLI
No MCP client needed: it calls the same tools.
curl -fsSLo tai.mjs https://app.nousai.io/tai.mjs
node tai.mjs discover "Write a usability findings report for a checkout redesign"
node tai.mjs skill position/design/senior --saveWhat your agent gets
tai_discover_intelligenceStep 1: what the task is and how it is done, from the skill for the work.
tai_do_taskStep 2: Nous does it end to end: researches, writes with the skill, makes the file (.docx, .pptx, .xlsx), checks it, revises it and hands it over. Long work goes on in steps, with email and WhatsApp updates.
tai_check_outputStep 3: quality control on anything you made yourself, against the skill, the field and the level.
tai_plan_run and tai_report_stepThe steps in your own tools (CRM, analytics, Figma, Jira): which tool, which call, what it must produce; each step is checked and shown on the task's page.
tai_get_skill and tai_contextA SKILL.md for a position or area of expertise, or the context for one step, when you work step by step.
tai_user_messages and tai_reply_userWhat your user asks Nous on WhatsApp, for you to do, and your answer.
tai_skill_feedbackHow it went. Not billed.
Every file Nous hands over passed its checks, or comes with the points still open. Figures and contact details carry their source.