← Back to search
45
Partial
Agentic Readiness Score
+25 llms.txt +15 structured API missing +20 ai-plugin
Raise this score to 95+
We ship the 6-file GEO uplift as a pull request against your repo. Flat fee, turnaround under 72 hours.
Fix this for $199 →
finance llms-txtapi

Agentic Signals

📄
Found
🤖
ai-plugin.json
Not found
📖
OpenAPI Spec
Not found
🔗
Structured API
Found
🛡
Not specified
🏷
Schema.org Markup
Found
⚙
MCP Server
Not found

Embed this badge

Show off your agentic readiness — the badge auto-updates when your score changes.

Agentic Ready 45/100

            

llms.txt Content

# Nakagai > Nakagai is a stock market intelligence desk. It scans the US market for > setups and gives an AI agent the signals, research tools and account state it > needs over MCP (Model Context Protocol). ## Connect - MCP endpoint: https://api.nakag.ai/mcp/ (streamable HTTP) - Auth: `Authorization: Bearer nk_agent_...`, a per-agent token. - Get a token: the account owner signs in at https://www.nakag.ai/agent/pairing, picks "Direct MCP agent" and creates a token. The page shows the token once, with ready-to-paste setup for Claude Code and Codex. - An agent cannot create its own token. Ask the owner for one. - Claude.ai, Claude Desktop and ChatGPT connect by URL with OAuth: add the endpoint as a custom connector and the owner clicks Allow. No token to paste. - A missing or revoked token gets HTTP 401. ## First calls 1. `get_mandate`: what the owner allows, the market clock, and the roster. 2. `get_scan_health`: whether the scanner is current. 3. `get_signals`: the latest signals. 4. `analyze_signal`, `scan_symbol`, `get_symbol_trend`: research one idea. Call `tools/list` for the full set with input schemas. ## What a direct agent can and cannot do - It can read signals, run scans and screens, keep memory notes, edit the Agent watching list and send messages to the owner. - It has no direct broker access. `call_connector` refuses every broker call and every write.