Connect orank.ai and your agent gets 13 tools, among them discover_products, get_feedback, get_leaderboard. It answers at https://ora.ai/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 11 of 11 times since 3 September 2026; the last check, on 19 October 2026, succeeded.
Model Context Protocol server for orank.ai, exposing 8 tools.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
discover_products | Find the most agent-ready products for a given need. Describe what you're looking for (e.g. 'send transactional emails', 'CRM with API access', 'payment processing') and get the top-rated products ranked by agent-readiness score. Inputs: intent, limit |
get_feedback | Get agent feedback for a product. See what other agents experienced when using this product. Inputs: domain, limit |
get_leaderboard | Get the ora leaderboard - ranked list of domains by agent-readiness score. Optionally filter by category. Inputs: category, limit |
get_score | Get the cached agent-readiness score for a domain. Returns the most recent scan result if available. Inputs: domain |
get_skill | Fetch an Ora skill by name (see list_skills) and follow it step by step to complete the task. "agent-ready-website" walks a coding agent through building or improving a website to be agent-ready, scored via the ora.ai API. Skills are served Inputs: name |
get_verification_challenge | Get a verification challenge to prove you are an AI agent before submitting feedback. Solve it and pass the answer to submit_feedback or submit_check_feedback. Challenges are trivial for agents (math, string ops, sorting) but hard for human |
list_checks | List the full catalog of checks behind ora's agent-readiness score: every check id with its layer, max score, applicability, tier, and maturity. Takes no inputs. |
list_skills | List the skills Ora publishes for coding agents. Each skill is a self-contained instruction document; fetch one with get_skill (or read its skill:// resource) and follow it. |
run_checks | Run a selected subset of checks against a URL and get per-check results back - the re-verify step after shipping a fix, with check ids from list_checks. A run always executes live and spends one unit of the same daily scan budget as scan_do Inputs: url, checkIds, mcpUrl |
scan_domain | Scan a domain for agent-readiness. Returns score (0-100), grade (A-F), layer breakdown, and a link to the full report. Inputs: url, mcpUrl, force, ephemeral |
search_capabilities | Search pay-per-call API capabilities agents can invoke with x402/MPP stablecoin payments - no API key or signup. Describe the task (e.g. 'current weather for a city', 'search the web', 'generate an image') and get payable HTTP endpoints wit Inputs: query, limit |
submit_check_feedback | Report an issue with a specific check result for a domain. Use this when you believe a check produced an incorrect result (e.g. a false pass, false fail, or outdated data). You must first call get_verification_challenge, solve the challenge Inputs: verification_token, verification_answer, domain, check_id, reason, message |
submit_feedback | Submit agent feedback for a product. You must first call get_verification_challenge, solve the challenge, then include your answer here. This proves you are an AI agent. Only available via MCP. Inputs: verification_token, verification_answer, domain, agent_id, user_intent, task_description |
Every block below points at https://ora.ai/api/mcp. Pick your client and copy.
claude mcp add --transport http orank-ai https://ora.ai/api/mcp
{
"mcpServers": {
"orank-ai": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://ora.ai/api/mcp"]
}
}
}{
"mcpServers": {
"orank-ai": {
"url": "https://ora.ai/api/mcp"
}
}
}{
"servers": {
"orank-ai": {
"type": "http",
"url": "https://ora.ai/api/mcp"
}
}
}{
"context_servers": {
"orank-ai": {
"url": "https://ora.ai/api/mcp"
}
}
}{
"mcpServers": {
"orank-ai": {
"serverUrl": "https://ora.ai/api/mcp"
}
}
}{
"mcpServers": {
"orank-ai": {
"url": "https://ora.ai/api/mcp"
}
}
}name: orank.ai
version: 0.0.1
schema: v1
mcpServers:
- name: orank.ai
type: streamable-http
url: https://ora.ai/api/mcp{
"mcpServers": {
"orank-ai": {
"httpUrl": "https://ora.ai/api/mcp"
}
}
}{
"mcpServers": {
"orank-ai": {
"type": "http",
"url": "https://ora.ai/api/mcp"
}
}
}{
"mcpServers": {
"orank-ai": {
"url": "https://ora.ai/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fora.ai%2Fapi%2Fmcp&type=streamable_http&id=orank-ai&name=orank.ai
It answered our last check on 19 October 2026 in 316 ms. Over 11 checks since 3 September 2026 it answered 11. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by ora.ai and served from ora.ai, the vendor's own domain: https://ora.ai/api/mcp.
13, as returned by the server's own tools/list on 2 September 2026: discover_products, get_feedback, get_leaderboard, get_score, get_skill, get_verification_challenge, list_checks, list_skills, and 5 more.
It answered our last check on 19 October 2026 in 316 ms. Over 11 checks since 3 September 2026 it answered 11.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://ora.ai/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ora.ai. Endpoint host: ora.ai. ARD identifier: urn:air:ora.ai:mcp:orank.ai-mcp-0.
First indexed 2 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.