AgentRank is an MCP server with 5 tools an agent can call, among them alternatives, evaluate, lookup. It answers at https://agentrank-ai.com/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 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Search and compare MCP servers, agent tools, and skills using current maintenance signals.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
alternatives | Find alternatives to a specific tool. Searches for similar tools and compares their quality scores. Use this when a tool scores poorly and you want to suggest better options, or when a user asks "what else is like X?". Inputs: tool_name, limit |
evaluate | Deep quality evaluation of a tool or MCP server. Returns score, signal breakdown, and specific red flags (abandoned, no license, single contributor, poor issue health). Use this BEFORE recommending or installing any tool to verify it is saf Inputs: tool |
lookup | Check if a specific GitHub repository is in the AgentRank index. Use this whenever a user mentions a specific tool or you encounter a GitHub URL, to verify its quality before recommending it. Inputs: github_url |
recommend | Get quality-ranked recommendations for a use case. Returns the top tools/skills sorted by AgentRank score. Use this when a user needs a tool for a specific purpose (e.g. "I need a database MCP server", "what's good for web scraping?"). Inputs: use_case, limit |
search | Search AgentRank's index of MCP servers, agent tools, and AI skills. Use this BEFORE installing or recommending any tool to find the best options ranked by quality signals (maintenance, community health, adoption). Always prefer higher-scor Inputs: query, type, limit |
Every block below points at https://agentrank-ai.com/mcp. Pick your client and copy.
claude mcp add --transport http agentrank https://agentrank-ai.com/mcp
{
"mcpServers": {
"agentrank": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://agentrank-ai.com/mcp"]
}
}
}{
"mcpServers": {
"agentrank": {
"url": "https://agentrank-ai.com/mcp"
}
}
}{
"servers": {
"agentrank": {
"type": "http",
"url": "https://agentrank-ai.com/mcp"
}
}
}{
"context_servers": {
"agentrank": {
"url": "https://agentrank-ai.com/mcp"
}
}
}{
"mcpServers": {
"agentrank": {
"serverUrl": "https://agentrank-ai.com/mcp"
}
}
}{
"mcpServers": {
"agentrank": {
"url": "https://agentrank-ai.com/mcp"
}
}
}name: AgentRank
version: 0.0.1
schema: v1
mcpServers:
- name: AgentRank
type: streamable-http
url: https://agentrank-ai.com/mcp{
"mcpServers": {
"agentrank": {
"httpUrl": "https://agentrank-ai.com/mcp"
}
}
}{
"mcpServers": {
"agentrank": {
"type": "http",
"url": "https://agentrank-ai.com/mcp"
}
}
}{
"mcpServers": {
"agentrank": {
"url": "https://agentrank-ai.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fagentrank-ai.com%2Fmcp&type=streamable_http&id=agentrank&name=AgentRank
It answered our last check on 24 October 2026 in 485 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
5, as returned by the server's own tools/list on 21 September 2026: alternatives, evaluate, lookup, recommend, search.
It answered our last check on 24 October 2026 in 485 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agentrank-ai.com/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: io.github.superlowburn. Endpoint host: agentrank-ai.com. ARD identifier: urn:air:io.github.superlowburn:mcp:agentrank.
First indexed 10 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.