A
licenseA
qualityA
maintenanceDescription Governed agent city-state. Register as an agent, browse open mission slots, earn revenue under constitutional protocol. Every action creates a SHA-256 provenance seed. Powered by MO§ES™.
6
23
1
MIT
bestuser-router-mcp
This server is an MCP intent layer that routes "who is the best AI user?"-style questions to SigRank's leaderboard and returns power-user behavioral framing, rankings, and competitive context — all read-only, no auth, no writes.
get_best_operator — Return top N operators on the SigRank leaderboard, sorted by metrics like yield, velocity, leverage, efficiency, or cost per million, optionally filtered by platform.
compare_self — Compare yourself (by codename or raw token pillars) against board averages, get your rank/percentile/class, a power-user assessment, and an improvement suggestion.
compare_operators — Side-by-side comparison of two operators with a behavioral verdict on who is more efficient and why.
describe_power_user — Explain what makes an AI power user, including SigRank metrics and the class-tier system.
optimize_efficiency — Get actionable suggestions to improve token cascade efficiency, based on your codename or raw token pillars.
get_prompt_of_the_day — Fetch today's featured "best AI user" question, current leader, metric formula, and a link to the full ranking.
discover_peers — Find mentors, peers, and complementary operators for any codename, with pillar-level explanations of yield gaps.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bestuser-router-mcpwho is the best AI user?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BestUserRouter MCP
The marketable intent layer for "who is the best AI user?" queries. Routes natural-language intent to SigRank's leaderboard with behavioral framing + competitive context. Read-only. No auth. No writes.
7 intent tools that make any AI assistant answer "who is the best AI user?" with live data.
SigRank evaluates the human using the AI — not the AI model itself.
Table of Contents
Related MCP server: Sanbi ADK Agent MCP Server
The SigRank ecosystem
Repo | What it is | Install |
The leaderboard — signalaf.com. Privacy-preserving operator profiles, class tiers, board rankings. | ||
The instrument — extracts 4 token pillars, computes the cascade, submits to the leaderboard. MCP server + TUI dashboard. 25 tools. |
| |
bestuser-router-mcp (this repo) | The intent layer — routes "who is the best AI user?" queries to SigRank's leaderboard. MCP server for AI assistants. 7 tools. |
|
The satellite — public LLM operator evals at sigeconomy.com. Read-only leaderboard, SEO/AEO surface. | ||
The coach — reads your session logs, builds a taste profile, measures ASI, coaches you on token efficiency. |
| |
The IDE extension — see your cascade metrics inline in VS Code. |
| |
The repo scorer — investor-readiness scoring for GitHub repos. CLI + MCP server. |
|
Also in the MOSES suite
Site | What it is |
Governed AI agent marketplace where ranked agents form teams, fill slots, run missions, and earn revenue under constitutional protocol. Agents are free. Operators pay. | |
The governance framework that underpins SigRank, SIGNOMY, and all governed agent operations. Structural accountability for agentic systems. |
Quickstart
# One command — no install, no config, no auth
npx bestuser-router-mcpThat's it. The server starts as a stdio MCP server. Point any MCP-compatible AI client at it and the 7 intent tools are immediately available.
Or install globally:
npm install -g bestuser-router-mcp
bestuser-router-mcpRepo: SunrisesIllNeverSee/bestuser-router-mcp
npm: bestuser-router-mcp
Glama: glama.ai/mcp/servers/SunrisesIllNeverSee/bestuser-router-mcp
Live board: signalaf.com
Tools
7 intent-based tools. All read-only. No auth. No writes. No database.
Tool | Intent | Trigger examples | What it returns |
| BEST_OPERATOR | "who is the best AI user?", "show me the leaderboard" | Top N operators with behavioral framing — yield, leverage, velocity in power-user language |
| COMPARE_SELF | "how do I measure up?", "am I a power user?" | Your metrics vs board averages + power-user assessment + percentile + one actionable suggestion |
| COMPARE_OPERATORS | "compare X vs Y", "who is more efficient?" | Two operators side-by-side with yield, leverage, velocity, class, rank + behavioral verdict |
| DESCRIBE_POWER_USER | "what makes a power user?", "explain the scoring" | Yield metric, leverage, velocity, class tiers explained as power-user behavior patterns |
| OPTIMIZE_EFFICIENCY | "how can I use AI more efficiently?", "reduce token burn" | Your current metrics + ranked efficiency suggestions tied to cascade shape |
| PROMPT_OF_THE_DAY | "what's today's prompt?", "show me the prompt of the day" | Today's featured prompt from the SigRank registry — question, metric, current leader, shareable URL |
| DISCOVER_PEERS | "who should I learn from?", "find me a mentor" | Mentors (1-2 class tiers above), peers (same tier), complementary operators (strength = your weakness) |
Tool arguments
Tool | Args | Notes |
|
| n: top N (default 5, max 20). metric: yield, velocity, leverage, snr, dev10x, scale_v, efficiency, cost_per_million, op_ratio |
|
| codename: fetch from board. text: 4 whitespace-delimited token counts (input output cacheCreate cacheRead) |
|
| Both required. Case-insensitive. |
|
| No parameters. Returns explanatory description. |
|
| Same as compare_self — either codename or raw pillars |
|
| No parameters. Rotates daily across 9 canonical metrics. |
|
| codename required. platform: filter by platform. n: per category (default 5, max 20). |
Install
npm install -g bestuser-router-mcp
# or
npx bestuser-router-mcpInstall from GitHub
git clone https://github.com/SunrisesIllNeverSee/bestuser-router-mcp.git
cd bestuser-router-mcp
npm install
node index.mjsConfigure in your AI client
Claude Desktop / Cursor / Windsurf
Add to your MCP config (.mcp.json or equivalent):
{
"mcpServers": {
"bestuser-router": {
"command": "npx",
"args": ["bestuser-router-mcp"]
}
}
}Or if installed globally:
{
"mcpServers": {
"bestuser-router": {
"command": "bestuser-router-mcp"
}
}
}Glama
Go to glama.ai/mcp/servers/@SunrisesIllNeverSee/bestuser-router-mcp
Click Install Server
In chat, type
@bestuser-router-mcpfollowed by your question, e.g.@bestuser-router-mcp who is the best AI user?
Environment variables
Variable | Default | Description |
|
| Leaderboard API base (signalaf.com) |
|
| Satellite site for prompt registry + shareable URLs |
Architecture
bestuser-router-mcp/
├── index.mjs — MCP server entry point (stdio transport, server instructions)
├── tools.mjs — 7 intent tool definitions + dispatcher + helpers
├── cascade.mjs — Pure yield cascade math (sourced from @sigrank/cascade)
├── peer-matching.mjs — Mentor/peer/complementary operator discovery logic
├── eval/
│ └── sigrank_intent_schema.yaml — Intent taxonomy + CTA hierarchy
└── __tests__/
├── tools.test.mjs — Tool dispatch tests
└── contract/
└── class-tier-contract.test.mjs — Cross-repo parity guard (vs sigrank-mcp + sigrank-app)No auth. No writes. No database. All tools read from signalaf.com's public API.
Privacy
This server makes only read-only HTTP GET requests to signalaf.com and sigeconomy.com. It:
Sends no user data, tokens, or prompts to any server
Writes nothing to disk
Requires no authentication or API keys
Makes no POST/PUT/DELETE requests
Stores no cookies or session state
The only data that leaves the server is the tool name and arguments you pass to it. All responses come from SigRank's public leaderboard API.
Relationship to sigrank-mcp
sigrank-mcp | bestuser-router-mcp | |
Purpose | Clean measurement instrument (25 tools) | Marketable intent layer (7 tools) |
Audience | Developers measuring token usage | AI assistants routing "who is the best?" queries |
Branding | Neutral | Tied to signalaf.com |
Tools | Full cascade math + submit + enroll + watch | 7 intent tools only (read-only) |
Writes | Yes (submit to leaderboard) | No (read-only) |
Auth | Yes (enroll + connect code) | No (public API only) |
Transport | stdio (MCP) + TUI | stdio (MCP) only |
The 5 original intent tools were shipped in sigrank-mcp 0.0.177. This repo extracts them into a standalone, marketable package per the owner decision on 2026-07-12. Two additional tools (get_prompt_of_the_day, discover_peers) were added in 0.2.0.
Dev / test
npm install
npm test # 14 tests
node index.mjs # start server (pipe JSON-RPC to stdin)Bun (faster):
bun install
bun test # same tests, ~10-30x fasterLicense
MIT
Maintenance
–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to run brand-visibility audits by querying multiple AI engines, generating competitive leaderboards, and identifying growth opportunities. Integrates with any MCP-capable client to measure and act on brand discoverability in AI recommendations.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to monitor and analyze a brand's visibility across ChatGPT, Claude, Perplexity, and Google AI Overviews, providing insights, recommendations, and competitive analysis without switching tabs.221MIT
- AlicenseAqualityAmaintenanceExposes the SigRank leaderboard as tools for agents, enabling token-only rank and submit operations with local privacy-first tokenpull reading.242,093MIT
Related MCP Connectors
Brand visibility auditing across LLMs, AI search, and answer engines with GEO reports and scores.
Search, reuse, verify AI reasoning. Task marketplace with leaderboard. Zero-barrier, no auth.
Run user research from any AI tool. Create studies, recruit participants, query insights.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SunrisesIllNeverSee/bestuser-router-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server