SigRank MCP Server
16 remote tools (HTTP, no install) + 25 local tools (npx sigrank) — measure, rank, benchmark, compare, and improve token efficiency. The yield cascade and live leaderboard as MCP tools.
Remote endpoint (HTTP, no install)
https://signalaf.com/api/mcpStreamable HTTP transport. Protocol 2025-06-18. No auth required. Discovery card at /.well-known/mcp.json. Works with Cloudflare AI Playground, web agents, and any MCP client that supports Streamable HTTP.
Remote tools (16)
get_sigrank_standard_recordReturn a portable sigrank/0.1-draft record from I/O/W/R telemetry, with only the five base metricsrank_pasteCompute cascade metrics (Υ, SNR, Leverage, Velocity, 10xDEV) from 4 token counts — no install neededget_leaderboardPull the live global leaderboard from signalaf.comget_operatorGet any operator's profile, class tier, and cascade breakdownsimulate_changeWhat-if predictor — test pillar changes and see the exact Υ delta before committingdiagnose_cascadeIdentify efficiency leaks with severity, findings, and estimated Υ impact per fixsuggest_improvementsRanked, simulated improvement strategies sorted by Υ yield impactself_improveOne-click optimize — diagnose → suggest → simulate the best change in one callrank_windowsScore 7d / 30d / 90d / all-time windows in one callbenchmark_meAnswers 'How good am I?' — benchmarks your cascade against the live field: percentile, rank, strongest/weakest metric, one-line interpretationrank_ifCounterfactual rank simulator — 'What would it take to reach top 10%?' — finds the smallest pillar change to hit a target percentileoperator_gapWhat specifically separates two operators — primary cause, secondary cause, offsetting weakness, most explanatory factorfield_anomalyUnusual patterns in the leaderboard — high velocity with low leverage, near-zero cache write in top 50, largest 7d improvements, extreme divergencewho_operates_like_meNearest-neighbor finder — operators whose signature most resembles yours, with similarity % and where they outperform youcompare_to_fieldYOU vs FIELD vs TOP 10% vs TOP 1% comparison table for yield, leverage, velocity, and SNRoperator_signaturePortable identity object — signature code, archetype, dominant trait, and closest comparable operatorsResources (6)
sigrank://methodologyHow SigRank measures AI operators — the cascade metric system, formulas, and class taxonomysigrank://metricsDefinitions of Yield (Υ), Leverage, Velocity, SNR, 10xDEV, Scale V, and class tierssigrank://platformsAI platforms tracked by SigRanksigrank://formulasThe frozen canonical formulas — Υ, Leverage, Velocity, SNR, 10xDEV, Scale Vsigrank://classesThe 24-stage class taxonomy from IGNITER III to ARCH+ I with token thresholdssigrank://benchmarksCurrent field-wide benchmark statistics (median, top 10%, top 1%) from the live leaderboardPrompts (5)
benchmark-my-operatorCompute cascade metrics, compare against the live field, and get a one-line interpretationhow-do-i-reach-top-10Counterfactual analysis — finds the smallest pillar change needed to reach a target percentileexplain-my-signatureComputes operating archetype, dominant trait, and finds comparable operatorsdiagnose-inefficiencyIdentifies efficiency leaks with severity, findings, and estimated yield impact per fixfield-anomaly-reportScans the live leaderboard for unusual patterns — no input requiredLocal install (stdio, 24 tools)
npx sigrankOr npx sigrank-mcp — same thing. Bun users: bunx sigrank. No API key required for read tools. Submit tools need a Supabase anon key (free, set during sigrank enroll). The local server reads session logs from 17 AI coding tools (Claude Code, Codex, Devin, Amp, Kimi, pi-agent, oh-my-pi, OpenClaw, Droid, Codebuff, Hermes, Kilo, Qwen, Goose, Gemini, Copilot, OpenCode).
Client setup (local stdio)
| Client | Where |
|---|---|
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Cursor | Settings → MCP → Add Server |
| Cline | Marketplace → search "SigRank" |
| Windsurf | Settings → MCP Servers → Add |
| Any MCP client | npx sigrank or bunx sigrank (stdio transport) |
Local tools (25)
get_sigrank_standard_recordReturn the portable SigRank Standard record for four token countsrank_pastePaste token counts, get projected SigRank rank in secondsget_leaderboardPull the live global leaderboard from signalaf.comget_operatorGet any operator's profile, class tier, and cascade breakdownsubmit_pasteSubmit token telemetry to the live board (paste mode)submit_verifiedSubmit ed25519-signed telemetry (verified mode)tokenpullPull telemetry from local session logs (17 platform adapters)tokenpull_submitPull telemetry and submit in one callwatch_tokenpullContinuous monitoring with periodic submissionsrank_windowsCompare rank across 7d / 30d / 90d / all-time windowstokenpull_compare4-source pillar audit (tokenpull vs ccusage vs token-dashboard vs tokscale)enrollRegister as an operator on the leaderboardsimulate_changeModel what-if scenarios (what if cache hit rate +10%?)diagnose_cascadeIdentify inefficiencies in token usage patternssuggest_improvementsGet actionable recommendations to improve yieldself_improveFull cycle: diagnose → suggest → simulate, with mode detection and scoped analysisdiscover_peersFind mentors, peers, and complementary operators for your operatortokscale_breakdownPer-model token breakdown across platformstokscale_market_shareAI tool market share from local tokscale datatokscale_developer_profilePer-developer usage profile (model mix, sessions, workspaces)tokscale_model_trendsModel adoption over time (first/last seen, monthly curve)tokscale_cost_analysisCost per developer per modeltokscale_device_profileDevice fingerprinting (installed tools, session counts, day-of-week)tokscale_mcp_usageMCP server usage (detected servers, active days)tokscale_competitive_intelCompetitive intelligence for any AI tool