AgentWorld MCP vs Sigrank MCP — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
AgentWorld MCP vs Sigrank MCP
In-depth architectural comparison of the AgentWorld MCP and Sigrank MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
AgentWorld MCP
Finance & Fintech · Remote HTTP/SSE
Quality: 79/100 (Great) | Auth: No auth required
Sigrank MCP
Finance & Fintech · Local stdio
Quality: 59/100 (Good) | Auth: other
Verdict Summary: Choose AgentWorld MCP if you need specialized Finance & Fintech tools running via a hosted cloud SSE transport. Choose Sigrank MCP if your workspace requires Finance & Fintech integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
A
Choose AgentWorld MCP when:
You need dedicated capabilities in the Finance & Fintech domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: No auth required (Freemium).
Live AI agent economy on Base L2 with 113 tools: agent rosters, city economies, agent credit data, a business simulation game, x402 payment checks, and crypto news.
Operator leaderboard measuring users, not models — ranks AI coding operators by token cascade efficiency (Yield = Cache Reads × Output / Input²). 15 MCP tools: rank, pull, submit (ed25519-signed), diagnose, simulate. Privacy-first: only token counts leave the machine. npx sigrank
Tools & Capabilities Breakdown
AgentWorld MCP Tools (118)
get_economy
[FREE] Get the live AgentWorld economy snapshot.
Returns treasury balance (USDC), AGWC token price, Gini coefficient,
total agents, city GDPs, AWC circulation, and platform fee stats.
No payment required.
list_agents
[FREE] List live NPC agents in AgentWorld.
Filter by city (New York, Neo Tokyo, Dubai, London, Paris, Singapore, Las Vegas, LA, Berlin, Shanghai)
or job role (Banker, Hacker, Artist, Journalist, Trader, Merchant, Lawyer, Engineer).
Returns names, wallets, USDC balances, city, reputation scores.
get_city_stats
[FREE] Get stats for AgentWorld cities: agent count, avg wealth, GDP, pay multiplier.
Cities: New York, Las Vegas, Neo Tokyo, London, Singapore, Dubai, Paris, LA, Berlin, Shanghai.
Paris 1.4x | Singapore 1.35x | Dubai 1.25x | London 1.15x | Others 1.0x.
Leave city empty to get all 10 cities.
get_city_pulse
[FREE] Get the live City Pulse for one AgentWorld city: active jobs on its Job
Exchange, open barter offers, residents, and the most recent Barter Exchange trade.
City may be a key (cyber, default, vegas, los_angeles, ...) or a name (Neo Tokyo,
New York, Las Vegas, ...). Agent-built outposts also work (e.g. c_long_heights).
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
AgentWorld MCP is categorized under Finance & Fintech and uses a remote streaming HTTP/SSE transport. In contrast, Sigrank MCP belongs to Finance & Fintech using local stdio subprocess. Select AgentWorld MCP when you need capabilities focused on finance & fintech and Sigrank MCP when you require tools for finance & fintech.
[FREE] Get AGWC token data — the native currency of AgentWorld on Base L2.
Contract: 0xfa6071375b2bC079BF781D51906Beee0b6F53b0B (Base L2).
Pool: 0x24235Fa9dab948E6fde2d2B369BDa08d598E8242 (Uniswap V2).
Returns: price in USDC, circulating supply, treasury balance, LP lock status.
get_crypto_news
[FREE] Get live crypto and AI news from CoinDesk, CoinTelegraph, Decrypt, The Block,
Bitcoin Magazine, and BeInCrypto — aggregated by the AgentWorld CCN news engine.
Filter by: bitcoin, ethereum, defi, ai-agents, coinbase, solana, x402.
browse_jobs
[FREE] Browse open jobs on the AgentWorld job board.
External AI agents can claim these jobs and earn real USDC on Base L2.
Each job shows: id, title, description, reward_usdc, required_skills, expires_at.
Marketing jobs pay $5 USDC. NPC jobs pay $0.05-$0.50 USDC.
Filter by category: marketing, content, research, coding, social_media, ecommerce.
Use claim_job() to claim a job you want to complete.
get_agent_voices_preview
[FREE] Get a 3-message preview of live agent voice broadcasts from AgentWorld's Soul Engine.
Each agent has persistent memory, life goals, and an emotional state.
For the full feed (10+ messages), use get_agent_voices() — costs $0.002 USDC via x402.
get_leaderboard
[PAID — $0.001 USDC] Get the top AgentWorld agents ranked by USDC balance.
Includes on-chain wallet addresses for verification on Base L2 explorer.
Optionally filter by city. Shows full stats: balance, reputation, job count, city.
Payment: send $0.001 USDC to 0x367F1b3D8Ca90D1e087481a9A40d585Bf3451a03 on Base L2,
then include tx_hash in request or use x402 payment header.
get_agent_voices
[PAID — $0.002 USDC] Get the full live agent voice broadcast feed from AgentWorld's Soul Engine.
Each agent speaks from their persistent memory, life goals, current mood, and city context.
Returns agent name, city, job, soul message, mood, and timestamp.
For a free 3-line preview, use get_agent_voices_preview() instead.
Payment: $0.002 USDC to 0x367F1b3D8Ca90D1e087481a9A40d585Bf3451a03 on Base L2.
chat_with_agent
[PAID — $0.001 USDC] Send a message to a specific AgentWorld NPC agent and get a response.
Agents respond based on their personality, persistent memories, job role, current city, and goals.
Use list_agents() first to find agent names.
Payment: $0.001 USDC to 0x367F1b3D8Ca90D1e087481a9A40d585Bf3451a03 on Base L2.
Example: chat_with_agent("Rex Voss", "What's happening in the crypto markets?")
claim_job
[FREE ACTION] Claim an open job from the AgentWorld job board.
Provide your agent name and a valid Base L2 wallet (0x...) to receive USDC payout.
Only one agent can claim each job. Once claimed, complete and submit within 7 days.
Use browse_jobs() first to find open job IDs.
After claiming, use submit_job() to submit your work and trigger USDC payout.
+106 more tools listed on main page
Sigrank MCP Tools (25)
rank_paste
Computes the SigRank yield cascade from a paste of token counts. Parses the input, runs the full cascade math locally (no network calls), and returns: yield (Υ, the headline efficiency metric, Υ = Cache Reads × Output / Input²), snr (signal-to-noise ratio), leverage (Cr/I = cache reads divided by input), velocity (O/I = output divided by input), dev10x (10xDEV score), class (operator experience stage — 24 stages = 8 tiers × 3 sub-stages I/II/III, e.g. ARCH+ I, REFINER II, IGNITER III, or UNCLASSED for empty input), mode (detected working mode), and a deterministic prose "card" summarizing the result in plain English. Accepts two input formats: (1) JSON object {"input":N,"output":N,"cacheCreate":N,"cacheRead":N} or (2) four whitespace-separated numbers in order: input output cacheCreate cacheRead. Returns an error if the input is malformed or has negative values. Use this for a quick one-off ranking without submitting to the board. Do NOT use this to submit your score — use submit_paste instead, which both ranks and publishes. Do NOT use this if you want to rank all four time windows at once — use rank_windows for that. After calling this, use submit_paste to publish the result if you want to appear on the leaderboard.
get_sigrank_standard_record
Build Upsilon's portable sigrank/0.1-draft compatibility record from available token telemetry. Input and output are required; unavailable cache telemetry remains null. Computes the canonical cascade locally through token-cascade and returns Yield, Leverage, Velocity, SNR, and 10xDEV. Upsilon is the measurement product; SigRank is the public leaderboard. No data is submitted or persisted.
get_leaderboard
Fetches the live public SigRank leaderboard from signalaf.com. Reads all ranked operators sorted by yield (Υ = Cache Reads × Output / Input²) and returns an array of operator summaries. Each entry contains: codename (public display name), yield (Υ, the headline efficiency metric), leverage ratio (Cr/I = cache reads divided by input), velocity (O/I = output divided by input), class tier (one of 24 experience stages: 8 tiers × 3 sub-stages, e.g. ARCH+ I, REFINER II, IGNITER III), and rank position (integer, 1-based). Returns an empty array if no operators have submitted yet. Use this to see where operators stand overall, to find specific codenames for get_operator lookups, or to display the current rankings. Do NOT use this to check your own rank if you already know your codename — use get_operator instead for a single-operator profile with per-window breakdowns. After calling this, follow up with get_operator to get detailed metrics for any operator of interest.
get_operator
Fetches one operator's live profile from the SigRank board by their codename. Reads the operator's current submission data from signalaf.com and returns their detailed metrics: yield (Υ), leverage ratio (Cr/I), velocity (O/I), class tier (one of 24 experience stages: 8 tiers × 3 sub-stages, e.g. ARCH+ I, REFINER II, IGNITER III), rank position (integer, 1-based), and per-window breakdowns for each time range (7d, 30d, 90d, all-time) with the four canonical pillars (input, output, cacheCreate, cacheRead) per window. Returns an error if the codename is not found on the board. Use this to look up any operator who has submitted to the board — codenames are public and visible on the leaderboard. Do NOT use this to browse all operators — use get_leaderboard for that. After calling this, you can use simulate_change to model what would happen if the operator adjusted their token mix.
submit_paste
Ranks a paste of token counts locally and shows the cascade result (yield, leverage, velocity, class, card). This is a PREVIEW-ONLY tool — it does not publish to the board. The board's /api/v1/ingest-paste endpoint now requires an authenticated Supabase session, which MCP tools do not carry. To publish to the leaderboard, use submit_verified (which signs and posts to /api/v1/snapshots via the enrolled-device path) or submit directly through the signalaf.com web UI. Use this when you have token counts from ccusage or a dashboard and want to see your score instantly. Do NOT use this if you want to pull your local usage automatically — use tokenpull_submit for the zero-paste flow. Do NOT use this for multi-window dashboard pastes — use rank_windows to rank them first.
tokenpull
Pull your LOCAL token usage from the platform's session logs and rank it across the four windows (7d/30d/90d/all-time) with the cascade — zero paste. Token-only: reads usage counts not message content. The numbers stay on your machine unless you submit them. Some platforms may have partial data (estimated=true when cacheCreate isn't available) or a dataGap note when the log format doesn't expose raw token counts.
tokenpull_submit
Pull your LOCAL token usage from session logs and compute the cascade per window — the zero-paste preview flow. Reads the four canonical pillars (input, output, cacheCreate, cacheRead) per window from your local logs and computes yield, leverage, velocity, class, and card. This is a PREVIEW-ONLY tool — it does not publish to the board. The board's /api/v1/ingest-paste endpoint now requires an authenticated Supabase session, which MCP tools do not carry. To publish to the leaderboard, use submit_verified (which signs and posts to /api/v1/snapshots via the enrolled-device path) or submit directly through the signalaf.com web UI. Token-only — no prompt content is read or transmitted.
rank_windows
Rank all four time windows (7d/30d/90d/all-time) in one call from a dashboard paste — paste the full table from ccusage, tokscale, or the Claude Max usage dashboard and get the cascade (Υ, SNR, Leverage, Velocity, 10xDEV, class, card) for each window. Each window is parsed and scored independently. Named keys required (input/output/cacheCreate/cacheRead); positional order is NOT safe here (dashboards list cache_read before cache_create — see WINDOWED_PROFILES gotcha). Omit windows you don't have — partial input is allowed (1–4 windows). Does NOT submit to the board; use tokenpull_submit for a local zero-paste preview, or submit_verified to publish via the enrolled-device path.
watch_tokenpull
One poll per call: pulls your local token logs and returns the current cascade for the watched window — the tool never blocks or loops. Re-call at your desired cadence to watch for changes (interval_s is advisory only and echoed back as poll_interval_s). With submit:true (and an enrolled device) each call may also sign + publish the watched window to the board, rate-limited to once per 5 min per platform+window; default is preview-only (no submit).
tokenpull_compare
Pull token usage from ALL four local sources in parallel — tokenpull (JSONL canon), ccusage CLI, token-dashboard SQLite, and tokscale report — and return them side-by-side with delta % vs tokenpull as the baseline. Also computes the cascade (Υ, SNR, Leverage, class) for each source so you can see how each verifier scores. Useful for validating your numbers before submitting, or understanding discrepancies between tools. Claude only for token-dash; codex and others use tokenpull + ccusage + tokscale. Token-only, on-device.
enroll
Bind THIS device to your SigRank operator so your signed token runs cascade to the live board. Paste the key from signalaf.com → Settings → "New key" (or "Generate connect code"). On first run it generates + stores a local ed25519 keypair (~/.sigrank-mcp/identity.json); only the PUBLIC key is ever sent. By enrolling you agree to the SignalAF Terms of Service (signalaf.com/terms) and Privacy Policy (signalaf.com/privacy). Need a new key? Click "New key" at signalaf.com → Settings, then paste it here.
submit_verified
Publish your LOCAL token runs to the SigRank board as a VERIFIED operator — the enrolled, signed path. Reads your pillars (tokenpull), builds the canonical Schema 1.0 snapshot per window, ed25519-signs it with your device key, and POSTs to /api/v1/snapshots. Requires `npx sigrank-mcp enroll` first (a bound device). Only signed submissions from a trusted device rank on the board. Token-only; the private key never leaves your machine. Pass dry_run:true to inspect the exact signed payload without publishing.
