Robin Saige we check the tools AI agents call

PredMCP

io.github.RavioleLabs/predmcp

Polymarket + Hyperliquid + macro for AI agents. 38 tools, signal backtest, SSE streaming. Free tier.

— the operator's own registry description reported

Publisher io.github.RavioleLabs · first seen 2026-08-12 · endpoint https://predmcp.com/mcp

allow
verdict
rich-slow-solo
cluster
ok_tools
answers
47
tools served

Dependency rating derived

allow — rich-slow-solo — safe to depend on

Cluster rich-slow-solo · distinctiveness 0.488 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Reach — can an agent get to it?
answersalive_tools
latency372 ms
vs populationslow
protocolcurrent
authopen
Use — can it use it?
tools47
vs populationhigh
capabilities1
harnessA
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_7f28952ecdc6ccb7c6de400e · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Tools last seen

create_api_key get_basic_macro get_carry_scanner get_cex_outflows get_conviction_score get_cross_venue_funding get_funding_curve_anomaly get_funding_outliers get_funding_rates get_hip4_vs_pm_arb get_late_game_sports get_liquidation_clusters get_macro_context get_macro_liquidity get_market_context get_market_regime get_markets get_markets_near_resolution get_movers get_news_correlation get_odds get_oi_divergence get_oi_history get_oi_near_cap get_options_iv get_orderbook get_orderbook_depth get_pm_hl_divergences get_portfolio_risk get_position_size get_price_summary get_recent_news get_recent_signals get_setup_quality get_signal_backtest get_signal_history get_signal_performance get_signals get_simple_iv get_top_funding_rates get_upcoming_catalysts get_volume_spikes get_whale_flow get_whale_label get_whale_positions get_whale_trades search_markets

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.

legibility checktools passingok
name is clear & specific47/47
has a description47/47
description is substantive47/47
parameters are typed47/47
parameters are described47/47

47 of 47 tools graded · 47 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2025-06-18
protocol version
session model
0.7.0
server version PredMCP

Capabilities: tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:59:14Zok_tools2003722025-06-18
2026-08-12T05:34:28Zok_tools2004252025-06-18

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/io.github.RavioleLabs/predmcp.svg)](https://robinsaige.com/s/io.github.RavioleLabs/predmcp)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview