Skip to main content
Glama

N2yo

by io.github.pipeworx-io

Polymarket Arbitrage

polymarket_arbitrage
Read-onlyIdempotent

Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a trending_scan of the top ~200 markets by weekly volume; pass event for the strongest per-event partition_check, or topic for a themed cross-event scan. event (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). topic (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FILL CHECK: when the partition signal fires, arbitrage.fill_check prices it against live CLOB depth (theoretical_edge_pp_at_book vs realizable_edge_pp at 1000 shares/leg, thin_legs[]) — realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it. For custom sizing use polymarket_fill_risk.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
eventNoSingle-event mode (use this if you know the specific Polymarket event): event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k". Full Polymarket URLs also accepted.
topicNoCross-event mode (use this if you want to scan related events across the platform): a topic or seed question like "Fed rate decision" or "Strait of Hormuz traffic returns to normal". Tool searches Polymarket for related events and checks monotonicity across them.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • removedInput schema / anyOf
      Removed value: -[
-  {
-    "required": [
-      "event"
-    ]
-  },
-  {
-    "required": [
-      "topic"
-    ]
-  }
-]
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes far beyond the annotations (readOnly, openWorld, idempotent, non-destructive) by detailing internal logic: semantic anchor Jaccard threshold (≥0.30), partition placeholder filter (>20% returns null), fill-check behavior (realizable_edge_pp ≤ 0 means do not trade), and the response structure. It even explains skipped_low_similarity and thin_legs, providing a comprehensive behavioral profile. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and long, but every section (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) adds unique, necessary information. It is front-loaded with a clear summary and mode breakdown. However, it could be tightened slightly (e.g., repeating 'event' and 'topic' definitions) without losing value, so it earns a 4 rather than a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description fully explains the response structure (opportunities[], partition_check fields, fill-check results). It covers edge cases (null signal, skipped_low_similarity, placeholders), behavioral thresholds, and cross-mode details. For a complex tool with multiple modes and checks, this is a complete and self-sufficient description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds substantial meaning beyond the schema: event accepts slugs or full URLs, topic expects seed questions, and the description explains exactly how each parameter affects mode behavior. It also clarifies that no arguments triggers trending_scan. This elevates the parameter semantics well beyond the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb and resource: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly distinguishes from sibling tools like polymarket_edges by focusing on arbitrage through structural checks. The three modes (trending_scan, event, topic) are explicitly described, making the tool's purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: call with no args for a trending scan, pass event for a specific market, pass topic for cross-event scanning. It recommends 'event (recommended for a specific market)' and explains what cross-event mode catches that single-event misses. It also points to an alternative tool for custom sizing (polymarket_fill_risk), satisfying the when-to-use vs alternatives criterion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All N2yo toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation2/5

Multiple tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-duplicates (beta is currently identical), and the five Polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread) require careful reading to distinguish. Additionally, entity_profile, compare_entities, and recent_changes all handle company data, and ai_visibility_check vs scan_competitor_ai_presence are clearly paired. The detailed descriptions help, but an agent will frequently misselect among these clusters.

Naming Consistency3/5

All names are lowercase with underscores, so the style is internally consistent. However, the pattern is mixed: many use verb_noun (get_positions, list_subscriptions, resolve_entity) but several are noun-first or noun-only (entity_profile, polymarket_edges, pipeworx_trending, bet_research). There's no strong verb/noun convention across the set, making the naming pattern less predictable than it could be.

Tool Count2/5

With 34 tools, the set exceeds the 16–25 'heavy' range and sits in the 'too many' band. The server name suggests a focused satellite-tracking service, yet only 3 tools (get_positions, get_visual_passes, whats_above) serve that purpose; the other 31 cover unrelated domains like data research, prediction markets, memory, and subscriptions. Even as a general-purpose research platform, the count feels bloated and unfocused.

Completeness3/5

The tool surface is broad, covering satellite tracking, data research, prediction markets, subscriptions, and memory, and within each cluster the main operations exist (e.g., subscription lifecycle, edge analysis + fill risk). However, the scattered scope creates gaps: there's no direct raw-data fetch tool (everything goes through ask_pipeworx), no general web search, and the presence of unrelated utilities (generate_llms_txt, scan_dependency) suggests the domain boundaries are unclear. For its stated satellite purpose, the satellite tools are thin (no TLE, no catalog, no detailed orbit info).

Resources