Skip to main content
Glama

Mapbox

by io.github.pipeworx-io

Polymarket Edges

polymarket_edges
Read-onlyIdempotent

Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets. FIVE MODEL FAMILIES grouped into three response segments under by_segment: (1) MODEL_DRIVEN — crypto_price (lognormal barrier from 90d FRED log-returns) and news_momentum (GDELT 7d/21d article-volume ratio, soft signal w/ halved Kelly). (2) STRUCTURAL_ARBITRAGE — partition_overround on mutually-exclusive events; per-leg favorite-longshot bias correction with per-sport α (tennis 1.02, soccer 1.10, MMA 1.15, default 1.0); placeholder-slug filter drops will-person-X / will-team-Y / will-manager-Z / will-someone-else- backstops; partitions with >20% placeholder fraction skipped entirely. (3) CONCENTRATED_LONGSHOT — basket trade when one leg ≥75% AND ≥2 longshots ≤8% AND portfolio return ≥25:1; rare-by-design (gates relaxed Run 8 from prior 85%/5%/50:1). EVERY OPPORTUNITY carries edge_pp_net (after slippage), kelly_fraction + kelly_fraction_half (capped at 0.25), market.liquidity, market.spread_pp, market.volume, plus a 24h-move warning ("Market moved X.Xpp in 24h") when the recent move alone exceeds the edge — your edge may already be in the price. TRADEABLE-EDGE KNOBS: min_liquidity / max_spread_pp drop opportunities where edge isn't realizable; min_partition_leg_kelly filters partitions by best per-leg Kelly. RESPONSE TOP-LEVEL: by_segment{model_driven,structural_arbitrage,concentrated_longshot}, fed_candidates/fed_note (Fed bets surface here, excluded from ranking — 1m-T vs EFFR signal is unreliable at meeting-month horizons without paid OIS/SOFR-futures data), and _diagnostics{concentrated_longshot:{...funnel counters},category_counts,filter_skips} so callers can see WHY a segment is empty (top-N stale, all candidates failed gates, knob dropped them). Cached 1h at the KV level keyed on all knobs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoTop N edges to return after ranking. Default 10, max 25.
windowNoPolymarket volume window to filter markets. Default 1wk.
min_kellyNoMinimum half-Kelly fraction (as decimal, e.g. 0.005 = 0.5% of bankroll) to include single-leg opportunities. Default 0 (no filter). Skips opportunities that are too small to bet sensibly even if the edge is large.
min_edge_ppNoMinimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage.
slippage_ppNoAssumed execution slippage in percentage points per leg (default 0.3). Subtracted from raw |edge| before ranking and Kelly sizing. Polymarket has zero trading fees as of 2024 but bid/ask + thin depth typically eats 20-50bp per trade. Bump for very thin partitions; drop to 0 if you have a smarter fill model.
max_spread_ppNoTradeable-edge filter. Maximum bid/ask spread in percentage points on the representative market. Default null (no filter). Set to 2 to require tight books — anything wider eats most plausible edges.
min_liquidityNoTradeable-edge filter. Minimum $ liquidity on the representative market (or for partition_overround, on at least one top_leg). Default 0 (no filter). Set to 5000 to drop thin-book opportunities where executing the edge would walk the book past breakeven.
category_filterNoComma-separated list to restrict the output: "model_driven" (crypto_price + news_momentum), "structural_arbitrage" (partition_overround), "concentrated_longshot". Combine like "model_driven,structural_arbitrage". Default: all.
min_partition_leg_kellyNoMinimum BEST per-leg half-Kelly fraction across a partition_overround opportunity's top_legs (or longshot_basket legs). Default 0 (no filter). Partition arbs always return kelly_fraction_half=0 at the parent level by design (basket trades don't compose to single-leg Kelly), so min_kelly never filters them — this knob applies to the per-leg Kelly inside top_legs instead. Use to suppress thin partitions whose individual leg edges aren't worth the per-leg slippage cost.

Schema Changelog

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

  1. Changed2 schema fields changed
    • addedInput schema / properties / max_spread_pp
      {
  "description": "Tradeable-edge filter. Maximum bid/ask spread in percentage points on the representative market. Default null (no filter). Set to 2 to require tight books — anything wider eats most plausible edges.",
  "type": "number"
}
    • addedInput schema / properties / min_liquidity
      {
  "description": "Tradeable-edge filter. Minimum $ liquidity on the representative market (or for partition_overround, on at least one top_leg). Default 0 (no filter). Set to 5000 to drop thin-book opportunities where executing the edge would walk the book past breakeven.",
  "type": "number"
}
  2. Changed1 schema field changed
    • addedInput schema / properties / min_partition_leg_kelly
      {
  "description": "Minimum BEST per-leg half-Kelly fraction across a partition_overround opportunity's top_legs (or longshot_basket legs). Default 0 (no filter). Partition arbs always return kelly_fraction_half=0 at the parent level by design (basket trades don't compose to single-leg Kelly), so min_kelly never filters them — this knob applies to the per-leg Kelly inside top_legs instead. Use to suppress thin partitions whose individual leg edges aren't worth the per-leg slippage cost.",
  "type": "number"
}
  3. Changed4 schema fields changed
    • addedInput schema / properties / category_filter
      {
  "description": "Comma-separated list to restrict the output: \"model_driven\" (crypto_price + news_momentum), \"structural_arbitrage\" (partition_overround), \"concentrated_longshot\". Combine like \"model_driven,structural_arbitrage\". Default: all.",
  "type": "string"
}
    • changedInput schema / properties / min_edge_pp / description
      Before
      "Minimum |edge| in percentage points to include (default 0.5)."
      After
      "Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage."
    • addedInput schema / properties / min_kelly
      {
  "description": "Minimum half-Kelly fraction (as decimal, e.g. 0.005 = 0.5% of bankroll) to include single-leg opportunities. Default 0 (no filter). Skips opportunities that are too small to bet sensibly even if the edge is large.",
  "type": "number"
}
    • addedInput schema / properties / slippage_pp
      {
  "description": "Assumed execution slippage in percentage points per leg (default 0.3). Subtracted from raw |edge| before ranking and Kelly sizing. Polymarket has zero trading fees as of 2024 but bid/ask + thin depth typically eats 20-50bp per trade. Bump for very thin partitions; drop to 0 if you have a smarter fill model.",
  "type": "number"
}
  4. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial behavioral context beyond these: it discloses caching behavior ('Cached 1h at the KV level keyed on all knobs'), response structure with diagnostics for empty segments ('_diagnostics... so callers can see WHY a segment is empty'), a 24h-move warning that flags when recent movement already exceeds the edge, and filtering rules like the placeholder-slug filter and >20% placeholder fraction skip. This far exceeds what annotations alone provide.

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 long but well-structured with clear section headers (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT, TRADEABLE-EDGE KNOBS, RESPONSE TOP-LEVEL). It front-loads the core purpose and then organizes detail hierarchically. While some specifics (e.g., per-sport α values, exact gate thresholds) could be considered excessive for an agent just selecting the tool, they are relevant for understanding output semantics. It earns its length through density, but could be trimmed without losing essential guidance.

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?

Given there is no output schema, the description compensates by thoroughly specifying the response structure: 'by_segment{model_driven,structural_arbitrage,concentrated_longshot}, fed_candidates/fed_note... and _diagnostics...'. It also details per-opportunity fields ('edge_pp_net (after slippage), kelly_fraction + kelly_fraction_half (capped at 0.25), market.liquidity, market.spread_pp, market.volume'). The description covers edge cases (empty segments, stale data, knob interactions) and performance characteristics (caching), making it complete for an agent to predict behavior without prior tool experience.

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 description coverage is 100%, so the baseline is 3, but the description adds meaningful semantics beyond field comments. It explains the practical effect of tradeable-edge knobs: 'min_liquidity / max_spread_pp drop opportunities where edge isn't realizable'. It also clarifies a non-obvious interaction: 'Partition arbs always return kelly_fraction_half=0 at the parent level by design... so min_kelly never filters them — this knob applies to the per-leg Kelly inside top_legs instead.' This goes beyond the schema and helps the agent select and set parameters correctly.

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 opens with a specific verb and resource: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It clearly distinguishes the tool from siblings like polymarket_arbitrage by framing it as a broad opportunity scanner for 'what should I bet on today' rather than a pure arbitrage tool. The segmentation into MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, and CONCENTRATED_LONGSHOT further clarifies its multi-purpose nature.

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

Usage Guidelines4/5

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

The description explicitly states its intended use case: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' It also explains when knobs like min_liquidity and max_spread_pp should be used ('Set to 2 to require tight books'), and provides an explicit exclusion for Fed bets ('excluded from ranking — 1m-T vs EFFR signal is unreliable'). However, it does not explicitly name sibling tools as alternatives (e.g., suggesting polymarket_arbitrage for pure arbitrage), so it stops short of a full when-not/alternatives guide.

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

All Mapbox 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

A3.6/5.0
Disambiguation2/5

Many tools have overlapping purposes (ask_pipeworx, ask_pipeworx_grounded, deep_research, validate_claim) and several tools serve similar data-retrieval functions, making it difficult for an agent to distinguish which to use.

Naming Consistency4/5

Tool names mostly follow a consistent verb_noun pattern (e.g., geocode_forward, generate_llms_txt, resolve_entity). A few less descriptive names (forget, recall) exist but overall naming is predictable.

Tool Count2/5

38 tools is far too many for a server branded as 'Mapbox'. Only about 8 tools directly relate to map/geospatial functionality; the rest are unrelated (Pipeworx data, Polymarket, memory). The scope is dramatically overextended.

Completeness2/5

The Mapbox-specific tools lack coverage of major features like style management, tilesets, or data upload. The non-Mapbox tools cover their domains moderately, but the server's overall completeness for its named purpose (Mapbox) is severely lacking.

Resources