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

Name	Required	Description
`limit`	No	Top N edges to return after ranking. Default 10, max 25.
`window`	No	Polymarket volume window to filter markets. Default 1wk.
`min_kelly`	No	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.
`min_edge_pp`	No	Minimum \|edge\| in percentage points to include (default 0.5). Edge is evaluated NET of slippage.
`slippage_pp`	No	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.
`max_spread_pp`	No	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.
`min_liquidity`	No	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.
`category_filter`	No	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.
`min_partition_leg_kelly`	No	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.

Schema Changelog

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

Changed2 schema fields changedMay 27, 2026

addedInput schema / properties / max_spread_pp

Added value: +{
+  "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

Added value: +{
+  "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"
+}

Changed1 schema field changedMay 26, 2026

addedInput schema / properties / min_partition_leg_kelly

Added value: +{
+  "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"
+}

Changed4 schema fields changedMay 24, 2026

addedInput schema / properties / category_filter

Added value: +{
+  "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

Previous value: -"Minimum |edge| in percentage points to include (default 0.5)."New value: +"Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage."

addedInput schema / properties / min_kelly

Added value: +{
+  "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

Added value: +{
+  "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"
+}

AddedMay 18, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Even with readOnlyHint and idempotentHint annotations, the description adds substantial behavioral detail: internal segmentation into three model families, precise edge calculation (net of slippage, Kelly capping at 0.25), the 24h-move warning, and a 'why is this empty' diagnostics section. It also discloses caching behavior ('Cached 1h at the KV level keyed on all knobs') and limitations (Fed signal unreliability), going well beyond what annotations alone convey.

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 and dense with technical jargon, but it is well-structured: purpose, model families, response segments, knobs, caveats, diagnostics, and caching. Every sentence adds information for a complex tool with nine knobs and multiple output segments. It could be slightly more streamlined, but the density is justified by the tool's complexity; it front-loads the core purpose before diving into detail.

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?

With no output schema, the description carries the full burden of explaining the response shape, and it does so thoroughly: top-level by_segment structure, fed_candidates/fed_note, and _diagnostics with funnel counters and filter_skips. It also explains the meaning of edge fields (edge_pp_net, kelly_fraction, market.liquidity) and the 24h-move warning. This is complete enough for an agent to know what to expect and how to interpret results.

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

Parameters4/5

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

The input schema has 100% parameter descriptions, so the baseline is 3. The description adds conceptual value by grouping parameters as 'TRADEABLE-EDGE KNOBS' and explaining their interplay (e.g., min_partition_leg_kelly is needed because partition arbs return kelly_fraction_half=0 at the parent level). This extra layer clarifies why and when to adjust knobs, going beyond the schema's per-parameter definitions.

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-resource pair ('Scan top Polymarket markets') and a clear outcome ('return opportunities where Pipeworx data disagrees with market price'). It narrows the scope to 'what should I bet on today' and explicitly avoids paging hundreds of markets, distinguishing its intent from broad list tools. This is more specific than many sibling tools, giving a clear sense of what this tool uniquely does.

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 gives a strong use case ('Built for "what should I bet on today"') and provides operational guidance on knobs like min_liquidity and max_spread_pp ('drop opportunities where edge isn't realizable'), and notes the Fed signal caveat ('excluded from ranking — 1m-T vs EFFR signal is unreliable...'). However, it does not explicitly contrast this tool with sibling alternatives (e.g., polymarket_edge_tracker or polymarket_fill_risk), so the when-not-to-use guidance is implicit rather than explicit.

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

All archive tools Inspect

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

The ask_pipeworx family (ask_pipeworx / ask_pipeworx_beta / ask_pipeworx_grounded / deep_research) has significant boundary blurring—ask_pipeworx_beta explicitly 'currently matches ask_pipeworx exactly'—and the six prediction-market tools (bet_research, polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) have heavily overlapping edge-detection purposes. Only the archive, memory, and subscription families are cleanly delineated.

Naming Consistency3/5

There are consistent family prefixes (ask_*, polymarket_*, pipeworx_*) and clean pluralized lists (list_files, list_subscriptions), but the full set mixes bare verbs (remember, recall, forget, search), nouns (entity_profile), and varying patterns (bet_research vs compare_entities, search vs search_within vs recent_changes). Readable in clusters, but no single naming convention binds the set.

Tool Count2/5

35 tools is heavy, and the count is fattened by five distinct product areas—data routing, prediction markets, archive.org access, memory, and subscriptions—that have little to do with each other or with the server name 'archive'. It sits in the 25+ heavy zone even before honoring the mismatch between its name and the sprawl of its purpose.

Completeness3/5

Individual subdomains are well-covered: the memory trio (remember/recall/forget), subscription lifecycle (subscribe/unsubscribe/list_subscriptions/recent_alerts), and archive lineup (search/get_metadata/list_files/wayback_check) are each complete, and extra machinery like pipeworx_feedback and recent_changes shows domain care. But the unifying domain is incoherent—a server named 'archive' that's also a universal data router and prediction-market toolkit—and the scope ends up both bloated and still full of gaps for any one of the intended users (e.g. no archive-item upload, no prediction-market portfolio management).

Polymarket Edges

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources