Skip to main content
Glama

Kegg

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. First observed

TDQS

A3.9/5.0
Behavior4/5

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

The description discloses several behavioral traits beyond annotations: caching ('Cached 1h at the KV level'), response structure with diagnostics ('_diagnostics{...filter_skips} so callers can see WHY a segment is empty'), and edge computation details (Kelly fraction caps at 0.25, slippage subtraction). The readOnlyHint and idempotentHint are already in annotations, so the description adds useful operational context without contradiction.

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

Conciseness2/5

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

The description is excessively long and dense, presenting a wall of text without clear structure. It covers multiple segments, response fields, and edge computation details in a single paragraph. While the content is valuable, it would benefit from breaking into sections (e.g., Overview, Model Families, Filtering, Response) to improve readability. 2 because overlong and unstructured.

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

Completeness4/5

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

Given the complexity (9 parameters, no output schema), the description is fairly complete. It explains the three response segments, the fed_note, diagnostics, and the tradeable-edge knobs. It even details edge computation and caching. The missing output schema is partially compensated by the description's detailed explanation of what each response element contains. Score 4 because it covers most aspects an agent would need to understand the tool's behavior.

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

Parameters3/5

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

All 9 parameters are documented in the input schema with descriptions, so the baseline is 3. The description adds some value by grouping parameters into 'TRADEABLE-EDGE KNOBS' and providing behavioral context (e.g., 'min_kelly never filters them' for partition arbs). However, the parameter descriptions in the schema are already comprehensive, so the description's addition is marginal.

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 clearly states the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today"'. It identifies the specific resource (Polymarket markets) and action (return opportunities with edge). The purpose is well-differentiated from sibling tools like polymarket_arbitrage and polymarket_edge_tracker.

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 explains the tool's use case: discovering opportunities without paging hundreds of markets. However, it does not explicitly state when to avoid this tool or suggest alternatives. Given the extensive sibling list, explicit guidance on when to use polymarket_arbitrage vs this tool would improve clarity. The description implies it is the primary edge discovery tool.

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

All Kegg 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
Disambiguation3/5

Most tools have clearly described distinct purposes, but several overlap: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, and ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all occupy neighboring query/discovery territory. The Polymarket and memory tool families, by contrast, are well differentiated.

Naming Consistency3/5

All names are snake_case and readable, but the set mixes verb-first names (ask_pipeworx, compare_entities, resolve_entity, validate_claim) with noun-phrase names (entity_profile, bet_research, recent_alerts, polymarket_arbitrage) and brand prefixes (pipeworx_*, polymarket_*). There is no consistent verb_noun pattern across the toolkit.

Tool Count2/5

34 tools is well beyond the heavy range, and the count is especially inappropriate because the server is named Kegg but only find, get_entry, and list_database relate to KEGG bioinformatics. The remaining 31 tools span unrelated domains (generic data research, prediction markets, memory, subscriptions, AI visibility, npm scanning), making the scope feel like several products merged into one.

Completeness2/5

As a KEGG server, the surface is severely thin: three read-only tools with no pathway mapping, sequence search, or cross-reference utilities. The Pipeworx research and Polymarket betting subsystems are more complete, but their presence under a Kegg server makes the overall surface incoherent rather than complete.

Resources