Skip to main content
Glama

Hunter

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

A4.7/5.0
Behavior5/5

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds extensive behavioral context: caching strategy (1h at KV level keyed on all knobs), edge calculation details, slippage handling, diagnostic output for empty segments, and the Fed note about unreliable signal. No contradictions 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 long but well-structured: front-loaded purpose, then segment details, tradeable-edge knobs, response structure. Every sentence provides value. Could be slightly more concise, but the complexity of the tool justifies the length.

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 9 parameters (0 required), no output schema, and multiple sibling tools, the description is remarkably complete. It explains the output structure (by_segment, fed_candidates, diagnostics), why segments may be empty, tradeable-edge knobs, and caching behavior. No gaps remain for an AI agent to invoke correctly.

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%, so baseline is 3. The description adds significant value beyond the schema: e.g., for slippage_pp it explains Polymarket zero fees but typical 20-50bp slippage; for min_partition_leg_kelly it explains why standard min_kelly doesn't apply and how this knob works. All 9 parameters have enriched descriptions with usage context.

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.' It distinguishes from siblings like polymarket_arbitrage and polymarket_edge_tracker by detailing the unique three-segment approach (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT) and specific use case 'what should I bet on today'.

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 addresses when to use the tool ('Built for "what should I bet on today"') and explains the three segments, including tradeable-edge knobs and Fed bets caveat. However, it does not explicitly state when NOT to use it or list alternative sibling tools for comparison, which would improve guidance.

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

All Hunter 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

Several tool clusters have genuinely blurry boundaries: ask_pipeworx, ask_pipeworx_beta (explicitly 'currently matches ask_pipeworx exactly'), ask_pipeworx_grounded, and deep_research all route questions to the same 5,743-tool catalog, and the six Polymarket tools (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) heavily overlap on 'should I bet / where is the edge'. The descriptions are detailed and cross-reference each other, but an agent would still struggle to pick correctly among near-duplicates.

Naming Consistency3/5

Everything is uniformly snake_case and readable, but there is no consistent verb_noun pattern: verb_noun (resolve_entity, discover_tools, validate_claim) mixes with noun_noun (domain_search, entity_profile, polymarket_arbitrage), adjective_noun (deep_research, recent_changes), bare verbs (forget, recall, remember), and brand prefixes (pipeworx_*, ask_pipeworx_*). Readable, but patternless.

Tool Count2/5

34 tools is well above the heavy threshold, but the bigger issue is scope incoherence: a server named 'Hunter' dedicates only 3 of 34 tools to Hunter.io email lookup while the remaining 31 belong to an unrelated Pipeworx data-research/prediction-market platform. The count is not earned by a single coherent purpose.

Completeness3/5

The Pipeworx research core is quite thorough: entity resolution, single-lookup, grounded answers, deep research, profiles, comparisons, claim validation, semantic search-within-records, change feeds, subscriptions, and memory form a full research lifecycle. However, the domain is a grab-bag spanning email finding, npm dependency checking, prediction markets, and data research, and the three Hunter.io tools that match the server name are only a thin fragment of the surface.

Resources