Skip to main content
Glama

Paperswithcode

by io.github.pipeworx-io

Polymarket–Kalshi Spread

polymarket_kalshi_spread
Read-onlyIdempotent

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) topic — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit kalshi_event_ticker + polymarket_event_slug for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning is a sentence and compatibility_codes[] the machine-readable form; BOTH can be non-empty on returned pairs, so read them even when matched_pairs>0. Codes: event_subject_mismatch (the two event titles share no subject words — probably not the same question), temporal_mismatch (they resolve in different months), temporal_alignment_unknown (the resolution month could not be parsed on one or both sides — NOT the same as confirmed-aligned; check each event's close/strike date yourself), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, pairing_unverified (set in EITHER mode whenever pairs are returned: the legs were matched by keyword and word overlap, not a shared resolution source). Each entry in top_spreads_pp carries its own flags[] (temporal_mismatch, temporal_alignment_unknown, event_subject_mismatch, low_token_overlap). A leg whose metric_type or match_subtype is "unknown" is NEVER paired — those comparisons land in spread.skipped_unclassified and, when the wording lined up, in spread.low_confidence_pairs[] for inspection only. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period, in EITHER mode; null means it could not be computed (see temporal_alignment_unknown), not that the two sides align. spread.fees_note is a standing disclosure: Kalshi charges per-contract trading fees, Polymarket does not, and this tool does not model Kalshi's fee schedule — every spread_pp is gross, not a net tradeable edge. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicNoPre-mapped: fed | btc | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president
kalshi_event_tickerNoExplicit Kalshi event ticker, e.g. "KXFED-26OCT". Overrides the topic-mapped Kalshi side.
polymarket_event_slugNoExplicit Polymarket event slug, e.g. "fed-decision-in-june-825". Overrides the topic-mapped Polymarket side.

Schema Changelog

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

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "topic": "fed"
+  },
+  {
+    "topic": "btc"
+  }
+]
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

The description goes far beyond the annotations, disclosing that spreads are gross rather than net of fees, that token-overlap matching is used, that compatibility warnings may appear even with matched pairs, and that unclassified legs are never paired. It also explains the meaning of all compatibility codes and skipped counters. This is exemplary behavioral disclosure for a read-only, open-world tool.

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

Conciseness5/5

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

The description is long, but every section earns its place: purpose, modes, response structure, safety fields, codes, fee disclosure, and limitations are all clearly organized and front-loaded. It reads as a dense reference rather than padding, and the warning at the end is material guidance rather than filler.

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 shoulders the burden of explaining return values, and it does so thoroughly: leg prices, spread points, compatibility fields, alignment data, skipped counters, and fee disclosures are all described. The edge cases and limitations—unknown temporal alignment, unclassified legs, pre-mapped not being tradeable—are explicitly covered, making the tool safely callable by an agent.

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 already provides 100% coverage of the three parameters, including descriptions and examples. The description adds valuable context by explaining that explicit parameters override topic-mapped sides and that both modes run the same matcher. This extra layer is useful but not strictly necessary given the schema's completeness.

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

Purpose4/5

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

The description clearly identifies the tool's function: computing cross-venue price spreads between Kalshi and Polymarket for the same resolving question. It names specific modes and expected outputs. However, it does not explicitly differentiate itself from sibling tools like polymarket_arbitrage, leaving some differentiation to inference.

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 clearly explains when to use the topic-based macro shortcuts versus explicit event ticker/slug pairing, and warns that most pre-mapped topics currently return compatibility warnings. It provides strong context for selecting the right mode, though it does not directly state when to prefer this tool over sibling alternatives.

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

All Paperswithcode 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

ask_pipeworx and ask_pipeworx_beta are currently identical in behavior, creating direct overlap. Additionally, the five query/research tools (ask_pipeworx, ask_pipeworx_grounded, deep_research, validate_claim, bet_research) and six Polymarket tools have heavily overlapping boundaries that require reading long descriptions to disambiguate.

Naming Consistency3/5

Names are uniformly snake_case and mostly readable, with consistent domain prefixes (polymarket_*, pipeworx_*) and a verb_noun majority (get_paper, search_papers, resolve_entity). However, bare-verb memory tools (remember, recall, forget) and adjective-noun names (recent_alerts, trending_papers, deep_research) break the dominant convention, making the set mixed though not chaotic.

Tool Count2/5

At 35 tools, this exceeds the 25+ threshold for 'too many,' and several are near-duplicates or overlapping query modes (ask_pipeworx vs ask_pipeworx_beta vs ask_pipeworx_grounded). The server bundles paper search, a universal data router, prediction-market analytics, memory, subscriptions, dependency scanning, and AI visibility into one surface, which feels over-scoped.

Completeness4/5

The surface is quite thorough for its broad domain: querying has grounded/deep/meta variants, companies have profile/compare/change/claim tools, prediction markets have research/edges/arbitrage/fill-risk/spread tracking, and subscriptions/memory have full lifecycles. Minor gaps exist (no full pack catalog listing, no direct fetch-by-URI tool, no paper leaderboards), but agents can work around them via discover_tools/ask_pipeworx.

Resources