Skip to main content
Glama

PropLine — Sports Betting Odds & Prop Resolution

by io.github.proplineapi
OverviewDiscussionsAdmin

Get cross-book +EV

propline_get_event_ev
Read-onlyIdempotent

Pro-tier endpoint. Returns cross-book +EV per outcome for an event. We anchor on a sharp book, remove vig, derive a no-vig fair line, and compute EV% per book at the same line. Outcomes are sorted with +EV plays floated to the top of each line group. PrizePicks is excluded from EV math (DFS payouts aren't comparable to per-book prices). The anchor is chosen PER LINE in the order pinnacle → polymarket → kalshi → bovada → smarkets, and each line's fair_source names the one used — report the anchor from fair_source per line, never assume Pinnacle anchored all of them. Optional bookmakers filter prices to the books the user holds accounts at; it never changes the anchor, so filtering to DraftKings still measures DraftKings against Pinnacle.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
devigNoHow the anchor's vig is removed. 'multiplicative' (default) divides each implied probability by the booksum; 'shin' solves Shin's insider-trading model, which loads the overround onto the longshot and corrects the favourite-longshot bias — use it when the user asks about longshot props (anytime TD, first scorer). The response echoes devig_method; say which method the numbers came from.
marketsNo
max_ageNoOptional, seconds. Drops quoted prices the book has not delivered within that many seconds (each outcome carries last_update). The fair line is unaffected.
event_idYes
sport_keyYes
bookmakersNoComma-separated book keys (e.g. 'draftkings,fanduel') to price only the user's books. Narrows prices, not the anchor.
min_ev_pctNoFilter to outcomes with EV ≥ this percent (e.g. 2.0).
fair_sourceNoOptional anchor override: one book or a comma-separated list tried IN ORDER per line, from pinnacle, polymarket, kalshi, bovada, smarkets (anything else is a 400). Lines none of them anchor are dropped. Omit for the default order. The single value 'consensus' (not combinable with book names) uses the median no-vig probability across every book quoting a clean, fresh two-sided market (3+ books); each line then lists the books used in fair_books. It is opt-in and NOT a proven better anchor — never describe it as more profitable.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / fair_source / description
      Previous value: -"Optional anchor override: one book or a comma-separated list tried IN ORDER per line, from pinnacle, polymarket, kalshi, bovada, smarkets (anything else is a 400). Lines none of them anchor are dropped. Omit for the default order."New value: +"Optional anchor override: one book or a comma-separated list tried IN ORDER per line, from pinnacle, polymarket, kalshi, bovada, smarkets (anything else is a 400). Lines none of them anchor are dropped. Omit for the default order. The single value 'consensus' (not combinable with book names) uses the median no-vig probability across every book quoting a clean, fresh two-sided market (3+ books); each line then lists the books used in fair_books. It is opt-in and NOT a proven better anchor — never describe it as more profitable."
    • addedInput schema / properties / max_age
      Added value: +{
+  "description": "Optional, seconds. Drops quoted prices the book has not delivered within that many seconds (each outcome carries last_update). The fair line is unaffected.",
+  "minimum": 0,
+  "type": "integer"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / fair_source
      Added value: +{
+  "description": "Optional anchor override: one book or a comma-separated list tried IN ORDER per line, from pinnacle, polymarket, kalshi, bovada, smarkets (anything else is a 400). Lines none of them anchor are dropped. Omit for the default order.",
+  "type": "string"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / devig
      Added value: +{
+  "description": "How the anchor's vig is removed. 'multiplicative' (default) divides each implied probability by the booksum; 'shin' solves Shin's insider-trading model, which loads the overround onto the longshot and corrects the favourite-longshot bias — use it when the user asks about longshot props (anytime TD, first scorer). The response echoes devig_method; say which method the numbers came from.",
+  "enum": [
+    "multiplicative",
+    "shin"
+  ],
+  "type": "string"
+}
  4. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare a safe read-only, idempotent, open-world operation, and the description layers on substantial extra behavior: outcomes sorted with +EV floated up, PrizePicks excluded, per-line anchor selection order, and the crucial warning to read the anchor from fair_source per line rather than assuming Pinnacle. That is real behavioral context beyond structured fields.

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?

It is front-loaded with the core purpose and then builds method detail efficiently. It is dense but mostly earns its length; the closing restatement of the bookmakers/filter behavior slightly overlaps the per-line anchor point, a minor redundancy.

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?

For a complex, 8-parameter analytics endpoint with no output schema, the description conveys return shape (per-outcome, sorted, fair_source, fair_books, last_update, devig_method echo) and the critical interpretation caveat about anchors. It stops short of enumerating the full output fields, which would be expected given the absence of an output schema.

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?

Schema coverage is 63% and the schema already carries rich text for devig, max_age, fair_source, and bookmakers. The description still adds cross-parameter meaning, notably that filtering to DraftKings 'still measures DraftKings against Pinnacle' (anchor unaffected by bookmakers) and that fair_source must be reported per line. It does not clarify markets/event_id/sport_key semantics, keeping it from a 5.

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 gives a specific verb+resource: 'Returns cross-book +EV per outcome for an event,' and immediately frames the methodology (anchor on a sharp book, remove vig, derive no-vig fair line, compute EV% per book). It is clearly distinguishable from siblings like propline_get_best_line or propline_get_odds, and states its scope exclusions (PrizePicks dropped from EV math).

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?

Guidance is present but embedded in method notes rather than an explicit when-to-use statement: devig='shin' is recommended 'when the user asks about longshot props,' and the bookmakers filter is explained as narrowing to the user's books. It does not explicitly name alternatives (e.g. get_best_line) or state when not to use this tool, so it falls short of a 5.

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

All PropLine — Sports Betting Odds & Prop Resolution toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources