Skip to main content
Glama
Hyperodds MCP

Hyperodds MCP

by usehyperodds

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HTTPS_PROXYNoProxy URL to use when running behind a proxy. Requires NODE_USE_ENV_PROXY=1 to take effect.
HYPERODDS_MCP_URLNoThe hosted Hyperodds MCP server the bridge forwards requests to.https://api.usehyperodds.com/mcp
NODE_USE_ENV_PROXYNoSet to 1 to make Node.js read the HTTPS_PROXY environment variable. Needs Node.js 22.21 or later.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

Hyperodds: read-only data on Hyperliquid HIP-4 outcome markets from every deployer. Prices and fair lines are side-0 probabilities from 0 to 1; edges are in points after all fees. Fair lines are estimates; check fairConfidence and singleSource before relying on one. Daily allowance: 1000 tool calls per IP address, reset at 00:00 UTC. Third-party names describe compatibility only; no affiliation.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
odds_marketsA

Lists HIP-4 outcome markets from every deployer with live top of book, fair line and edge after all fees. Filter by category, deployer or text, sort by edge, volume, new or settling, and page with offset.

odds_clusterA

Gives one question listed by several HIP-4 deployers: each member's rule grade against the anchor (SAME, CLOSE or DIFFERENT) with the differences found, its top of book, and the merged book across SAME members. Look it up by cluster id or by any member's outcome id.

odds_fairA

Gives one market's fair line (probability and band, method, confidence, and each source with its weight and age) with the top of book and the edge after all fees for each way to trade. Check confidence and singleSource before acting on the line.

odds_newA

Lists HIP-4 markets newest first, with the same fields as odds_markets. Outcome ids grow with each listing.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 4 tools

Disambiguation3/5

odds_markets and odds_new overlap heavily: odds_new is essentially a newest-first view with the same fields, so an agent could reasonably pick either. odds_fair and odds_cluster are more clearly distinct, but the listing duplication keeps the set from being fully unambiguous.

Naming Consistency5/5

All tools use the same lowercase snake_case odds_ prefix with short, readable suffixes. There is no mixing of conventions or inconsistent verb styles.

Tool Count4/5

Four tools is a reasonable, focused surface for read-only odds analytics. However, odds_new does not fully earn its place because it largely duplicates odds_markets with a sort order.

Completeness4/5

The set covers market listing/filtering, fair-line detail, recent listings, and cross-deployer clustering, which is solid for a read-only analysis server. Minor gaps remain, such as direct market lookup or deployer-level metadata, but agents can work around them.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues