odds-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
odds-mcp
An MCP server over odds data where every read names its evidence and the one write is impossible without an approval token.
Model Context Protocol is how an LLM agent gets tools. The dangerous part is never the reads - it is the one tool that does something. This server demonstrates the pattern that makes side-effectful agent tools safe enough to exist: a risk envelope checked before a human ever sees the request, a single-use approval token issued by a separate step, a publish that cannot happen without it, and an append-only audit log that records every attempt - especially the refused ones.
Data comes from odds-consensus: 5 books normalized into one schema, de-margined fair prices, and a cross-book consensus view. This repo is the integration surface on top.
MCP client (Claude, any agent)
│ tools
▼
odds-mcp server ──── reads ────> store.py (consensus / fair price / outliers)
│ ▲
└──── the one write ────> gate.py propose → approve → publish
│ (envelope · token · audit)
└──────> out/audit_log.jsonlTools
Tool | Kind | Behavior |
| read | events in the snapshot |
| read | books per market, price ranges, median fair odds, outliers |
| read | one market's fair price — or an explicit not-found with the valid alternatives. Ambiguous line? It asks. Single book? "A single book is not a consensus." Never a guess. |
| read | books off the consensus median, with exact deviation % |
| read | counts plus every upstream devig refusal — what the snapshot does not cover |
| write-intent | checked against the risk envelope (max % over fair, stake cap) before a human sees it; refusals carry the reason |
| human gate | issues a single-use approval token (production: a trader's Telegram approval card; same gate logic) |
| write | requires proposal id + matching token; token dies on use; replay fails |
| read | the append-only log of every attempt and outcome |
Related MCP server: RapidOddsAPI MCP
Run it
pip install -r requirements.txt
python -m pytest tests/ -q # 13 tests
PYTHONPATH=src python -m odds_mcp.server # stdio MCP serverClaude Desktop config:
{"mcpServers": {"odds": {"command": "python", "args": ["-m", "odds_mcp.server"],
"cwd": "<this repo>", "env": {"PYTHONPATH": "src"}}}}What the tests pin down
Publishing without approval: refused. Wrong token: refused. Replaying a used token: refused. (Tokens are single-use and compared constant-time.)
A boost priced above the envelope (default: 5% over consensus fair) is refused at propose time, with the arithmetic in the reason.
get_fair_priceon a market with two live lines demands an explicitlineinstead of picking one; on a single-book market it refuses to call one price a "consensus".Every attempt - including every refusal - lands in the audit log.
All 9 tools are actually registered on the server (test asserts the exact set).
Why this shape
An agent that can only read is safe but useless; an agent that can write is useful but dangerous. The resolution is not "trust the model" - it is structure: envelope, then human, then token, then audit. The model can draft; only the gate can act; and the log never forgets.
MIT licensed. Part of a set of small, honest data gates: jigonyoo.com.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hosted MCP for live Pinnacle odds, drops, fair prices and closing lines.
Sportsbook-derived no-vig fair value with confidence, provenance, and history over REST/MCP.
Historical tick, order book and settlement data for Polymarket and Predict.fun crypto up/down markets, plus smart-money lists and backtest quotes, over a read-only MCP server.
MCP server for accessing Glypse's prediction market analytics and research.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP-compatible server that gives AI agents access to alternative sports data across 30+ leagues — odds, events, probabilities, settlement, and futures for prediction markets, DFS platforms, and sportsbooks.2918 PyPIMIT

RapidOddsAPI MCPofficial
AlicenseAqualityCmaintenanceLive bookmaker odds from 100+ sportsbooks (AU, US, EU), arbitrage and value bet finders, live game results and player stats for AI assistants. Built on the official RapidOddsAPI Python SDK. Free tier available.5MIT- AlicenseAqualityDmaintenanceMCP server providing deterministic betting odds tools including conversions, margin, parlay pricing, settlement, and Kelly staking.7MIT
- AlicenseAqualityBmaintenanceMCP server that brings live Australian racing and sports odds from 12 bookmaker/exchange sources into AI assistants, with per-price age data and tools for next races, best odds, results, and movers.9MIT