io.github.rapidoddsapi/rapidoddsapi-mcp
PYPI · RAPIDODDSAPI-MCP
Bookmaker odds, live scores, arbitrage and value bets from 100+ books, via RapidOddsAPI.
Available components
Last scanned (15 hours ago)
Scores higher than 48% of PyPI servers
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 33 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 4 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability56
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2146 tokens (~357/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (14)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (2)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 20 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 16 Nov 26 50
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed pypi/rapidoddsapi-mcp@0.5.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 33 packages
| Packages resolved | 33 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
find_arbitrage ~288
Find bets where backing both sides at different bookmakers locks in profit. Fetches odds first, so it costs the same as get_odds: ceil(number of bookmakers / 5) credits for the single market. It defaults to every feed, about 7 credits, since an arbitrage only exists where books disagree and the more of them priced, the more chances there are. A group or names narrow it, as on get_odds. Works on any market whose bets have two sides: head_to_head and its period variants, soccer's draw_no_bet, totals, handicaps, team totals and player props. Only three-way markets are rejected, with an explanation rather than silently returning nothing. On a market with a line each line is a separate bet, so a totals market can return several results for one game. Over 8.5 is never paired with Under 9.5, and a handicap of -1.5 only ever with +1.5. min_profit is a percentage, default 1.0. Below roughly 1 percent an edge usually disappears while the second leg is being placed. Set it negative to see near misses.
| Name | Type | Req | Description |
|---|---|---|---|
| bookmakers | – | – | – |
| market | string | – | – |
| min_profit | number | – | – |
| sport | string | yes | – |
| stake | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
find_value_bets ~379
Find prices that beat fair value. Bookmakers price in a margin, so their odds sum to more than certainty. Removing it leaves a fair price, and any book paying more than that is positive expected value. devig says where the fair price comes from, and is worth explaining to the user rather than just picking: "all" the default. Every bookmaker fetched is de-vigged on its own and the results averaged. Needs no view on which book is sharp, works on markets Pinnacle does not price, and is the one to use unless there is a reason not to. a book name "Pinnacle" measures every other book against that one. A sharp book runs thin margins and moves fast, so its prices track true probability more closely than an average does. Tighter, but only where that book prices the market, and it cannot itself appear in the results. Fetches odds first, so it costs the same as get_odds: ceil(number of bookmakers / 5) credits for the single market. Defaults to every feed, about 7 credits; a group or names narrow it, as on get_odds. A book named as devig is added to the request automatically, since the calculation is impossible without it. Same markets as find_arbitrage: head_to_head and its period variants, draw_no_bet, totals, handicaps, team totals and player props. min_edge is a percentage, default 2.0. Smaller edges are usually inside the error of the fair price rather than real value.
| Name | Type | Req | Description |
|---|---|---|---|
| bookmakers | – | – | – |
| devig | string | – | – |
| market | string | – | – |
| min_edge | number | – | – |
| sport | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_futures ~242
Season-long outright odds for one sport, such as the Brownlow Medal or the AFL Premiership, live from RapidOddsAPI. Use this, not get_odds, for anything decided over a season rather than in one game. Only AFL has futures today; list_sports marks which sports do. market_types is required. Take the keys from list_sports(sport), which lists the futures keys separately from the match ones. A match key such as head_to_head returns nothing here. Cost: number of market types x ceil(number of bookmakers / 5) credits, charged only when prices come back. bookmakers works as on get_odds: every feed by default, about 7 credits per market, or a group or names. season defaults to the latest one stored. Long fields are cut to the favourites, with a count of the rest. A market disappears once it settles, since the books stop pricing it, so an empty result shortly after the event is expected rather than an error.
| Name | Type | Req | Description |
|---|---|---|---|
| bookmakers | – | – | – |
| market_types | array | yes | – |
| season | – | – | – |
| sport | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_odds ~366
Current bookmaker odds for one sport, live from RapidOddsAPI. Use this for any question about what a bookmaker is paying right now, or for comparing prices across bookmakers, rather than answering from memory. sport is required and must be an id from list_sports. There is no option for every sport at once. Cost: number of market types x ceil(number of bookmakers / 5) credits, charged only when games come back. The default, one market across every feed, is about 7 credits. Both arguments multiply, so nine market types across every feed is about 63. market_types defaults to head_to_head, the plain winner market. Soccer has no head_to_head because of the draw, so use head_to_head_3_way or draw_no_bet there. Get exact keys from list_sports(sport). bookmakers defaults to every feed. To narrow it, and the cost with it, pass a group, "AU", "US", "EU" or "EXCHANGES", or names from list_sports(sport), or a mix: ["AU", "Pinnacle"]. Feeds price across regions, so a group is a way to choose books, not a guarantee they carry the sport. Never guess a name: an unknown one returns no prices rather than an error, so guessing is indistinguishable from the sport having no odds. Names are odds feeds, not brands. "Ladbrokes" is the feed that also carries Neds, "Betmakers" carries the 26 brands running on it, so a brand name that is not itself a feed returns nothing.
| Name | Type | Req | Description |
|---|---|---|---|
| bookmakers | – | – | – |
| market_types | – | – | – |
| sport | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_results ~167
Live scores and player stats for one sport, from RapidOddsAPI. Use this for current scores, whether a game has finished, and player statistics, rather than answering from memory or searching. Costs 1 credit, charged only when games come back, whatever the filters. Results cover fewer sports than odds do. list_sports marks which ones have them; asking for a sport without results coverage returns nothing. status: all (default), live, concluded or upcoming. include: scores, players, or both (default). A typo is rejected. A named total such as full_time stays null until that period is complete, so nothing settles early. Sum by_period for a live running total.
| Name | Type | Req | Description |
|---|---|---|---|
| include | – | – | – |
| sport | string | yes | – |
| status | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
list_sports ~314
List the sports RapidOddsAPI covers, or one sport's market types. This is the live coverage list, read from the API. It answers "what sports does RapidOddsAPI have", "which leagues are supported", "does it cover the NFL" and anything similar. Call it rather than answering from memory or searching the web, both of which go stale as coverage changes. Costs 0 credits, so call it freely. Use it before get_odds whenever the sport id or the market type is not certain, since a guessed market type returns nothing and a guessed sport id is an error. With no argument: every sport id, plus which of them have live scores and which have futures. With a sport: that sport's market types, grouped into game, team and player_props, and every bookmaker you can request for it. Any of those market keys is valid as a get_odds market_type, and any of those bookmaker names is valid as a get_odds bookmaker. Sports with futures also list their futures keys, which go to get_futures instead. Call this before naming bookmakers. Unrecognised names are not an error, they return no prices, so probing to find out which exist looks like a sport simply having no odds and costs credits for each attempt. A sport being listed means the id is accepted, not that games are on right now. Out of season returns an empty result, which costs nothing.
| Name | Type | Req | Description |
|---|---|---|---|
| sport | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the io.github.rapidoddsapi/rapidoddsapi-mcp server?
io.github.rapidoddsapi/rapidoddsapi-mcp runs locally as a PyPI package, launched with uvx rapidoddsapi-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · rapidoddsapi-mcp
claude mcp add rapidoddsapi-rapidoddsapi-mcp -- uvx rapidoddsapi-mcp
What is the io.github.rapidoddsapi/rapidoddsapi-mcp server?
io.github.rapidoddsapi/rapidoddsapi-mcp is listed in the public MCP registry as io.github.rapidoddsapi/rapidoddsapi-mcp. Bookmaker odds, live scores, arbitrage and value bets from 100+ books, via RapidOddsAPI. This page covers its PyPI package (rapidoddsapi-mcp).
Is the io.github.rapidoddsapi/rapidoddsapi-mcp server safe to use?
io.github.rapidoddsapi/rapidoddsapi-mcp scores 50 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.rapidoddsapi/rapidoddsapi-mcp server expose?
io.github.rapidoddsapi/rapidoddsapi-mcp exposes 6 tools: list_sports, get_odds, get_futures, get_results, find_arbitrage, find_value_bets. Their descriptions and schemas cost roughly 1,756 tokens of context every time the server is loaded.
Is the io.github.rapidoddsapi/rapidoddsapi-mcp server still maintained?
io.github.rapidoddsapi/rapidoddsapi-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.rapidoddsapi/rapidoddsapi-mcp server under?
io.github.rapidoddsapi/rapidoddsapi-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the io.github.rapidoddsapi/rapidoddsapi-mcp server?
VerifyMCP ran 14 checks on io.github.rapidoddsapi/rapidoddsapi-mcp, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about io.github.rapidoddsapi/rapidoddsapi-mcp: Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.