NegativeEV bet checker MCP server
com.negativeev/bet-checkernegativeev.comstreamable-httpv1.4.5Scanned
Grade any MLB, WNBA, PGA or ATP bet against thousands of play-by-play sims. No key, no signup.
3 tools: 1 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the NegativeEV bet checker MCP server can do
The NegativeEV bet checker MCP server is published by negativeev.com, a domain the MCP Registry verified. It has 3 tools. It can create or change data (1 tool: check_bet), but cannot delete data. 2 tools only read.
1 tool brings in text other people can write (check_bet).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 1.4.5.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Changes things 1Claude Code: ask
check_betCheck a specific sports bet against thousands of play-by-play game simulations: each leg's simulated probability, the sportsbook's implied probability, and the edge.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check a specific sports bet against thousands of play-by-play game simulations: each leg's simulated probability, the sportsbook's implied probability, and the edge. Send the bet as plain text - teams or players, market, line, odds. A parlay in one string is graded leg by leg and priced as a whole. Call this first; nothing has to be set up, and a missing slate, an unrecognized bet, or an unsupported market comes back as a plain `status` without spending a check. It prices a bet the caller names and never suggests one, so there is nothing to send for "what should I bet tonight". Every result leads with `status` and `check_spent` and says whether re-wording would change anything; when it says no, it means no. Covers MLB, WNBA, PGA, ATP, and NFL. A game that already started still checks, against the simulations from before it began.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
get_slateWhich of MLB, WNBA, PGA, ATP, and NFL have a checkable slate right now - at least one simulated game that has not started.No findings
Why it is in this group
- The name "get_slate" says "get": a word for reading.
Description, as the server wrote it Which of MLB, WNBA, PGA, ATP, and NFL have a checkable slate right now - at least one simulated game that has not started. Pass `sport` for one; omit it for all. Free, spends no check. It is not required before `check_bet`, which reports a missing slate itself at no cost. Call it to answer "what can be checked today", or after a `no_slate` or `ungraded` result, which mean the game is not on the simulated slate rather than that the bet was worded wrong.
Annotations the server declares
- readOnlyHint: true
get_usageHow many bet checks the caller has left and when the next one frees up - 100 a day shared per device anonymously, 1000 an hour with a signed-in user's token.No findings
Why it is in this group
- The name "get_usage" says "get": a word for reading.
Description, as the server wrote it How many bet checks the caller has left and when the next one frees up - 100 a day shared per device anonymously, 1000 an hour with a signed-in user's token. Free, spends no check. It grades nothing, so it is not a step before a check: call it when a check comes back refused for quota, or before working through a long list of bets.
Annotations the server declares
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:43 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://negativeev.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://bnmlyacvflqcwslhcxua.supabase.co/auth/v1
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://negativeev.com/mcp: tools/list returned 3 tools to an anonymous client, including check_bet (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Install
Pinned to version 1.4.5. Values in angle brackets are yours to fill in.
claude mcp add --transport http bet-checker https://negativeev.com/mcpclaude mcp add --transport http bet-checker https://negativeev.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__bet-checker__get_slate",
"mcp__bet-checker__get_usage"
],
"ask": [
"mcp__bet-checker__check_bet"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as bet-checker. Review it before you use it.
Capability tags behind 1 rule
- mcp__bet-checker__check_bet untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.negativeev/bet-checker/verify?hash=ba8da8df0eda52064d065124b41e0a27dee7d27ca5390887a549ae65b3f3f505" | jq -e '.changed == false'Pinned hash ba8da8df0eda, from Nov 10, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.negativeev/bet-checker/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.negativeev/bet-checker)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:59 UTC.
NegativeEV bet checker MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the NegativeEV bet checker MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the NegativeEV bet checker MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the NegativeEV bet checker MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the NegativeEV bet checker MCP server have?
- 3 tools: 1 write, 2 read. check_bet, get_slate and get_usage.
Does the NegativeEV bet checker MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the NegativeEV bet checker MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the NegativeEV bet checker MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.