creditcards.best MCP server
best.creditcards/mcpcreditcards.beststreamable-httpv0.1.0Scanned
Search, compare and estimate rewards across US credit cards. Verified fees, APRs and bonuses.
6 tools: 2 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- 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 creditcards.best MCP server can do
The creditcards.best MCP server is published by creditcards.best, a domain the MCP Registry verified. It has 6 tools. It can create or change data (2 tools: estimate_rewards and check_eligibility), but cannot delete data. 4 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
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.
Last scanned Nov 12, 2026, version 0.1.0.
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.
6 tools
Changes things 2Claude Code: ask
check_eligibilityGiven a user's credit band (and optionally income), return cards they would typically qualify for, surfacing issuer application rules (e.g.No 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.
Description, as the server wrote it Given a user's credit band (and optionally income), return cards they would typically qualify for, surfacing issuer application rules (e.g. Chase 5/24) and any income floor. Only cards that publish a credit requirement can be answered; cards with no published requirement are counted in `unknownCount`, never listed as qualifying. This is a likelihood signal from published guidance, not an approval guarantee.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
estimate_rewardsGiven an annual spending profile (USD per category, e.g.No 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.
Description, as the server wrote it Given an annual spending profile (USD per category, e.g. { dining: 6000, groceries: 8000, travel: 4000, other: 20000 }), estimate each card's net rewards value and rank them. Net value = rewards earned on spend + first-year signup bonus − annual fee. Statement credits are reported separately (max value if fully used), NOT folded into the headline, to avoid overstating premium 'coupon-book' cards. Returns a per-category breakdown and the assumptions used. All card facts come from the verified dataset; only point valuation is modeled.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 4Show 4 read-only tools
compare_cardsSide-by-side detail for two or more cards by id: fees, foreign-transaction fee, signup bonus, earn rates, credits and eligibility.No findings
Why it is in this group
- The name "compare_cards" says "compare": a word for reading.
Description, as the server wrote it Side-by-side detail for two or more cards by id: fees, foreign-transaction fee, signup bonus, earn rates, credits and eligibility. Apply links are tracked redirects.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_apply_linkReturn the apply link for a card.No findings
Why it is in this group
- The name "get_apply_link" says "get": a word for reading.
Description, as the server wrote it Return the apply link for a card. This is always a creditcards.best tracked redirect that records the referral and forwards to the issuer; the raw issuer URL is never returned.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_cardFull detail for a single card by id (slug), including earn rates, credits, eligibility, sources and lastVerified.No findings
Why it is in this group
- The name "get_card" says "get": a word for reading.
Description, as the server wrote it Full detail for a single card by id (slug), including earn rates, credits, eligibility, sources and lastVerified. The apply link is our tracked redirect, not the issuer URL.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
search_cardsFilter the US credit-card dataset by product type, rewards currency (program name or kind), issuer, annual fee, foreign-transaction fee, signup-bonus value, credit band, or curated…No findings
Why it is in this group
- The name "search_cards" says "search": a word for reading.
Description, as the server wrote it Filter the US credit-card dataset by product type, rewards currency (program name or kind), issuer, annual fee, foreign-transaction fee, signup-bonus value, credit band, or curated category. Searches ONLY issuer-verified cards by default, because unverified stubs carry null for most filterable fields and a null is not a zero. Set verified:false for the stubs, or verified:null to search everything knowingly. Returns at most 25 summaries unless you raise `limit`; `total` is the full match count and `truncated` says whether you are seeing all of it. Rankings reflect fit, not placement.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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, 18:31 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
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.creditcards.best: tools/list returned 6 tools to an anonymous client, including estimate_rewards (write), check_eligibility (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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http creditcards https://mcp.creditcards.bestclaude mcp add --transport http creditcards https://mcp.creditcards.bestRun 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__creditcards__search_cards",
"mcp__creditcards__get_card",
"mcp__creditcards__get_apply_link",
"mcp__creditcards__compare_cards"
],
"ask": [
"mcp__creditcards__estimate_rewards",
"mcp__creditcards__check_eligibility"
],
"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 creditcards. Review it before you use it.
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/best.creditcards/mcp/verify?hash=93158140609c84757e7930bbe79e462b0bd3648b6ffa11ac155c1acb8138207e" | jq -e '.changed == false'Pinned hash 93158140609c, from Nov 12, 2026, 06:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/best.creditcards/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/best.creditcards/mcp)Source: MCP Registry. Synced Oct 21, 2026, 17:45 UTC.
creditcards.best MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the creditcards.best MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 2 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 creditcards.best MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the creditcards.best 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 creditcards.best MCP server have?
- 6 tools: 2 write, 4 read. estimate_rewards, check_eligibility, search_cards, get_card, get_apply_link and compare_cards.
Does the creditcards.best MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the creditcards.best MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the creditcards.best MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.