Feefo MCP by usefulapi
io.usefulapi/feefousefulapi.iostreamable-httpv1.19.4Scanned
Read Feefo service, product and NPS reviews and ratings; reply to reviews.
5 tools: 1 do something that can't be undone and 4 only read.
- Reads private data · 1
- Reads text others write · 5
- Can send data out · 1
- No findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
1 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Feefo MCP by usefulapi can do
The Feefo MCP by usefulapi is published by usefulapi.io, a domain the MCP Registry verified. It has 5 tools. It can do things that cannot be undone, such as sending, paying or publishing (feefo_reply_to_review), but cannot delete data. 4 tools only read.
1 tool reads private data (feefo_get_review); 5 tools bring in text other people can write (feefo_list_reviews, feefo_get_review, feefo_get_review_summary and 2 more); 1 tool can send data out of your system (feefo_reply_to_review). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 25, 2026, version 1.19.4.
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.
5 tools
Can't be undone 1Claude Code: ask
feefo_reply_to_reviewWRITE: publish a public reply to a review on your Feefo account, optionally emailing the customer (notify_customer).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "feefo_reply_to_review" says "reply": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "feefo_reply_to_review" says "reply": it sends or publishes something to other people.
Description, as the server wrote it WRITE: publish a public reply to a review on your Feefo account, optionally emailing the customer (notify_customer). Visible to the public on your Feefo page and not undoable through this server. `review_id` is the `id` of the service or product element returned by feefo_list_reviews (not the outer review url id). Confirm the wording with the user first.
Annotations the server declares
- title: Reply to a Feefo review
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 4Show 4 read-only tools
feefo_get_product_ratingsAverage star rating per product SKU (products[] with rating, sku and optionally review_count).Reads text others writeNo findings
Why it is in this group
- The name "feefo_get_product_ratings" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it Average star rating per product SKU (products[] with rating, sku and optionally review_count). Filter by product_sku (comma-separated, leading/trailing * wildcards allowed) or parent_product_sku.
Annotations the server declares
- title: Get Feefo product ratings
- readOnlyHint: true
feefo_get_reviewGet one review by its id (the `id` of a service or product element from feefo_list_reviews), optionally with its full thread of replies.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "feefo_get_review" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "thread": it reads messages.
- untrusted-inputThe name "feefo_get_review" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get one review by its id (the `id` of a service or product element from feefo_list_reviews), optionally with its full thread of replies.
Annotations the server declares
- title: Get a Feefo review
- readOnlyHint: true
feefo_get_review_summaryAggregate ratings for your Feefo account: average rating and star distribution (1 to 5 stars) for service and product reviews, merchant details, review counts.Reads text others writeNo findings
Why it is in this group
- The name "feefo_get_review_summary" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "feefo_get_review_summary" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it Aggregate ratings for your Feefo account: average rating and star distribution (1 to 5 stars) for service and product reviews, merchant details, review counts. mode: all (default), service, product (needs product_sku or parent_product_sku) or nps (promoters/passives/detractors). Use since_period=all for lifetime figures (Feefo default: the last year).
Annotations the server declares
- title: Get Feefo rating summary
- readOnlyHint: true
feefo_list_reviewsList reviews of your Feefo account, newest updates first.Reads text others writeNo findings
Why it is in this group
- The name "feefo_list_reviews" says "list": a word for reading.
What it can reach
- untrusted-inputThe name "feefo_list_reviews" says "list" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "review": it reads comments, which other people can write.
Description, as the server wrote it List reviews of your Feefo account, newest updates first. mode: all (service + product, default), service (seller/service reviews), product (product reviews; give product_sku or parent_product_sku) or nps (Net Promoter Score responses). Returns summary.meta (count, pages) and reviews[] with ratings, comment text, customer display name and review threads. Page with page/page_size.
Annotations the server declares
- title: List Feefo reviews
- 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.
5 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__feefo__feefo_reply_to_review"
]
}
}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 17, 2026, 15:25 UTC, unchanged since Oct 26, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: The server redirected a POST to a different request.
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 1.19.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http feefo https://feefo.usefulapi.io/mcpclaude mcp add --transport http feefo https://feefo.usefulapi.io/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__feefo__feefo_list_reviews",
"mcp__feefo__feefo_get_review",
"mcp__feefo__feefo_get_review_summary",
"mcp__feefo__feefo_get_product_ratings"
],
"ask": [
"mcp__feefo__feefo_reply_to_review"
],
"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 feefo. Review it before you use it.
Capability tags behind 5 rules
- mcp__feefo__feefo_list_reviews untrusted-input
- mcp__feefo__feefo_get_review private-data, untrusted-input
- mcp__feefo__feefo_get_review_summary untrusted-input
- mcp__feefo__feefo_get_product_ratings untrusted-input
- mcp__feefo__feefo_reply_to_review untrusted-input, outbound
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/io.usefulapi/feefo/verify?hash=cbda9397eaaa1131e12d79910c12564fb7f2a786fcdfe9e939244384717ff082" | jq -e '.changed == false'Pinned hash cbda9397eaaa, from Oct 25, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.usefulapi/feefo/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.usefulapi/feefo)Source: MCP Registry · repository. Synced Nov 18, 2026, 11:18 UTC.
Feefo MCP by usefulapi: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Feefo MCP by usefulapi safe?
- No scan can promise that. What its definitions show: 5 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 Feefo MCP by usefulapi delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Feefo MCP by usefulapi do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: feefo_reply_to_review.
What tools does the Feefo MCP by usefulapi have?
- 5 tools: 1 irreversible, 4 read. feefo_reply_to_review, feefo_list_reviews, feefo_get_review, feefo_get_review_summary and feefo_get_product_ratings.
Does the Feefo MCP by usefulapi need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Feefo MCP by usefulapi send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): feefo_reply_to_review.
Has the Feefo MCP by usefulapi changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 25, 2026.