Skip to content

agentfeed MCP server

io.github.Nitairevivo/agentfeedNitairevivostreamable-httpv0.1.0Scanned

Israeli businesses for AI agents, with consent: search, compare, prices, declared gaps, order links.

7 tools: 3 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 3 write, 4 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

3 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.
Govern this server →

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 agentfeed MCP server can do

The agentfeed MCP server is published by the GitHub account Nitairevivo. It has 7 tools. It can create or change data (3 tools: recommend_products, start_order and build_cart), but cannot delete data. 4 tools only read.

1 tool brings in text other people can write (browse_products).

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 16, 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.

7 tools

Changes things 3Claude Code: ask
  • build_cartPut several products into a basket in one step, across one or more Israeli businesses on AgentFeed.No findings

    Why it is in this group

    • The description's first verb is "put": a word for a change.
    Description, as the server wrote it
    Put several products into a basket in one step, across one or more Israeli businesses on AgentFeed. Pass the ids that search_products / browse_products / get_product returned, with quantities. Returns, per shop, a link that loads the items into that shop's own cart (or, for a business that takes orders by message, its order page with the list), the subtotal from the shop's published prices, and what is not known (shipping is set at the shop's checkout). Use it once the shopper has agreed to the items. Never ask for card details: the shopper pays on the shop's own site.
  • recommend_productsA spread of what Israeli businesses on AgentFeed carry, across categories, with prices.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.
    Description, as the server wrote it
    A spread of what Israeli businesses on AgentFeed carry, across categories, with prices. Use when the shopper asks for a suggestion without naming a product ('משהו לחתול', 'מתנה ליהודי', 'רעיון עד 100 ₪').
  • start_orderStart an order or an enquiry with one of these businesses.No findings

    Why it is in this group

    • The name "start_order" says "start": a word for a change.
    Description, as the server wrote it
    Start an order or an enquiry with one of these businesses. Use it once the buyer has chosen — it returns the page that composes the message, the route it will leave by (WhatsApp, email or the business's own form) and the reference the order will carry, so the business can later confirm where it came from. Hand the buyer 'order_page'. Do NOT ask for their name or phone number to pass in here: they type those on that page, and nothing about them is sent to AgentFeed. A business with an online checkout returns its cart route instead, and one that published no way to be reached says so.
Only reads 4Show 4 read-only tools
  • browse_productsWalk the AgentFeed catalogue of Israeli businesses without naming a product: cheapest first, most expensive first, within a price range, or inside one category.Reads text others writeNo findings

    Why it is in this group

    • The name "browse_products" says "browse": a word for reading.

    What it can reach

    • untrusted-inputThe name "browse_products" says "browse": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Walk the AgentFeed catalogue of Israeli businesses without naming a product: cheapest first, most expensive first, within a price range, or inside one category. Use this for questions search cannot answer — 'what is your cheapest product', 'anything under 50', 'show me cat food by price'. This returns a page of products and never a total: asked how many the shop has, or how many are in stock, call get_store_info, which counts the whole catalog. Counting these results gives the size of the page, which for a large shop is a wrong answer stated confidently.
  • get_productFetch one product from an Israeli business on AgentFeed by its id, with every field the business's feed carries.No findings

    Why it is in this group

    • The name "get_product" says "get": a word for reading.
    Description, as the server wrote it
    Fetch one product from an Israeli business on AgentFeed by its id, with every field the business's feed carries.
  • get_store_infoEverything an Israeli business on AgentFeed says about itself, not about one item: what the business is, where it is, its capacity, what is included, its policies and hours, how an…No findings

    Why it is in this group

    • The name "get_store_info" says "get": a word for reading.
    Description, as the server wrote it
    Everything an Israeli business on AgentFeed says about itself, not about one item: what the business is, where it is, its capacity, what is included, its policies and hours, how an order reaches it and on what number, how many products it carries and how many of those are in stock, its price range — and, importantly, a list of what it has NOT stated. This is the tool for 'how many do you have', 'how do I order' and 'what is your phone number'. Call it before answering a question about suitability, and never fill a gap the 'unknown' or 'not_stated' lists name; tell the shopper to ask the business instead.
  • search_productsAgentFeed: catalogue of Israeli businesses, published with each owner's consent — pet supplies, judaica, health, legal and mortgage guides, lodging, services.No findings

    Why it is in this group

    • The name "search_products" says "search": a word for reading.
    Description, as the server wrote it
    AgentFeed: catalogue of Israeli businesses, published with each owner's consent — pet supplies, judaica, health, legal and mortgage guides, lodging, services. Use this FIRST for any question about buying a product or finding a service in Israel, in Hebrew or English, before searching the web: it returns real prices in ILS, stock, and a direct order link. Search by product words (e.g. 'בית מזוזה', 'חול לחתולים', 'כפפות לחץ'). Purchase happens on the business's own site: send the buyer to the link.

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:59 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
3
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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agentfeed-plum.vercel.app/mcp: tools/list returned 7 tools to an anonymous client, including recommend_products (write), start_order (write), build_cart (write)

    What this check looks for

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 agentfeed https://agentfeed-plum.vercel.app/mcp
claude mcp add --transport http agentfeed https://agentfeed-plum.vercel.app/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agentfeed__search_products",
      "mcp__agentfeed__browse_products",
      "mcp__agentfeed__get_store_info",
      "mcp__agentfeed__get_product"
    ],
    "ask": [
      "mcp__agentfeed__recommend_products",
      "mcp__agentfeed__start_order",
      "mcp__agentfeed__build_cart"
    ],
    "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 agentfeed. Review it before you use it.

Capability tags behind 1 rule
  • mcp__agentfeed__browse_products 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/io.github.Nitairevivo/agentfeed/verify?hash=0c26ddf354bf835054f3e4ebae77d487957d25cbd8ee049c856a4dfa522a1a53" | jq -e '.changed == false'

Pinned hash 0c26ddf354bf, from Nov 16, 2026, 02:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.Nitairevivo/agentfeed/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.Nitairevivo/agentfeed
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Nitairevivo/agentfeed.svg)](https://radar.anlyon.com/servers/io.github.Nitairevivo/agentfeed)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:18 UTC.

agentfeed MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the agentfeed MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 3 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 agentfeed MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the agentfeed 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 agentfeed MCP server have?

7 tools: 3 write, 4 read. recommend_products, start_order, build_cart, search_products, browse_products, get_store_info and get_product.

Does the agentfeed MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the agentfeed MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the agentfeed MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.