Skip to content

agproxy MCP server

dev.shveik/agproxyshveik.devstreamable-httpv1.0.0Scanned

Residential proxy traffic and raw fetch for agents, 190+ countries, sticky sessions. Pay per call.

3 tools: 2 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 2 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

2 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 agproxy MCP server can do

The agproxy MCP server is published by shveik.dev, a domain the MCP Registry verified. It has 3 tools. It can create or change data (2 tools: proxy and feedback), but cannot delete data. 1 tool only reads.

2 tools bring in text other people can write (proxy and fetch); 1 tool can send data out of your system (fetch).

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 17, 2026, version 1.0.0.

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.

3 tools

Changes things 2Claude Code: ask
  • feedbackFree.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
    Free. Tell the people who run this service what worked, what failed or what you miss: a bug, an idea or a thanks. A person reads it. No payment, no account; limited to a few messages an hour.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
  • proxyResidential proxy for AI agents.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
    Residential proxy for AI agents. Pay for gigabytes of traffic and get a proxy login (host, port, username, password) after payment, to use with curl, a browser or any HTTP client. Choose a country, rotate the IP on every connection or keep one with a session tag. A pack lasts 90 days. Pay per pack in stablecoins. Not offered on Solana: pay on Base or Polygon.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: true
Only reads 1Show 1 read-only tool
  • fetchFetch one URL from a residential IP and get the raw response as JSON: status, final URL, headers and body (text or base64), up to 10 MB.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Fetch one URL from a residential IP and get the raw response as JSON: status, final URL, headers and body (text or base64), up to 10 MB. GET, HEAD or POST, your own headers, an optional country. No JavaScript rendering. You pay for the megabytes delivered; a fetch that fails is not charged. Pay per call in stablecoins.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • 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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
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.

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, 19:24 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
https://agproxy.shveik.dev/.well-known/oauth-protected-resource
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.

    Matched text

    https://agproxy.shveik.dev/mcp: tools/list returned 3 tools to an anonymous client, including proxy (write), feedback (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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agproxy https://agproxy.shveik.dev/mcp
claude mcp add --transport http agproxy https://agproxy.shveik.dev/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": [],
    "ask": [
      "mcp__agproxy__proxy",
      "mcp__agproxy__fetch",
      "mcp__agproxy__feedback"
    ],
    "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 agproxy. Review it before you use it.

Capability tags behind 2 rules
  • mcp__agproxy__proxy untrusted-input
  • mcp__agproxy__fetch 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/dev.shveik/agproxy/verify?hash=d49f462508021536505657ac90097f587f9d93569bf006577e7be6ecac92926f" | jq -e '.changed == false'

Pinned hash d49f46250802, from Nov 17, 2026, 08:18 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.shveik/agproxy/changes.xml

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

Badge

Anlyon Radar badge for dev.shveik/agproxy
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.shveik/agproxy.svg)](https://radar.anlyon.com/servers/dev.shveik/agproxy)

Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.

agproxy MCP server: questions and answers

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

Is the agproxy MCP server safe?

No scan can promise that. What its definitions show: 3 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 agproxy MCP server delete data?

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

Can the agproxy 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 agproxy MCP server have?

3 tools: 2 write, 1 read. proxy, feedback and fetch.

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

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

Does the agproxy MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): fetch.

Has the agproxy MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.