Skip to content
anlyon.devby Anlyon

Rinat Sultanov — Agent Lab

com.rinatsultan/agent-labrinatsultan.comstreamable-httpv1.1.0Scanned

Public profile, manufacturing AI cases and read-only agent protocol reference.

6 tools: 2 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 2 write, 4 read.
  • Reads private data · 2
  • Reads text others write · 1
  • Can send data out · 0
  • No findings

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 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 →
Compare with similar serversMarkdownJSONReport this listing

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
  • explore_manufacturing_pilotsInteractive MCP App showing three preliminary industrial AI pilots, their input data, KPIs and human approval boundaries; no model calls or operational changes.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
    Interactive MCP App showing three preliminary industrial AI pilots, their input data, KPIs and human approval boundaries; no model calls or operational changes.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • request_contactPass a company inquiry to Rinat.No findings

    Why it is in this group

    • The name "request_contact" says "request": a word for a change.
    Description, as the server wrote it
    Pass a company inquiry to Rinat. Delivered to his Telegram. Use when an agent acts on behalf of a company interested in working together.
Only reads 4Show 4 read-only tools
  • get_agent_protocol_catalogRead 16 source-backed protocol explanations and the implementation status on rinatsultan.com.No findings

    Why it is in this group

    • The name "get_agent_protocol_catalog" says "get": a word for reading.
    Description, as the server wrote it
    Read 16 source-backed protocol explanations and the implementation status on rinatsultan.com. Opens a read-only MCP App in compatible hosts. No payments, external fetches or operational actions.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • get_case_studyMeasured results of the AI outbound sales agent: emails sent, hours replaced, replies, price requests, and what the agent does not do.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_case_study" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "email": it reads mail.
    • untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Measured results of the AI outbound sales agent: emails sent, hours replaced, replies, price requests, and what the agent does not do.
  • get_profileRole, positioning, background, work formats and contact.Reads private dataNo findings

    Why it is in this group

    • The name "get_profile" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "contact": it reads contacts.
    Description, as the server wrote it
    Role, positioning, background, work formats and contact. Canonical facts about the person.
  • search_public_ai_pagesRead-only, deterministic lookup of publicly available pages on rinatsultan.com.No findings

    Why it is in this group

    • The name "search_public_ai_pages" says "search": a word for reading.
    Description, as the server wrote it
    Read-only, deterministic lookup of publicly available pages on rinatsultan.com. Results are website sources, not a generated answer.

    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 outbound.

Reads private data2
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.

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.

All changes to this server

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-lab https://rinatsultan.com/mcp
claude mcp add --transport http agent-lab https://rinatsultan.com/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__agent-lab__get_profile",
      "mcp__agent-lab__get_case_study",
      "mcp__agent-lab__search_public_ai_pages",
      "mcp__agent-lab__get_agent_protocol_catalog"
    ],
    "ask": [
      "mcp__agent-lab__request_contact",
      "mcp__agent-lab__explore_manufacturing_pilots"
    ],
    "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 agent-lab. Review it before you use it.

Capability tags behind 2 rules
  • mcp__agent-lab__get_profile private-data
  • mcp__agent-lab__get_case_study private-data, 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://anlyon.dev/api/v1/servers/com.rinatsultan/agent-lab/verify?hash=9e6d9f32af8d1eb9493b48d065d5e5abb04801b4f9be95fe2ba1f9a51699dc93" | jq -e '.changed == false'

Pinned hash 9e6d9f32af8d, from Nov 4, 2026, 21:18 UTC.

Watch

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

https://anlyon.dev/servers/com.rinatsultan/agent-lab/changes.xml

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

Badge

anlyon.dev badge for com.rinatsultan/agent-lab
[![anlyon.dev](https://anlyon.dev/badge/com.rinatsultan/agent-lab.svg)](https://anlyon.dev/servers/com.rinatsultan/agent-lab)

Source: MCP Registry. Synced Nov 4, 2026, 22:17 UTC.