IRI Lab MCP server
ru.agi-iri/iri-labagi-iri.rustreamable-httpv1.0.0Scanned
AI model ratings, Gateway prices in rubles, subscriptions and AI jobs in Russia. Read-only, no key.
6 tools: 6 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 IRI Lab MCP server can do
The IRI Lab MCP server is published by agi-iri.ru, a domain the MCP Registry verified. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (search_subscriptions); 1 tool brings in text other people can write (search_subscriptions).
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.
6 tools
Only reads 6Show 6 read-only tools
get_connection_infoКак подключить IRI Gateway: адрес API, формат ключа, документация, где получить ключ.No findings
Why it is in this group
- The name "get_connection_info" says "get": a word for reading.
Description, as the server wrote it Как подключить IRI Gateway: адрес API, формат ключа, документация, где получить ключ.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_gateway_pricesЦены моделей IRI Gateway в рублях за 1M входных и выходных токенов.No findings
Why it is in this group
- The name "get_gateway_prices" says "get": a word for reading.
Description, as the server wrote it Цены моделей IRI Gateway в рублях за 1M входных и выходных токенов.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_model_ratingРейтинг нейросетей по внешним бенчмаркам LLM Stats: лучшие модели в целом или одного разработчика.No findings
Why it is in this group
- The name "get_model_rating" says "get": a word for reading.
Description, as the server wrote it Рейтинг нейросетей по внешним бенчмаркам LLM Stats: лучшие модели в целом или одного разработчика.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_jobsНайти вакансии в сфере ИИ и машинного обучения в России: роль, компания, город, зарплата и ссылка.No findings
Why it is in this group
- The name "search_jobs" says "search": a word for reading.
Description, as the server wrote it Найти вакансии в сфере ИИ и машинного обучения в России: роль, компания, город, зарплата и ссылка.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_modelsНайти нейросеть по названию или разработчику: место в рейтинге, контекст, цена в IRI Gateway и ссылка на страницу.No findings
Why it is in this group
- The name "search_models" says "search": a word for reading.
Description, as the server wrote it Найти нейросеть по названию или разработчику: место в рейтинге, контекст, цена в IRI Gateway и ссылка на страницу.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_subscriptionsПодписки на ИИ-сервисы с оплатой из России: ChatGPT, Claude, Gemini, Cursor и другие.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search_subscriptions" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it Подписки на ИИ-сервисы с оплатой из России: ChatGPT, Claude, Gemini, Cursor и другие. Цена в рублях и ссылка. Оформляет человек на сайте.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: 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 outbound.
- Reads private data1
- 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.
Looked at Nov 18, 2026, 16:23 UTC, unchanged since Nov 4, 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
- 0
- 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
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 iri-lab https://agi-iri.ru/mcpclaude mcp add --transport http iri-lab https://agi-iri.ru/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__iri-lab__search_models",
"mcp__iri-lab__get_model_rating",
"mcp__iri-lab__get_gateway_prices",
"mcp__iri-lab__search_subscriptions",
"mcp__iri-lab__search_jobs",
"mcp__iri-lab__get_connection_info"
],
"ask": [],
"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 iri-lab. Review it before you use it.
Capability tags behind 1 rule
- mcp__iri-lab__search_subscriptions 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://radar.anlyon.com/api/v1/servers/ru.agi-iri/iri-lab/verify?hash=8e3287bc6b24e1f7acedc918aa77c18da004629206a124f0a28269c1dc63b1d6" | jq -e '.changed == false'Pinned hash 8e3287bc6b24, from Nov 17, 2026, 14:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ru.agi-iri/iri-lab/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ru.agi-iri/iri-lab)Source: MCP Registry. Synced Nov 3, 2026, 23:18 UTC.
IRI Lab MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the IRI Lab MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the IRI Lab MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the IRI Lab 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 IRI Lab MCP server have?
- 6 tools: 6 read. search_models, get_model_rating, get_gateway_prices, search_subscriptions, search_jobs and get_connection_info.
Does the IRI Lab MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the IRI Lab MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the IRI Lab MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.