# Iskat — Russian-language web search for agents (remote · iskat.io)

Russian-language web search for agents: hybrid retrieval, product prices, full page text

- Trust score: 25/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- remote · `iskat.io`: 25/100 (this document), [markdown](https://verifymcp.io/servers/io-iskat-webdex/iskat.md), [page](https://verifymcp.io/servers/io-iskat-webdex/iskat)

## Channel facts

- Endpoint: `https://iskat.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint returned HTTP 502.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Iskat — Russian-language web search for agents MCP server?

Iskat — Russian-language web search for agents is a hosted endpoint at https://iskat.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-iskat-webdex 'https://iskat.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-iskat-webdex": {
      "url": "https://iskat.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-iskat-webdex": {
      "type": "http",
      "url": "https://iskat.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-iskat-webdex]
url = "https://iskat.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-iskat-webdex": {
      "type": "remote",
      "url": "https://iskat.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-iskat-webdex --url 'https://iskat.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-iskat-webdex:
    url: "https://iskat.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-iskat-webdex": {
      "Transport": "http",
      "Url": "https://iskat.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-iskat-webdex -t streamable-http -u 'https://iskat.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-iskat-webdex": {
      "type": "http",
      "url": "https://iskat.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 25, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-25 (score 25, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-21 (score 25)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.60 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Authorization: fail → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Schema quality: Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.

### 2026-09-03 (score 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-02 (score 0)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 65
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 0

### 2026-08-28 (score 0)

First indexed and scored.

## MCP tools (14)

### `search` (~291 tokens)

Search the web index

Search the Webdex index of crawled websites. Combines keyword (BM25) and semantic (vector) retrieval. Supports "quoted phrases" for exact matches and -term to exclude a term. Works across languages: a query in one language can retrieve pages written in another.

Input parameters:

- `category` (string): Restrict to a task category, e.g. "news", "legal", "forum-it". See list_sites.
- `expand` (boolean): Widen the query with synonyms and acronym expansions (грм → газораспределительный механизм, НДФЛ → налог на доходы). On by default; set false for an exact-terms search. The terms actually added come…
- `lang` (string): Restrict to a two-letter language code, e.g. "ru".
- `limit` (integer): Maximum number of results.
- `mode` (string): hybrid = both arms fused (best general choice); keyword = exact terms only, for names, codes and error strings; semantic = meaning-based, for vague or descriptive questions.
- `offset` (integer): Skip this many results — for a second page.
- `query` (string, required): The search query.
- `sinceDays` (integer): Only pages published within this many days. Use for anything time-sensitive.
- `site` (string): Restrict to one host, e.g. "example.com".

### `search_products` (~294 tokens)

Find products with prices

Search shop catalogues by name and specification, filter by price and availability, and sort by price. Use this rather than `search` whenever the question is what something costs or where to buy it: `search` returns pages that mention a product, this returns the offer itself — price, stock, specifications and a link straight to the product page. Specifications are searchable, so a query like "ноутбук 16 гб 512 ссд" or "холодильник samsung no frost" matches on capacity and features, not just the model name. Coverage is whatever has been crawled: an exact model, colour and size that no indexed shop stocks returns nothing rather than the wrong colour — an empty result means not indexed, not nonexistent.

Input parameters:

- `best_per_product` (boolean): Collapse the same product across shops to its cheapest offer.
- `in_stock` (boolean): Only offers the shop states are in stock. Off by default: many shops never say.
- `limit` (integer)
- `max_price` (number): Upper bound.
- `min_price` (number): Lower bound, in the shop's currency.
- `query` (string, required): What to find, in words a shopper would use.
- `shop` (string): Restrict to one shop by host, e.g. citilink.ru.
- `sort` (string)
- `vendor` (string): Manufacturer, exact match.

### `fetch_page` (~79 tokens)

Read an indexed page

Return the full extracted text of a page already in the index. This serves stored content and does not hit the live site, so it is fast and cannot be blocked. Use it after search to read a result.

Input parameters:

- `maxChars` (integer): Truncate the body to this many characters.
- `url` (string, required): URL of an indexed page.

### `fetch_pages` (~94 tokens)

Read several indexed pages at once

Like fetch_page but for up to 20 URLs in one call — the bulk-read counterpart to search_batch, so reading a page of results is one round trip instead of ten. Each page comes back with its cleaned text from the index; URLs not in the index are marked, not fatal.

Input parameters:

- `maxChars` (integer): Truncate each body to this many characters.
- `urls` (array, required): URLs of indexed pages.

### `find_similar` (~49 tokens)

Find pages similar to a page

Given an indexed URL, return other indexed pages with similar content, compared by meaning rather than shared keywords.

Input parameters:

- `limit` (integer)
- `url` (string, required): URL of an indexed page.

### `search_batch` (~86 tokens)

Run several searches at once

Execute up to 10 queries in one call. Answering a real question usually takes several related searches, and doing them one at a time spends a round trip on each; this runs them together and returns the results grouped by query.

Input parameters:

- `category` (string)
- `lang` (string)
- `limit` (integer): Results per query.
- `queries` (array, required)

### `find_passages` (~86 tokens)

Get quotable passages, not just links

Return the specific passages that answer a question, each with the URL and title it came from. Use this when you intend to cite or summarise rather than browse: it skips the step of fetching pages and hunting for the relevant paragraph, and the attribution is exact.

Input parameters:

- `category` (string)
- `limit` (integer): Number of passages.
- `query` (string, required)

### `source_profile` (~106 tokens)

What kind of source is this

Describe a site in the index: what type of source it is (official, media, reference, forum, shop), how much of it we hold, how trusted it is by the link graph, and how fresh the copy is.

Use this before relying on a result. A ministry's own page and a forum post repeating it are both 'a URL', and the difference decides how much weight the claim deserves.

Input parameters:

- `host` (string, required): Domain, e.g. cbr.ru

### `watch_query` (~96 tokens)

Track a query for new results

Save a query and later ask what has appeared since you last checked. Pull-based: nothing is pushed to you, you call check_watch when you want to know — which fits an agent that runs on its own schedule.

Use for monitoring: a topic, a competitor, a regulation, a product.

Input parameters:

- `category` (string)
- `label` (string)
- `lang` (string)
- `query` (string, required)

### `check_watch` (~61 tokens)

What is new for a tracked query

Return pages matching a watched query that were indexed since the last check, then advance the cursor. Call with no id to check all of your watches at once.

Input parameters:

- `id` (integer): Watch id; omit to check all.
- `limit` (integer)

### `list_watches` (~22 tokens)

List tracked queries

Show the queries you are watching and when each was last checked.

### `delete_watch` (~69 tokens)

Stop tracking a query

Remove a watch. Pass its id (from list_watches) or the exact query text. Watches accumulated with no way to remove them; this closes that.

Input parameters:

- `id` (integer): Watch id from list_watches.
- `query` (string): Exact watched query, as an alternative to id.

### `list_sites` (~58 tokens)

List indexed sites

Show which sites the index covers, with page counts. Use this to understand coverage before concluding that something is missing.

Input parameters:

- `limit` (integer)
- `search` (string): Filter by substring of the host.
- `status` (string)

### `index_stats` (~23 tokens)

Index statistics

Size and freshness of the corpus: sites, pages, passages, languages.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-iskat-webdex/iskat#diagnostics

## Score history

- 2026-10-24: 25
- 2026-10-23: 25
- 2026-10-22: 25
- 2026-10-21: 25
- 2026-10-20: 25
- 2026-10-19: 25
- 2026-10-18: 25
- 2026-10-17: 25
- 2026-10-16: 25
- 2026-10-15: 25
- 2026-10-14: 25
- 2026-10-13: 25
- 2026-10-12: 25
- 2026-10-10: 25
- 2026-10-07: 25
- 2026-10-05: 25
- 2026-10-04: 25
- 2026-10-03: 25
- 2026-10-02: 25
- 2026-10-01: 25
- 2026-09-30: 25
- 2026-09-29: 25
- 2026-09-28: 25
- 2026-09-27: 25
- 2026-09-26: 25
- 2026-09-25: 25
- 2026-09-24: 25
- 2026-09-23: 25
- 2026-09-22: 25
- 2026-09-21: 25

## Common questions

### What is the Iskat — Russian-language web search for agents MCP server?

Iskat — Russian-language web search for agents is an MCP server listed in the public MCP registry as io.iskat/webdex. Russian-language web search for agents: hybrid retrieval, product prices, full page text. This page covers its hosted endpoint (https://iskat.io/mcp).

### Is the Iskat — Russian-language web search for agents MCP server safe to use?

Iskat — Russian-language web search for agents scores 25 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Iskat — Russian-language web search for agents MCP server expose?

Iskat — Russian-language web search for agents exposes 14 tools: search, search_products, fetch_page, fetch_pages, find_similar, and 9 more. Their descriptions and schemas cost roughly 1,414 tokens of context every time the server is loaded.

### Does the Iskat — Russian-language web search for agents MCP server require authentication?

Its publisher declares no required credentials for Iskat — Russian-language web search for agents. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the Iskat — Russian-language web search for agents MCP server still maintained?

Iskat — Russian-language web search for agents is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://iskat.io/mcp
- Website: https://iskat.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-iskat-webdex/iskat.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-iskat-webdex/iskat.json
- HTML version of this page: https://verifymcp.io/servers/io-iskat-webdex/iskat