# typesearch (remote · api.typesearch.ai)

News search for AI agents: recent news on any topic from outlets worldwide, by country and language.

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `api.typesearch.ai`: 71/100 (this document), [markdown](https://verifymcp.io/servers/ai-typesearch-news/api.md), [page](https://verifymcp.io/servers/ai-typesearch-news/api)

## Channel facts

- Endpoint: `https://api.typesearch.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## 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 2026-09-28.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1699 tokens (~424/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 3 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 1 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the typesearch MCP server?

typesearch is a hosted endpoint at https://api.typesearch.ai/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 ai-typesearch-news 'https://api.typesearch.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-typesearch-news": {
      "url": "https://api.typesearch.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-typesearch-news": {
      "type": "http",
      "url": "https://api.typesearch.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-typesearch-news]
url = "https://api.typesearch.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-typesearch-news": {
      "type": "remote",
      "url": "https://api.typesearch.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-typesearch-news --url 'https://api.typesearch.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-typesearch-news:
    url: "https://api.typesearch.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-typesearch-news": {
      "Transport": "http",
      "Url": "https://api.typesearch.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-typesearch-news -t streamable-http -u 'https://api.typesearch.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-typesearch-news": {
      "type": "http",
      "url": "https://api.typesearch.ai/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 71, +7)

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

### 2026-09-27 (score 64, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 317 → 424
- [functional] New tool “create_chart”
- [cosmetic] “search_news” added an optional parameter “index”

### 2026-09-26 (score 65, 0)

- [security regression] Stability: unverified → fail
- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [security regression] Tool “check_coverage” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 261 → 317

### 2026-09-25 (score 65)

First indexed and scored.

## MCP tools (4)

### `search_news` (~481 tokens)

Search news

Search recent news on any topic across a curated index of news outlets worldwide, judged by a relevance model. Returns the matching articles: title, link, source, date, country and language, standfirst, and short excerpts in the modes that read. Use it for current events and for what outlets reported about a company, person, place or topic. Defaults: mode "fast" (US$1.40 per 1,000 searches) and the last 7 days; mode "ultra" judges headlines only, for US$1.00.

Input parameters:

- `countries` (array): Only sources from these countries: ISO 3166-1 alpha-2 codes, such as ["AR"] or ["US", "GB"].
- `days` (integer): Only the last N days, 1 to 365. Defaults to 7 unless published_after or published_before are given.
- `exclude_domains` (array): Never these domains or paths.
- `include_domains` (array): Only these domains or paths, such as example.com or example.com/sports.
- `index` (string): Optional: search your own custom index (its id, idx_…) instead of the news index: your own list of URLs, sitemap or feed, created at https://app.typesearch.ai/indexes or with POST /v1/indexes. Same m…
- `languages` (array): Only sources that publish in these languages: ISO 639-1 codes, such as ["es"] or ["en", "pt"].
- `max_results` (integer): How many results, 1 to 25. Defaults to 10.
- `mode` (string): fast (default): headlines and standfirsts · ultra (cheapest): headlines only · normal: also reads the best matches · deep: reads more, finds the topic in other words too.
- `published_after`: Published on or after this date: 2026-09-25, or a date-time with offset.
- `published_before`: Published on or before this date; a bare date includes that whole day.
- `query` (string, required): What to look for, in any language: a topic, event, person, company or place, such as "inflation in Argentina" or "OpenAI funding".

Output parameters:

- `cached` (boolean)
- `cost_usd` (number)
- `incomplete` (boolean): The time or token budget ran out: there may be more.
- `mode` (string)
- `near_misses` (array): Only when nothing matched: the closest articles, which may not be about it.
- `query` (string)
- `request_id` (string)
- `results` (array)
- `warnings` (array)

### `get_contents` (~140 tokens)

Get article contents

Get the title, standfirst, date, source and a short verbatim excerpt (up to 25 words) of up to 10 news article URLs. With a query, the excerpt is the one about it and relevance says how much the article covers it. Never returns the full text. US$0.20 per 1,000 pages read (US$0.40 with a query); pages that fail are free.

Input parameters:

- `query` (string): Optional: the excerpt is then the one about this query, with a relevance score.
- `urls` (array, required): Up to 10 article URLs, such as https://example.com/news/article.

Output parameters:

- `cost_usd` (number)
- `request_id` (string)
- `results` (array)

### `find_similar` (~117 tokens)

Find similar news

Find other news articles about the same story as a given article URL, across the index (the last 7 days by default). Useful to see how other outlets covered a story. US$2.20 per 1,000 calls.

Input parameters:

- `days` (integer): Only the last N days, 1 to 365. Defaults to 7.
- `max_results` (integer): How many results, 1 to 25. Defaults to 10.
- `url` (string, required): The article URL whose story to find elsewhere.

Output parameters:

- `cached` (boolean)
- `cost_usd` (number)
- `incomplete` (boolean): The time or token budget ran out: there may be more.
- `mode` (string)
- `near_misses` (array): Only when nothing matched: the closest articles, which may not be about it.
- `reference` (object)
- `request_id` (string)
- `results` (array)
- `warnings` (array)

### `create_chart` (~536 tokens)

Create a chart

Turn a question into a chart card, without thinking about chart types: the standings of the latest race, poll or election results by candidate, wins in a season, coverage over time, share of voice between names, tone, the outlets that cover a topic most, what an outlet published, a timeline of a story, the figures the articles publish (a price, a rate), or data from a custom index. It works out what the user expects (`understood`, with other readings to pass as `interpretation`), verifies every value against its source, picks the chart, the key figures and a title that states the finding, and returns an image URL (show it to the user) and an embed URL. If the exact data is not published it shows the closest thing and says so (`rung`, warnings). It costs its search (the mode it needs, per query) plus US$0.50 per 1,000 charts; the same request within 10 minutes is free.

Input parameters:

- `compare` (array): What to compare, 2 to 5, if the query does not say it with "vs": ["Milei", "Bullrich"].
- `countries` (array): Only sources from these countries: ISO 3166-1 alpha-2 codes, such as ["AR"] or ["US", "GB"].
- `days` (integer): Only the last N days, 1 to 365. By default it depends on the chart: 30 for coverage, 7 for figures.
- `index` (string): Optional: chart your own custom index (idx_…) instead of the news: prices, ratings, availability, brands.
- `interpretation` (string): Optional: one of the `alternatives` of a previous call, to chart that reading of the query instead.
- `languages` (array): Only sources that publish in these languages: ISO 639-1 codes, such as ["es"] or ["en", "pt"].
- `query` (string, required): What to chart, in plain words and any language: "blue dollar this week", "Milei vs Bullrich coverage", "tone of the IMF coverage", "which outlets cover lithium", or "prices" with index.
- `theme` (string): light (default), dark, editorial (warm paper) or electric (deep blue).
- `type` (string): auto (default) picks the chart that tells the data best. Or force one: line, area, bar, bar_horizontal, stacked_bar, pie, donut, scatter, funnel, timeline, kpi, table.

Output parameters:

- `alternatives` (array): Other readings of the query: pass one as `interpretation` to chart it instead.
- `cached` (boolean)
- `cost_usd` (number)
- `data` (array): The values drawn (up to 40 per series).
- `embed_url` (string): An iframe for a web page or app.
- `events` (array)
- `id` (string)
- `image_url` (string): PNG: show it to the user.
- `improving` (boolean): Still looking for the exact data: the image and embed update themselves if it arrives.
- `key_figures` (array)
- `request_id` (string)
- `rung` (string): exact (the data asked for), partial (a verified part), related, coverage or stories (the closest thing found).
- `sources` (array)
- `subtitle` (string)
- `table` (array): The rows of a table chart (up to 10), keyed by column label.
- `title` (string): It states the finding.
- `type` (string)
- `understood` (string): What we understood the user expects to see.
- `warnings` (array)

## Diagnostics

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

## Score history

- 2026-09-28: 71
- 2026-09-27: 64
- 2026-09-26: 65
- 2026-09-25: 65

## Common questions

### What is the typesearch MCP server?

typesearch is an MCP server listed in the public MCP registry as ai.typesearch/news. News search for AI agents: recent news on any topic from outlets worldwide, by country and language. This page covers its hosted endpoint (https://api.typesearch.ai/mcp).

### Is the typesearch MCP server safe to use?

typesearch scores 71 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 typesearch MCP server expose?

typesearch exposes 4 tools: search_news, get_contents, find_similar, create_chart. Their descriptions and schemas cost roughly 1,274 tokens of context every time the server is loaded.

### Does the typesearch MCP server require authentication?

No. We connected to typesearch without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the typesearch MCP server still maintained?

typesearch is still listed as active in the MCP registry. We last reached this channel on 28 September 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://api.typesearch.ai/mcp
- Authorisation metadata: https://api.typesearch.ai/.well-known/oauth-protected-resource/mcp
- Website: https://typesearch.ai/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-typesearch-news/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-typesearch-news/api.json
- HTML version of this page: https://verifymcp.io/servers/ai-typesearch-news/api