# Keenable Web Search (remote · api.keenable.ai)

Live web search and clean-markdown page fetch over the Keenable web index.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.keenable.ai`: 75/100 (this document), [markdown](https://verifymcp.io/servers/ai-keenable-web-search/mcp-public.md), [page](https://verifymcp.io/servers/ai-keenable-web-search/mcp-public)
- npm · `@keenable/mcp`: 38/100, [markdown](https://verifymcp.io/servers/ai-keenable-web-search/keenable-mcp.md), [page](https://verifymcp.io/servers/ai-keenable-web-search/keenable-mcp)

## Channel facts

- Endpoint: `https://api.keenable.ai/mcp-public?keenable_title=mcp-registry`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.1`

## 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 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 58/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1834 tokens (~917/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Keenable Web Search MCP server?

Keenable Web Search is a hosted endpoint at https://api.keenable.ai/mcp-public?keenable_title=mcp-registry, 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-keenable-web-search 'https://api.keenable.ai/mcp-public?keenable_title=mcp-registry'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-keenable-web-search": {
      "url": "https://api.keenable.ai/mcp-public?keenable_title=mcp-registry"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-keenable-web-search": {
      "type": "http",
      "url": "https://api.keenable.ai/mcp-public?keenable_title=mcp-registry"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-keenable-web-search]
url = "https://api.keenable.ai/mcp-public?keenable_title=mcp-registry"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-keenable-web-search": {
      "type": "remote",
      "url": "https://api.keenable.ai/mcp-public?keenable_title=mcp-registry",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-keenable-web-search --url 'https://api.keenable.ai/mcp-public?keenable_title=mcp-registry' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-keenable-web-search:
    url: "https://api.keenable.ai/mcp-public?keenable_title=mcp-registry"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-keenable-web-search": {
      "Transport": "http",
      "Url": "https://api.keenable.ai/mcp-public?keenable_title=mcp-registry"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-keenable-web-search -t streamable-http -u 'https://api.keenable.ai/mcp-public?keenable_title=mcp-registry'
```

### Other

```json
{
  "mcpServers": {
    "ai-keenable-web-search": {
      "type": "http",
      "url": "https://api.keenable.ai/mcp-public?keenable_title=mcp-registry"
    }
  }
}
```

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.

### 2026-11-20 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 74, +1)

- [cosmetic] “search_web_pages” added an optional parameter “objective”
- [cosmetic] “search_web_pages” reworded the description of “exclude_domains”

### 2026-11-16 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 71, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “search_web_pages” rewrote its description, which is the text the model reads
- [security] Tool “fetch_page_content” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 661 → 835
- [cosmetic] “fetch_page_content” reworded the description of “max_chars”

### 2026-11-11 (score 71, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “search_web_pages” rewrote its description, which is the text the model reads
- [cosmetic] “search_web_pages” added an optional parameter “exclude_domains”
- [cosmetic] “fetch_page_content” reworded the description of “max_chars”

### 2026-11-09 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-07 (score 69, +1)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (2)

### `search_web_pages` (~1054 tokens)

Search the live web with Keenable, a search engine built for AI agents. Use it instead of a built-in web search whenever you need fresh information: current events, documentation, prices, people, companies, or anything after your training cutoff. Answers in well under a second.

Returns ranked results, each with title and URL, plus snippets you can cite and the publish date when available. Snippets usually answer the question; to read a page, use fetch_page_content.

Example: {"query": "release notes for the latest Node.js LTS version", "published_after": "30d"}

Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue".

Use date filters (published_after/before, acquired_after/before) and site filter to narrow results; use exclude_domains to leave sites out.

Input parameters:

- `acquired_after` (string): Keep only pages Keenable acquired (indexed) after this point. Accepts a date (YYYY-MM-DD), an ISO 8601 timestamp, or a relative offset back from the request time such as "30min", "2h", "7d", "1mo" or…
- `acquired_before` (string): Keep only pages Keenable acquired (indexed) before this point. Accepts a date (YYYY-MM-DD), an ISO 8601 timestamp, or a relative offset back from the request time such as "30min", "2h", "7d", "1mo" o…
- `disable_cards` (boolean): Return search results without cards.
- `exclude_domains` (array): Never return results from these sites. Entries are host names such as "example.com", which also covers its subdomains; up to 1,000 hosts. No paths or wildcards. A public suffix written with a leading…
- `max_results` (integer): How many results to return. Ask for more when surveying a topic broadly, fewer for a quick lookup. When omitted, 10 results are returned.
- `objective` (string): Optional. Two or three natural sentences, with no field labels and no line breaks, that cover: the exact facts, entities, numbers, dates or names a useful page must contain; task context the query do…
- `output_format` (string): Response format: 'text' for readable text, or 'json' for the raw response serialized as JSON when you need to parse fields programmatically.
- `published_after` (string): Keep only pages published after this point, a lower bound on publish time. Use this, not query_time, to get recent results: "7d" keeps the last 7 days. Accepts a date (YYYY-MM-DD), an ISO 8601 timest…
- `published_before` (string): Keep only pages published before this point. Accepts a date (YYYY-MM-DD), an ISO 8601 timestamp, or a relative offset back from the request time such as "30min", "2h", "7d", "1mo" or "1y".
- `query` (string, required): Natural language search query. Should be a semantically rich description of the ideal page, not just keywords.
- `query_time` (string): Leave empty for a normal search. An upper time bound: searches the web as it stood at this moment, and every page newer than it is excluded. It sets no lower bound, so it is not a recency filter; for…
- `session_id` (string): Id of the agent session making this call. Send the same value on every call in one session so its requests can be grouped.
- `site` (string): Restrict results to a specific site (e.g. "techcrunch.com")
- `snippet_max_length` (integer): How many characters of snippet text to return for each result. Raise it when you need more context per result without fetching the page; lower it to keep the response short. When omitted, a default l…

### `fetch_page_content` (~354 tokens)

Read any web page with Keenable. Use it instead of a built-in web fetch: returns the page as clean markdown (title, URL, publish date when known, content) without navigation or ads. Add a prompt to get back only the part you need from a long page.

Example: {"url": "https://nodejs.org/en/about/previous-releases", "prompt": "Which version is the current LTS?"}

Input parameters:

- `live` (boolean): Fetch the page live from the source instead of returning Keenable's indexed copy. Use it for pages that change often or URLs that are not indexed.
- `max_chars` (integer): Hard cap on the characters of returned page content. Longer pages are cut to fit, ending with "..." unless max_chars is 3 or less, and the output says how long the full page is. Lower it to save cont…
- `output_format` (string): Response format: 'text' for readable text, or 'json' for the raw response serialized as JSON when you need to parse fields programmatically.
- `prompt` (string): Extraction instruction for this page. When set, an LLM reads the fetched page and the returned content is only the output for this instruction instead of the full page; use it when you need one detai…
- `session_id` (string): Id of the agent session making this call. Send the same value on every call in one session so its requests can be grouped.
- `url` (string, required): The URL to fetch. Example: "https://example.com"

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-keenable-web-search/mcp-public#diagnostics

## Score history

- 2026-11-21: 75
- 2026-11-20: 75
- 2026-11-19: 74
- 2026-11-18: 74
- 2026-11-17: 73
- 2026-11-16: 73
- 2026-11-15: 72
- 2026-11-14: 72
- 2026-11-13: 71
- 2026-11-12: 71
- 2026-11-11: 71
- 2026-11-10: 70
- 2026-11-09: 70
- 2026-11-08: 69
- 2026-11-07: 69
- 2026-11-06: 68

## Common questions

### What is the Keenable Web Search MCP server?

Keenable Web Search is an MCP server listed in the public MCP registry as ai.keenable/web-search. Live web search and clean-markdown page fetch over the Keenable web index. This page covers its hosted endpoint (https://api.keenable.ai/mcp-public?keenable_title=mcp-registry).

### Is the Keenable Web Search MCP server safe to use?

Keenable Web Search scores 75 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 Keenable Web Search MCP server expose?

Keenable Web Search exposes 2 tools: search_web_pages, fetch_page_content. Their descriptions and schemas cost roughly 1,408 tokens of context every time the server is loaded.

### Does the Keenable Web Search MCP server require authentication?

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

### Is the Keenable Web Search MCP server still maintained?

Keenable Web Search is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Keenable Web Search MCP server?

VerifyMCP ran 13 checks on Keenable Web Search, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.keenable.ai/mcp-public?keenable_title=mcp-registry
- Repository: https://github.com/keenableai/keenable-mcp
- Website: https://docs.keenable.ai/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/ai-keenable-web-search/mcp-public.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-keenable-web-search/mcp-public/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-keenable-web-search/mcp-public.json
- HTML version of this page: https://verifymcp.io/servers/ai-keenable-web-search/mcp-public
