# Agent Data Tools: Web, documents and search (remote · agent-data-tools.revmesh2074.workers.dev)

13 tools: web pages, JS apps and PDFs as text, feeds, sitemaps, search. 25 free calls.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: yes
- Last scored: 2026-10-24

## Components

- remote · `agent-data-tools.revmesh2074.workers.dev`: 69/100 (this document), [markdown](https://verifymcp.io/servers/nutshell2000-agent-data-tools-web/mcp-web.md), [page](https://verifymcp.io/servers/nutshell2000-agent-data-tools-web/mcp-web)

## Channel facts

- Endpoint: `https://agent-data-tools.revmesh2074.workers.dev/mcp/web`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.55.0`

## 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**: 69/100
  - 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 enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - 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**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3076 tokens (~236/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 12/100
  - Stability check failed: schema churn in the 5 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 2 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 (15% 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 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 Agent Data Tools: Web, documents and search MCP server?

Agent Data Tools: Web, documents and search is a hosted endpoint at https://agent-data-tools.revmesh2074.workers.dev/mcp/web, 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 nutshell2000-agent-data-tools-web 'https://agent-data-tools.revmesh2074.workers.dev/mcp/web'
```

### Cursor

```json
{
  "mcpServers": {
    "nutshell2000-agent-data-tools-web": {
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/web"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "nutshell2000-agent-data-tools-web": {
      "type": "http",
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/web"
    }
  }
}
```

### Codex

```toml
[mcp_servers.nutshell2000-agent-data-tools-web]
url = "https://agent-data-tools.revmesh2074.workers.dev/mcp/web"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nutshell2000-agent-data-tools-web": {
      "type": "remote",
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/web",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nutshell2000-agent-data-tools-web --url 'https://agent-data-tools.revmesh2074.workers.dev/mcp/web' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  nutshell2000-agent-data-tools-web:
    url: "https://agent-data-tools.revmesh2074.workers.dev/mcp/web"
```

### Netclaw

```json
{
  "McpServers": {
    "nutshell2000-agent-data-tools-web": {
      "Transport": "http",
      "Url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/web"
    }
  }
}
```

### Vellum

```bash
assistant mcp add nutshell2000-agent-data-tools-web -t streamable-http -u 'https://agent-data-tools.revmesh2074.workers.dev/mcp/web'
```

### Other

```json
{
  "mcpServers": {
    "nutshell2000-agent-data-tools-web": {
      "type": "http",
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/web"
    }
  }
}
```

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.

### 2026-10-24 (score 69, 0)

- [security] Tool “feed” rewrote its description, which is the text the model reads
- [functional] Server version: 1.52.0 → 1.55.0
- [cosmetic] Tool “url_meta” changed its title: Link preview metadata for a page → Website metadata, link preview: title, description and images of a page

### 2026-10-23 (score 69, +1)

- [functional] Server version: 1.51.3 → 1.52.0
- [functional] Server version: 1.50.5 → 1.51.3

### 2026-10-22 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “dictionary” rewrote its description, which is the text the model reads
- [security] Tool “feed” rewrote its description, which is the text the model reads
- [security] Tool “papers” rewrote its description, which is the text the model reads
- [security] Tool “url_meta” rewrote its description, which is the text the model reads
- [security] Tool “wikipedia” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 2678 → 3075
- [functional] Server version: 1.50.3 → 1.50.5
- [functional] Server version: 1.50.2 → 1.50.3
- [functional] Server version: 1.50.1 → 1.50.2
- [functional] Server version: 1.49.1 → 1.50.1
- [functional] Server version: 1.48.6 → 1.49.1
- [functional] Server version: 1.48.4 → 1.48.6
- [functional] Server version: 1.48.2 → 1.48.4
- [functional] Server version: 1.48.0 → 1.48.2
- [functional] Server version: 1.47.15 → 1.48.0
- [functional] Server version: 1.47.7 → 1.47.15
- [functional] Server version: 1.45.3 → 1.47.7
- [functional] New tool “news”
- [functional] New tool “search”
- [cosmetic] Tool “extract_rendered” changed its title: Scrape a JavaScript-rendered page as text or Markdown → Web page to Markdown, rendered: a JavaScript-rendered page as text or Markdown
- [cosmetic] Tool “extract” changed its title: Scrape web page to Markdown: page URL into clean Markdown or text for LLMs → Scrape website page to Markdown: page URL into clean Markdown or text for LLMs
- [cosmetic] Tool “dictionary” changed its title: English dictionary lookup → Dictionary definition lookup: English words
- [cosmetic] Tool “extract” changed its title: Web scraping: page URL to clean Markdown or text for LLMs → Scrape web page to Markdown: page URL into clean Markdown or text for LLMs
- [cosmetic] Tool “feed” changed its title: Read an RSS or Atom feed → RSS feed reader: read an RSS or Atom feed
- [cosmetic] Tool “papers” changed its title: Search academic papers → Research papers search: academic papers
- [cosmetic] Tool “sitemap” changed its title: Discover documentation URLs from a bounded XML sitemap → Sitemap URL extractor: documentation URLs from a bounded XML sitemap

### 2026-10-21 (score 68, +1)

- [security] Tool “summarize” rewrote its description, which is the text the model reads
- [security] Tool “sitemap” rewrote its description, which is the text the model reads
- [functional] Server version: 1.45.1 → 1.45.3
- [functional] Server version: 1.45.0 → 1.45.1
- [functional] Server version: 1.44.0 → 1.45.0
- [cosmetic] Tool “extract” changed its title: Web page URL to clean Markdown or text for LLMs → Web scraping: page URL to clean Markdown or text for LLMs
- [cosmetic] Tool “extract_rendered” changed its title: Read a JavaScript-rendered page as text or Markdown → Scrape a JavaScript-rendered page as text or Markdown
- [cosmetic] Tool “screenshot” changed its title: Screenshot of a web page → Website screenshot: capture a web page as an image
- [cosmetic] Tool “summarize” changed its title: Summarize a web page → Summarize a web page from its URL

### 2026-10-20 (score 67, 0)

- [security regression] Stability: unverified → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “extract” rewrote its description, which is the text the model reads
- [security] Tool “extract_rendered” rewrote its description, which is the text the model reads
- [security] Tool “feed” rewrote its description, which is the text the model reads
- [security] Tool “papers” rewrote its description, which is the text the model reads
- [security] Tool “pdf_text” rewrote its description, which is the text the model reads
- [security] Tool “screenshot” rewrote its description, which is the text the model reads
- [security] Tool “sitemap” rewrote its description, which is the text the model reads
- [security] Tool “summarize” rewrote its description, which is the text the model reads
- [security] Tool “wikipedia” rewrote its description, which is the text the model reads
- [functional regression] “screenshot” changed the type of “fullPage”: string → string|number|boolean
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.41.0 → 1.44.0
- [functional] Server version: 1.40.0 → 1.41.0
- [functional] Server version: 1.39.3 → 1.40.0
- [functional] Server version: 1.37.1 → 1.39.3
- [functional] Server version: 1.36.1 → 1.37.1
- [functional] Server version: 1.35.3 → 1.36.1
- [cosmetic] Tool “extract” changed its title: Static web page to text, Markdown, code and tables → Web page URL to clean Markdown or text for LLMs

### 2026-10-19 (score 67)

First indexed and scored.

## MCP tools (13)

### `search` (~189 tokens)

Web search results

Search the web and get the top results as JSON: title, URL, a short snippet and the page age, from the Brave Search API. 1-20 results per call. Results are for the caller's immediate use only: no storing, resale or model training (Brave API terms). Upstream failures and exhausted daily capacity return 503, uncharged. Pair with /extract to read a result in full. Use when an agent needs current information or sources from the open web. Example: q=x402 payment protocol. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `count` (integer): Number of results (1-20, default 10)
- `q` (string, required): Search query, at most 400 characters

### `news` (~210 tokens)

News headlines, latest news: search current news articles (Brave)

Search current news and get the latest headlines as JSON: title, URL, snippet, publisher domain and age, from the Brave Search API's news index. 1-20 results per call; freshness limits results to the past day, week or month. Results are for the caller's immediate use only: no storing, resale or model training (Brave API terms). Upstream failures and exhausted capacity return 503, uncharged. Use when an agent needs current news on a topic. Example: q=bitcoin ETF. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `count` (integer): Number of results (1-20, default 10)
- `freshness` (string): Only articles from the past day, week or month (default: any age)
- `q` (string, required): News search query, at most 400 characters

### `extract` (~306 tokens)

Scrape website page to Markdown: page URL into clean Markdown or text for LLMs

Fetch any public web page URL and get clean, LLM-ready text or Markdown: main content, code blocks, tables, links and headings, for RAG and agent context. Static HTML, Markdown or text; optional section ID. Default 20,000 output characters, max 100,000; input 2 MiB. No JavaScript rendering (see /extract/rendered), logins or paywalls. Empty pages, bad sections, browser challenges and errors are not charged. Use to read docs or articles. Example: url=https://example.com. Price $0.002/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `format` (string): Returned representation: text (default), markdown, or both. HTML structured details are included in every format; Markdown/plain sources have empty details.
- `maxChars` (integer): Maximum characters of body text to return (500-100000, default 20000)
- `section` (string): Optional exact visible HTML ID within primary content, 1-500 characters. Heading scope includes subsections until next same/higher-level heading; section/article/main/div scope is its subtree. Missin…
- `url` (string, required): Absolute http(s) URL of the page to fetch

Output parameters:

- `canonical` (string|null)
- `codeBlocks` (array)
- `contentHash` (string)
- `contentSelection`
- `contentType` (string)
- `description` (string|null)
- `fetchedAt` (string)
- `finalUrl` (string)
- `format`
- `hashFormat`
- `headings` (array)
- `lang` (string|null)
- `linkBaseUrl` (string): Effective source-derived HTTP(S) base for links: the first supported HTML base href outside inert/foreign subtrees, otherwise finalUrl. Credentials and non-HTTP(S) base values are ignored with a warn…
- `links` (array)
- `markdown` (string)
- `section`: Null for full primary-content reading. Otherwise the explicitly requested scope; title/description/canonical remain page-level metadata. Heading scope ends before the next same/higher-level heading,…
- `sourceFormat`: Source interpretation. Markdown is identified by text/markdown, or a .md/.markdown final path served as text/plain (warned). Markdown syntax is retained verbatim within the cap, not converted to HTML…
- `sourceMetadata` (object): Page-level source declarations, not verified authorship or freshness. Head author/Open Graph date tags and bounded direct Schema.org JSON-LD Article/WebPage-like nodes only; exact-URL matches preferr…
- `status` (integer)
- `tables` (array)
- `text` (string)
- `textLength` (integer): Full extracted text length before the character cap, within the input limit.
- `title` (string|null)
- `truncated` (boolean): Input or requested primary representation is incomplete. Structured detail limits are reported separately in warnings.
- `url` (string)
- `warnings` (array)

### `extract_rendered` (~211 tokens)

Web page to Markdown, rendered: a JavaScript-rendered page as text or Markdown

Same output as /extract, but the page is first rendered in a real browser, so single-page apps and pages that build their content with JavaScript come back with their text instead of an empty shell. Waits for the network to settle (up to 15 seconds). Public pages only; no login. Use when /extract returns EXTRACTION_EMPTY or too little text for a page you can read in a browser. Example: url=https://example.com/. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `format` (string): text (default), markdown or both
- `maxChars` (integer): Output limit, 500-100000 characters (default 20000)
- `section` (string): Optional exact HTML id to read only that element
- `url` (string, required): Absolute public http(s) URL of the page

### `pdf_text` (~234 tokens)

PDF to text, page by page

Download a public PDF (up to 10 MB) and return its text page by page, with title, author, page count and character counts. Choose a first page and how many pages to read (up to 200) and cap the output with maxChars. Scanned PDFs without a text layer, encrypted files and non-PDF URLs fail uncharged. Use to read papers, invoices, reports and manuals into an agent's context. Example: url=https://bitcoin.org/bitcoin.pdf. Price $0.005/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `firstPage` (integer): First page to read (default 1)
- `maxChars` (integer): Maximum characters of text returned across all pages (1000-200000, default 50000)
- `pages` (integer): How many pages to read (1-200, default 50)
- `url` (string, required): Absolute public http(s) URL of the PDF

### `sitemap` (~253 tokens)

Sitemap URL extractor: documentation URLs from a bounded XML sitemap

Read one public XML sitemap or sitemap index as structured URLs and source-reported dates. Supports gzip, substring filtering and pagination. Maximum 512 KiB expanded input and 1000 entries. Does not crawl pages or follow child sitemaps. Invalid XML and execution errors are not charged; a valid empty match is charged. Use to find which pages of a docs site to read before calling /extract. Example: url=https://www.sitemaps.org/sitemap.xml. Price $0.002/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `contains` (string): Optional case-insensitive URL substring, at most 200 characters
- `maxUrls` (integer): Reported matching locations examined in one page (1-100, default 25); invalid/nonpublic locations may reduce returned entries
- `offset` (integer): Offset into distinct reported matching locations (0-1000, default 0); use nextOffset to continue
- `url` (string, required): Absolute public HTTP(S) XML sitemap URL; child sitemaps are not fetched automatically

Output parameters:

- `contains` (string)
- `contentHash` (string)
- `duplicateReportedLocations` (integer)
- `entries` (array)
- `fetchedAt` (string)
- `finalUrl` (string)
- `format`
- `hasMore` (boolean)
- `hashFormat`
- `kind`
- `matchingReportedLocations` (integer): Distinct reported locations matching contains, before public-URL validation of the selected page.
- `missingOrInvalidLocations` (integer)
- `nextOffset` (integer|null)
- `offset` (integer)
- `rejectedLocationsInPage` (integer)
- `reportedEntries` (integer)
- `sourceHash` (string)
- `text` (string)
- `uniqueReportedLocations` (integer)
- `url` (string)
- `warnings` (array)

### `summarize` (~174 tokens)

Summarize a web page from its URL

Give a URL, get a short summary of the page plus three to six key points, ready to drop into an agent's context. Fetches the page, strips navigation and boilerplate, and summarizes the main text with an LLM. HTML pages only; for a PDF use pdf_text, then ai_summarize_text. Use for research, news triage, link previews and deciding whether a page is worth reading in full. For the full text use extract. Example: url=https://en.wikipedia.org/wiki/HTTP_402. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `url` (string, required): Absolute http(s) URL of the page to summarize

### `screenshot` (~186 tokens)

Website screenshot: capture a web page as an image

Render any public web page in a real headless Chrome browser, with JavaScript executed, and get a JPEG screenshot (1280 px wide, base64) plus the final URL, HTTP status and page title. Set fullPage=true to capture up to 4000 px of page height. Use for visual checks, page previews, monitoring and feeding pages to vision models. Example: url=https://example.com. Price $0.02/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `fullPage` (string|number|boolean): Set to true to capture the full page height (max 4000 px) instead of the 1280x800 viewport
- `url` (string, required): Absolute http(s) URL of the page to capture

### `papers` (~190 tokens)

Research papers search: academic papers

Search scholarly literature across journals, conferences, preprints and books: title, authors, year, venue, citation count, DOI link and abstract where available. Optional fromYear filter and up to 20 results per call. Use for research agents, literature reviews, fact-checking a claim against published work, and finding the DOI for a citation. Example: query=CRISPR off-target effects. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `fromYear` (integer): Only works published in or after this year
- `limit` (integer): Number of results, 1-20 (default 5)
- `query` (string, required): Search terms, a title or a research question (3-300 characters)

### `feed` (~198 tokens)

RSS feed reader: read an RSS or Atom feed

Read a public RSS 2.0, RSS 1.0 or Atom feed and get the feed title, link and description plus its newest items: title, link, date (ISO 8601), short plain-text summary, author and id. Up to 50 items, feeds up to 2 MB. Lenient with real-world feeds; a page that is not a feed returns 422, uncharged. Use to follow news, blogs, release notes or podcasts without scraping pages. Example: url=https://blog.cloudflare.com/rss/. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `limit` (integer): Items to return (1-50, default 20)
- `url` (string, required): Absolute public http(s) URL of the feed

### `url_meta` (~160 tokens)

Website metadata, link preview: title, description and images of a page

Fetch a public web page's head and return link-preview metadata: title, description, site name, type, preview image, canonical URL, language, author, published time, favicon, theme colour, and every OpenGraph and Twitter-card field. Reads at most 512 KB and never runs JavaScript. Use to build link previews, label citations or check how a URL will unfurl before sharing it. Example: url=https://github.com/. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `url` (string, required): Absolute public http(s) URL of the page

### `wikipedia` (~123 tokens)

Wikipedia summary

Short summary of a Wikipedia article in any language edition: title, one-paragraph extract, description, thumbnail and page URL. Use to ground an agent's answer in a quick, citable fact sheet. Example: title=Stockholm. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `lang` (string): Language code (default en)
- `title` (string, required): Article title

### `dictionary` (~125 tokens)

Dictionary definition lookup: English words

Definitions of an English word from Wiktionary, grouped by part of speech, with example sentences where Wiktionary gives them, plus the page link and the CC BY-SA attribution to show. Use for writing help, vocabulary, translation checks and word games. Example: word=serendipity. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input parameters:

- `word` (string, required): An English word

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/nutshell2000-agent-data-tools-web/mcp-web#diagnostics

## Score history

- 2026-10-24: 69
- 2026-10-23: 69
- 2026-10-22: 68
- 2026-10-21: 68
- 2026-10-20: 67
- 2026-10-19: 67

## Common questions

### What is the Agent Data Tools: Web, documents and search MCP server?

Agent Data Tools: Web, documents and search is an MCP server listed in the public MCP registry as io.github.Nutshell2000/agent-data-tools-web. 13 tools: web pages, JS apps and PDFs as text, feeds, sitemaps, search. 25 free calls. This page covers its hosted endpoint (https://agent-data-tools.revmesh2074.workers.dev/mcp/web). Its publisher has verified ownership with us.

### Is the Agent Data Tools: Web, documents and search MCP server safe to use?

Agent Data Tools: Web, documents and search scores 69 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 Agent Data Tools: Web, documents and search MCP server expose?

Agent Data Tools: Web, documents and search exposes 13 tools: search, news, extract, extract_rendered, pdf_text, and 8 more. Their descriptions and schemas cost roughly 2,559 tokens of context every time the server is loaded.

### Does the Agent Data Tools: Web, documents and search MCP server require authentication?

No. We connected to Agent Data Tools: Web, documents and search without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Data Tools: Web, documents and search MCP server still maintained?

Agent Data Tools: Web, documents and search 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://agent-data-tools.revmesh2074.workers.dev/mcp/web
- Repository: https://github.com/Nutshell2000/agent-data-tools
- Website: https://agent-data-tools.revmesh2074.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/nutshell2000-agent-data-tools-web/mcp-web.xml
- Changelog JSON feed: https://verifymcp.io/servers/nutshell2000-agent-data-tools-web/mcp-web.json
- HTML version of this page: https://verifymcp.io/servers/nutshell2000-agent-data-tools-web/mcp-web