# Ujeebu (remote · mcp.ujeebu.com)

Web scraping, Google SERP, Markdown and ChatGPT/Gemini answers as typed tools for AI agents.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `mcp.ujeebu.com`: 63/100 (this document), [markdown](https://verifymcp.io/servers/com-ujeebu-mcp/mcp.md), [page](https://verifymcp.io/servers/com-ujeebu-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.ujeebu.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-10-17.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (ujeebu_account).
  - 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**: 57/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4379 tokens (~257/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 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 17 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 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 Ujeebu MCP server?

Ujeebu is a hosted endpoint at https://mcp.ujeebu.com/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 com-ujeebu-mcp 'https://mcp.ujeebu.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-ujeebu-mcp": {
      "url": "https://mcp.ujeebu.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-ujeebu-mcp": {
      "type": "http",
      "url": "https://mcp.ujeebu.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-ujeebu-mcp]
url = "https://mcp.ujeebu.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-ujeebu-mcp --url 'https://mcp.ujeebu.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-ujeebu-mcp:
    url: "https://mcp.ujeebu.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-ujeebu-mcp": {
      "Transport": "http",
      "Url": "https://mcp.ujeebu.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-ujeebu-mcp -t streamable-http -u 'https://mcp.ujeebu.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-ujeebu-mcp": {
      "type": "http",
      "url": "https://mcp.ujeebu.com/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.

### 2026-10-16 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 61, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-12 (score 61)

First indexed and scored.

## MCP tools (17)

### `ujeebu_account` (~35 tokens)

Get account usage information including balance, quota, requests used, and billing details. Rate limited to 10 calls per minute.

### `ujeebu_buy` (~236 tokens)

Buy a credit top-up or upgrade the plan directly, charging the account's saved card. Requires an API key. This charges the saved card only if the human enabled agent purchases and set a monthly cap in the Ujeebu dashboard (Billing); agent purchases are off by default. Otherwise (purchases disabled, no saved card, over the monthly cap, card declined, or extra verification required) it returns an error with a checkout_url: hand that link to your human instead. Never retry a declined charge in a loop. Check ujeebu_plans first for prices and the remaining monthly cap. Downgrades and cancellations are not possible via agents.

Input parameters:

- `interval` (string): Billing interval for kind=plan only. Default: month. Ignored for top-ups.
- `item` (string, required): Id of the top-up or plan, as listed by ujeebu_plans (e.g. 'mini' for a top-up, 'starter' for a plan).
- `kind` (string, required): 'topup' for a one-off credit pack (credits never expire) or 'plan' for a subscription upgrade.

### `ujeebu_card` (~255 tokens)

Fast article preview extraction using meta tags. Returns title, summary, author, dates, image, and site info. Much faster than full extraction.

Input parameters:

- `auto_proxy` (boolean): Auto-escalate to better proxy on failure. Default: false
- `custom_proxy` (string): Custom proxy URI: scheme://user:pass@host:port (required if proxy_type='custom')
- `js` (string): Execute JavaScript: 'true', 'false', or 'auto' (let extractor decide). Default: 'false'
- `js_timeout` (number): JS engine timeout when js=true (seconds). Default: 60
- `proxy_country` (string): ISO 3166-1 alpha-2 country code for premium proxy. Default: 'US'
- `proxy_type` (string): Proxy type: 'rotating', 'advanced', 'premium', 'residential', 'custom'. Default: 'rotating'
- `session_id` (string): Session ID (1-16 alphanumeric chars) to route through same proxy. Active 30 min
- `timeout` (number): Request timeout in seconds. Default: 60
- `url` (string, required): URL of article to preview

### `ujeebu_chatgpt` (~74 tokens)

Fetch a URL and ask ChatGPT about it. Ujeebu loads the page, sends it to ChatGPT with your prompt, and returns the model's reply.

Input parameters:

- `prompt` (string, required): Question or instruction for ChatGPT about the page
- `url` (string, required): URL of the page to analyze

### `ujeebu_checkout_link` (~176 tokens)

Create a Stripe checkout link for a credit top-up or a plan upgrade. Requires an API key. Nothing is charged: give the checkout_url to your human, who pays on Stripe's page; credits or the new plan are applied automatically after payment. Only upgrades are possible; downgrades and cancellations must be done by the human in the dashboard.

Input parameters:

- `interval` (string): Billing interval for kind=plan only. Default: month. Ignored for top-ups.
- `item` (string, required): Id of the top-up or plan, as listed by ujeebu_plans (e.g. 'mini' for a top-up, 'starter' for a plan).
- `kind` (string, required): 'topup' for a one-off credit pack (credits never expire) or 'plan' for a subscription upgrade.

### `ujeebu_extract` (~678 tokens)

Extract clean, structured data from news or blog articles. Returns main text/HTML, author, publish date, images, media, RSS feeds, and more.

Input parameters:

- `author` (boolean): Extract article author. Default: true
- `auto_proxy` (boolean): Auto-escalate to better proxy on failure. Default: false
- `custom_proxy` (string): Custom proxy URI: scheme://user:pass@host:port (required if proxy_type='custom')
- `feeds` (boolean): Extract RSS feeds. Default: false
- `html` (boolean): Extract article HTML. Default: true
- `image_analysis` (boolean): Analyze images for minimum dimensions. Default: true
- `image_timeout` (number): Image fetch timeout in seconds. Default: 2
- `images` (boolean): Extract all images from article. Default: true
- `is_article` (boolean): Return probability [0-1] of URL being an article (>=0.5 is likely article). Default: true
- `js` (string): Execute JavaScript: 'true', 'false', or 'auto' (let extractor decide). Default: 'false'
- `js_timeout` (number): JS engine timeout when js=true (seconds). Default: timeout/2
- `media` (boolean): Extract embeddable media (YouTube, Twitter, etc.). Default: false
- `min_image_height` (number): Minimum image height in pixels (requires image_analysis=true). Default: 100
- `min_image_width` (number): Minimum image width in pixels (requires image_analysis=true). Default: 200
- `pagination` (boolean): Extract and concatenate multi-page articles. Default: true
- `pagination_max_pages` (number): Max pages to extract when pagination enabled. Default: 30
- `partial` (string): Number of characters or percentage (with %) of text/HTML to return. '0' for all. Default: '0'
- `proxy_country` (string): ISO 3166-1 alpha-2 country code for premium proxy. Default: 'US'
- `proxy_type` (string): Proxy type: 'rotating', 'advanced', 'premium', 'residential', 'custom'. Default: 'rotating'
- `pub_date` (boolean): Extract publish date. Default: true
- `quick_mode` (boolean): Fast analysis mode (30-60% faster, slightly less accurate). Default: false
- `raw_html` (string): HTML content to extract from (skips fetching from url, but url still needed for resolving relative links)
- `return_only_enclosed_text_images` (boolean): Return only images within extracted article HTML. Default: true
- `scroll_down` (boolean): Scroll down page when JS enabled. Default: true
- `session_id` (string): Session ID (1-16 alphanumeric chars) to route through same proxy. Active 30 min
- `strip_tags` (string): Comma-separated CSS selectors/tags to remove before extraction (e.g., 'meta,form,.hidden')
- `text` (boolean): Extract article text. Default: true
- `timeout` (number): Request timeout in seconds. Default: 60
- `url` (string, required): URL of the article to extract

### `ujeebu_gemini` (~71 tokens)

Fetch a URL and ask Gemini about it. Ujeebu loads the page, sends it to Gemini with your prompt, and returns the model's reply.

Input parameters:

- `prompt` (string, required): Question or instruction for Gemini about the page
- `url` (string, required): URL of the page to analyze

### `ujeebu_markdown` (~79 tokens)

Convert any web page into clean, LLM-optimized Markdown. Ideal for feeding page content to a model or RAG pipeline.

Input parameters:

- `js` (string): Execute JavaScript before converting: 'true', 'false', or 'auto'. Default: 'auto'
- `url` (string, required): URL of the page to convert to Markdown

### `ujeebu_plans` (~78 tokens)

Show the account's current plan, credits left, whether agent purchases are enabled (and the monthly cap and remaining amount), plus the available plans and credit top-ups with prices (in cents). Requires an API key. Use the plan/top-up ids from here as 'item' in ujeebu_checkout_link or ujeebu_buy.

### `ujeebu_scrape_extract` (~301 tokens)

Extract structured data from web pages using custom rules. Define CSS selectors or XPath queries to extract specific data. Always returns JSON with extracted data.

Input parameters:

- `auto_proxy` (boolean): Auto-escalate proxy. Default: false
- `block_ads` (boolean): Block ads. Default: false
- `cookies` (string): Custom cookies
- `custom_js` (string): Custom JavaScript code
- `custom_proxy` (string): Custom proxy URI
- `device` (string): Device: 'desktop' or 'mobile'. Default: 'desktop'
- `extract_rules` (string, required): JSON string defining extraction rules with CSS selectors or XPath
- `js` (boolean): Execute JavaScript. Default: true
- `js_timeout` (number): JS timeout in seconds
- `progressive_scroll` (boolean): Progressive scroll. Default: false
- `proxy_country` (string): Proxy country. Default: 'US'
- `proxy_type` (string): Proxy type. Default: 'rotating'
- `scroll_down` (boolean): Scroll page before extraction. Default: false
- `session_id` (string): Session ID
- `timeout` (number): Timeout in seconds. Default: 60
- `url` (string, required): URL to extract data from
- `useragent` (string): Custom user agent
- `wait_for` (string): Wait condition before extraction
- `wait_for_timeout` (number): Wait timeout in milliseconds

### `ujeebu_scrape_html` (~551 tokens)

Scrape and render web pages to get HTML content. Supports JavaScript execution, custom headers, scrolling, and content manipulation. Returns clean HTML or raw HTML.

Input parameters:

- `auto_proxy` (boolean): Auto-escalate proxy. Default: false
- `block_ads` (boolean): Block ads. Default: false
- `block_resources` (boolean): Block images, CSS, fonts. Default: true
- `cookies` (string): Custom cookies: 'cookie1=value1;cookie2=value2'
- `custom_js` (string): Custom JavaScript code to execute
- `custom_proxy` (string): Custom proxy URI
- `custom_proxy_password` (string): Custom proxy password
- `custom_proxy_username` (string): Custom proxy username
- `device` (string): Device: 'desktop' or 'mobile'. Default: 'desktop'
- `http_method` (string): HTTP method: 'GET', 'POST', 'PUT'. Default: 'GET'
- `js` (boolean): Execute JavaScript. Default: true
- `js_timeout` (number): JS execution timeout in seconds. Default: timeout/2
- `post_data` (string): POST/PUT data
- `progressive_scroll` (boolean): Scroll until page height stabilizes. Default: false
- `proxy_country` (string): ISO country code for premium proxy. Default: 'US'
- `proxy_type` (string): Proxy: 'rotating', 'advanced', 'premium', 'residential', 'mobile', 'custom'. Default: 'rotating'
- `response_type` (string): Response type: 'html' (clean) or 'raw' (unprocessed). Default: 'html'
- `scroll_callback` (string): JS function (base64) to control scroll continuation
- `scroll_down` (boolean): Scroll down the page. Default: false
- `scroll_to_selector` (string): CSS selector to scroll to
- `scroll_wait` (number): Milliseconds between scrolls. Default: 100
- `session_id` (string): Session ID (1-16 chars)
- `strip_tags` (string): CSS selectors/tags to remove
- `timeout` (number): Request timeout in seconds. Default: 60
- `url` (string, required): URL to render and scrape
- `useragent` (string): Custom user agent string
- `wait_for` (string): Wait condition: milliseconds, CSS selector, or base64-encoded JS function
- `wait_for_timeout` (number): Timeout for wait_for in milliseconds
- `window_height` (number): Viewport height in pixels
- `window_width` (number): Viewport width in pixels

### `ujeebu_scrape_json` (~460 tokens)

General web scraping that always returns JSON response with metadata. Use this when you need structured response data including headers, status, timing info, and content. Can return HTML, screenshot, or PDF in JSON format.

Input parameters:

- `auto_proxy` (boolean): Auto-escalate proxy. Default: false
- `block_ads` (boolean): Block ads. Default: false
- `block_resources` (boolean): Block resources. Default: false for screenshot/pdf
- `cookies` (string): Custom cookies
- `custom_js` (string): Custom JavaScript code
- `custom_proxy` (string): Custom proxy URI
- `custom_proxy_password` (string): Custom proxy password
- `custom_proxy_username` (string): Custom proxy username
- `device` (string): Device: 'desktop' or 'mobile'. Default: 'desktop'
- `http_method` (string): HTTP method. Default: 'GET'
- `js` (boolean): Execute JavaScript. Default: true
- `js_timeout` (number): JS timeout in seconds
- `post_data` (string): POST/PUT data
- `progressive_scroll` (boolean): Progressive scroll. Default: false
- `proxy_country` (string): Proxy country. Default: 'US'
- `proxy_type` (string): Proxy type. Default: 'rotating'
- `response_type` (string): Content type: 'html', 'raw', 'pdf', or 'screenshot'. Default: 'html'
- `screenshot_fullpage` (boolean): Full page screenshot (if response_type=screenshot)
- `screenshot_partial` (string): Partial screenshot selector/coords (if response_type=screenshot)
- `scroll_down` (boolean): Scroll page. Default: false
- `session_id` (string): Session ID
- `strip_tags` (string): Tags/selectors to remove
- `timeout` (number): Timeout in seconds. Default: 60
- `url` (string, required): URL to scrape
- `useragent` (string): Custom user agent
- `wait_for` (string): Wait condition
- `wait_for_timeout` (number): Wait timeout in milliseconds
- `window_height` (number): Viewport height
- `window_width` (number): Viewport width

### `ujeebu_scrape_pdf` (~314 tokens)

Generate PDF from web pages. Supports custom page sizes, JavaScript execution, and rendering options. Returns base64-encoded PDF data.

Input parameters:

- `auto_proxy` (boolean): Auto-escalate proxy. Default: false
- `block_ads` (boolean): Block ads. Default: false
- `cookies` (string): Custom cookies
- `custom_js` (string): Custom JavaScript code
- `custom_proxy` (string): Custom proxy URI
- `custom_proxy_password` (string): Custom proxy password
- `custom_proxy_username` (string): Custom proxy username
- `device` (string): Device: 'desktop' or 'mobile'. Default: 'desktop'
- `js` (boolean): Execute JavaScript. Default: true
- `js_timeout` (number): JS timeout in seconds
- `proxy_country` (string): Proxy country. Default: 'US'
- `proxy_type` (string): Proxy type. Default: 'rotating'
- `scroll_down` (boolean): Scroll before PDF. Default: false
- `session_id` (string): Session ID
- `timeout` (number): Timeout in seconds. Default: 60
- `url` (string, required): URL to convert to PDF
- `useragent` (string): Custom user agent
- `wait_for` (string): Wait condition before PDF generation
- `wait_for_timeout` (number): Wait timeout in milliseconds
- `window_height` (number): Viewport height
- `window_width` (number): Viewport width

### `ujeebu_scrape_screenshot` (~353 tokens)

Take screenshots of web pages. Supports full page or partial screenshots, JavaScript execution, and custom viewport sizes. Returns base64-encoded image data.

Input parameters:

- `auto_proxy` (boolean): Auto-escalate proxy. Default: false
- `block_ads` (boolean): Block ads. Default: false
- `cookies` (string): Custom cookies
- `custom_js` (string): Custom JavaScript code
- `custom_proxy` (string): Custom proxy URI
- `custom_proxy_password` (string): Custom proxy password
- `custom_proxy_username` (string): Custom proxy username
- `device` (string): Device: 'desktop' or 'mobile'. Default: 'desktop'
- `js` (boolean): Execute JavaScript. Default: true
- `js_timeout` (number): JS timeout in seconds
- `proxy_country` (string): Proxy country. Default: 'US'
- `proxy_type` (string): Proxy type. Default: 'rotating'
- `screenshot_fullpage` (boolean): Capture full page. Default: false
- `screenshot_partial` (string): CSS selector or JSON coordinates {x,y,width,height} for partial screenshot
- `scroll_down` (boolean): Scroll before screenshot. Default: false
- `session_id` (string): Session ID
- `timeout` (number): Timeout in seconds. Default: 60
- `url` (string, required): URL to screenshot
- `useragent` (string): Custom user agent
- `wait_for` (string): Wait condition before screenshot
- `wait_for_timeout` (number): Wait timeout in milliseconds
- `window_height` (number): Viewport height
- `window_width` (number): Viewport width

### `ujeebu_serp` (~276 tokens)

Retrieve Google search results programmatically. Supports web search, images, news, videos, and maps with customizable location, language, and device settings.

Input parameters:

- `device` (string): Device type to simulate: 'desktop', 'mobile', 'tablet'. Default: 'desktop'
- `extra_params` (string): Additional custom query parameters (e.g., '&safe=active&tbs=qdr:d')
- `lang` (string): ISO 639-1 language code (e.g., 'en', 'es', 'fr'). Default: 'en'
- `location` (string): ISO 3166-1 alpha-2 country code for geographic location (e.g., 'us', 'uk', 'fr'). Default: 'us'
- `page` (number): Results page number for pagination. Default: 1
- `results_count` (number): Maximum number of results per page (1-100). Default: 10
- `search` (string): Search query term (provide this OR 'url' parameter, not both)
- `search_type` (string): Search type: 'search' (web), 'images', 'news', 'videos', 'maps'. Default: 'search'
- `url` (string): Direct Google search page URL (provide this OR 'search' parameter, not both)

### `ujeebu_signup` (~267 tokens)

Create a Ujeebu account (and get an API key) for your human, without a key. Works in an unauthenticated session. Ujeebu emails a confirmation link to the address: a human must open it and click Confirm; you cannot confirm it yourself, so tell your human to check their inbox. The response contains request_id and poll_token: keep both and call ujeebu_signup_status about every 10 seconds until status is confirmed (or expired/declined). Requests expire after 24 hours. If the email already has a Ujeebu account, the owner gets an approval email instead; the flow is the same from your point of view (a new key is returned once approved). New accounts start on a free trial.

Input parameters:

- `agent` (string): Optional: your agent or app name, e.g. 'Claude Code'. Shown to the human in the confirmation email. Defaults to the MCP client name.
- `email` (string, required): Email address of the human who will own the account. They must be able to open the confirmation email.
- `name` (string): Optional: the human's name (or company).
- `purpose` (string): Optional: one short sentence on what the account will be used for (shown to the human).

### `ujeebu_signup_status` (~175 tokens)

Check a pending ujeebu_signup request. Works without a key. Poll about every 10 seconds (never faster than every 2 seconds). status values: pending_confirmation (the human has not clicked the link yet, keep polling), confirmed (the response contains api_key, shown ONCE: store it immediately, then reconnect to this MCP server with header Authorization: Bearer <key>), delivered (the key was already returned by an earlier poll and cannot be shown again), expired or declined (start over with ujeebu_signup if appropriate).

Input parameters:

- `poll_token` (string, required): poll_token returned by ujeebu_signup (starts with agp_). Secret: do not show it to anyone else.
- `request_id` (string, required): request_id returned by ujeebu_signup (starts with ags_).

## Diagnostics

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

## Score history

- 2026-10-17: 63
- 2026-10-16: 63
- 2026-10-15: 62
- 2026-10-14: 62
- 2026-10-13: 61
- 2026-10-12: 61

## Common questions

### What is the Ujeebu MCP server?

Ujeebu is an MCP server listed in the public MCP registry as com.ujeebu/mcp. Web scraping, Google SERP, Markdown and ChatGPT/Gemini answers as typed tools for AI agents. This page covers its hosted endpoint (https://mcp.ujeebu.com/mcp).

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

Ujeebu scores 63 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 Ujeebu MCP server expose?

Ujeebu exposes 17 tools: ujeebu_account, ujeebu_buy, ujeebu_card, ujeebu_chatgpt, ujeebu_checkout_link, and 12 more. Their descriptions and schemas cost roughly 4,379 tokens of context every time the server is loaded.

### Does the Ujeebu MCP server require authentication?

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

### Is the Ujeebu MCP server still maintained?

Ujeebu is still listed as active in the MCP registry. We last reached this channel on 17 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://mcp.ujeebu.com/mcp
- Website: https://ujeebu.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-ujeebu-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-ujeebu-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-ujeebu-mcp/mcp