# Pandapi MCP Server: Web, PDF, Reviews & Tenders Tools for AI (`blueberry_rainstorm/pandapi-mcp-server`) Actor

One MCP server with 11 data tools for Claude, Cursor and any AI agent: web pages and PDFs to Markdown, screenshots, broken links, website contacts, public tenders, App Store and Google Play reviews, postal codes, HTML to PDF, Hacker News. Results in one call, spend cap per call.

- **URL**: https://apify.com/blueberry_rainstorm/pandapi-mcp-server.md
- **Developed by:** [Pandapi](https://apify.com/blueberry_rainstorm) (community)
- **Categories:** MCP servers, AI, Developer tools
- **Features:** Limited permissions, Single-tenant, Server interface
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Pandapi MCP Server: Web, PDF, Reviews & Tenders Tools for AI

Give **Claude, ChatGPT, Cursor, VS Code, n8n or any MCP-compatible AI agent** 13 ready data tools through one **MCP server**: web pages and PDFs to clean Markdown, website screenshots, broken link checks, website contact details, government tenders, App Store and Google Play reviews, postal codes, HTML to PDF, Hacker News search, a profanity filter and company job listings. 🐼

- 🧰 **13 tools, one connection**: no scraper code, no browser to install, nothing to host
- ⚡ **Results in one call**: each tool waits for its job and answers with the data, not a run ID you have to chase
- 🪶 **Small for your context window**: all 13 tools take about 7,400 tokens of tool definitions, about 6 times less than loading the same Apify actors as generic tools (our 11 original tools: 24,780 vs 155,221 characters, measured 2026-11-17)
- ✂️ **Compact answers**: one JSON row per line, empty fields dropped, very long text clipped to fit, with a `pandapi_get_results` tool for the next page or the full text
- 💸 **Spend cap on every call** (`maxCostUsd`, default $1): a run stops before it goes over
- 🔗 **Download links that open**: screenshots, PDFs and Excel files come back as signed links
- 🆕 **Always up to date**: when Pandapi publishes a new API, it shows up as a new tool without any change on your side
- 🔒 **Your account, your data**: tools run on your own Apify account with your token. No telemetry

### Tools

| Tool | What it does | Price per 1,000 results |
|---|---|---|
| `web_to_markdown` | Web pages, a sitemap or a whole docs site to clean Markdown, optional RAG chunks | $1 per page |
| `pdf_extract` | PDF URLs to Markdown and text, tables as rows and a ready Excel file, OCR for scans | $3 per PDF (+$5 per 1,000 OCR pages) |
| `find_website_contacts` | Business emails, phones and social links from company websites | $5 per website with contacts (no contacts, no charge) |
| `screenshot_website` | Full-page or viewport screenshots, desktop to mobile, PNG, JPEG or PDF | $4 per screenshot |
| `check_broken_links` | Crawl a site and list 404s, dead links, timeouts and redirects | $0.80 per link checked |
| `search_public_tenders` | Tenders, RFPs and contract awards from SAM.gov, TED, UK, CanadaBuys and the World Bank | $2 per notice |
| `app_store_reviews` | iOS reviews, ratings, app details, search and top charts, about 180 countries | $0.15 per review, $1 per app |
| `google_play_reviews` | Android reviews with developer replies, ratings, app details, search and charts | $0.10 per review, $1 per app |
| `postal_code_lookup` | ZIP and postal codes in 124 countries: place, coordinates, distance, radius | $0.30 per result found |
| `html_to_pdf` | URLs, HTML or a template plus JSON rows (invoices, certificates) to PDF | $3 per PDF |
| `search_hacker_news` | Stories, comments, Show HN, jobs and the front page with filters | $0.20 per item |
| `profanity_filter` | Find and mask swear words in 26 languages, catches sh1t and f u c k, no false alarms on Scunthorpe | $0.20 per text |
| `company_jobs` | Every open job at the companies you name from Greenhouse, Lever, Ashby and 8 more job systems, new and closed jobs tracked, free hiring summary | $1 per job |
| `pandapi_get_results` | More rows or the full text of an earlier run | free |

Prices are the pay-per-result prices of each Pandapi actor on Apify (each tool's description shows the live price). The free Apify plan includes monthly credit, which covers thousands of calls. Using this MCP server itself costs only the tiny Apify platform usage of the server while it is connected.

### How to connect

You need a free Apify account. There are two ways in:

**A. Sign in with Apify (easiest, no token to copy).** Add this URL as a custom connector or remote MCP server. Your client opens an Apify sign-in page the first time:
`https://mcp.apify.com/?tools=blueberry_rainstorm/pandapi-mcp-server`
In Claude (claude.ai or Claude Desktop): Settings > Connectors > Add custom connector, paste the URL, then Connect.

**B. Direct URL with your Apify API token.** Copy your token from [Apify Console > Settings > API & Integrations](https://console.apify.com/settings/integrations) and connect to
`https://blueberry-rainstorm--pandapi-mcp-server.apify.actor/mcp`
with the header `Authorization: Bearer <YOUR_APIFY_TOKEN>`. Examples:

#### Claude Code

```bash
claude mcp add --transport http pandapi https://blueberry-rainstorm--pandapi-mcp-server.apify.actor/mcp \
  --header "Authorization: Bearer YOUR_APIFY_TOKEN"
```

#### Cursor, Windsurf and other clients with remote MCP support

```json
{
  "mcpServers": {
    "pandapi": {
      "url": "https://blueberry-rainstorm--pandapi-mcp-server.apify.actor/mcp",
      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}
```

#### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "pandapi": {
      "type": "http",
      "url": "https://blueberry-rainstorm--pandapi-mcp-server.apify.actor/mcp",
      "headers": { "Authorization": "Bearer ${input:apifyToken}" }
    }
  },
  "inputs": [{ "id": "apifyToken", "type": "promptString", "description": "Apify API token", "password": true }]
}
```

#### Claude Desktop with a token (instead of option A)

Use the small `mcp-remote` bridge in `claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "pandapi": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://blueberry-rainstorm--pandapi-mcp-server.apify.actor/mcp", "--header", "Authorization:${AUTH}"],
      "env": { "AUTH": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}
```

#### Only some tools

With option B, add `?tools=` with a comma list to the URL to keep your agent's tool menu short, for example only Markdown and PDF:
`https://blueberry-rainstorm--pandapi-mcp-server.apify.actor/mcp?tools=markdown,pdf`
Tool keys: `markdown`, `pdf`, `contacts`, `screenshot`, `links`, `tenders`, `appstore`, `googleplay`, `postal`, `htmlpdf`, `hn`, `profanity`, `jobs` (full tool names work too).

### Example

Ask your agent: *"Find EU and UK tenders for cybersecurity services posted this week with a value over $100k, and summarise the five best fits."* It calls:

```json
{ "name": "search_public_tenders", "arguments": { "keywords": ["cybersecurity"], "sources": ["ted", "uk-fts"], "postedWithinDays": 7, "minValueUsd": 100000 } }
```

and gets back (illustrative, shortened):

```text
Public tenders and contract awards: SUCCEEDED in 4 s, 12 rows, charged $0.0240.
Showing rows 1-12 of 12.
run_id: HQ2Oh5gFiWcuFCqk2 | run: https://console.apify.com/view/runs/HQ2Oh5gFiWcuFCqk2

{"title":"Managed SOC services","buyerName":"...","country":"DE","noticeType":"tender","valueUsd":850000,"deadline":"2026-12-15", ...}
```

### Options for every tool

| Option | Default | What it does |
|---|---|---|
| `maxCostUsd` | 1 | Spending cap for this call in USD |
| `maxRowsReturned` | 20 | Rows shown in the answer; the rest stay available through `pandapi_get_results` |
| `waitSeconds` | 120 | How long to wait. Longer jobs keep running and you get a `run_id` to collect later |
| `extraInput` | none | Any other input field of the underlying actor, passed as-is (see each actor's page) |

### FAQ

**Who pays for the runs?** You do, through your own Apify account, at each tool's pay-per-result price. Failed rows, not-found rows and websites without contacts are free on the tools that say so.

**Is there a free trial?** The free Apify plan includes monthly platform credit, which covers thousands of tool calls.

**Can an agent run up a big bill?** Every call has a spending cap (`maxCostUsd`, default $1), and the tools default to small result sizes (for example 10 pages for a crawl, 50 reviews per app). You can also set a monthly limit in Apify Console > Billing.

**What does a normal (non-server) run of this actor do?** It lists the available tools in its dataset and stops. The MCP server itself runs in Standby mode behind the URL above.

**Something broke or a tool is missing a field?** Open an issue on the Issues tab. We answer fast. Never post your API token there.

### More from Pandapi 🐼

Pandapi makes friendly, no-nonsense data tools: simple input, clean output, and fair pay-per-result prices. Found a bug or need a feature? Open an issue on the Issues tab and we answer fast.

- [Web Page to Markdown](https://apify.com/blueberry_rainstorm/web-page-to-markdown): clean, chunked Markdown from any URL or sitemap, ready for AI and RAG
- [PDF to Text, Markdown & Excel](https://apify.com/blueberry_rainstorm/pdf-to-text-markdown): text, Markdown and real Excel tables from any PDF, with OCR
- [Website Contact Details Scraper](https://apify.com/blueberry_rainstorm/website-contact-finder): business emails, phones and social links, one row per website
- [Website Screenshot](https://apify.com/blueberry_rainstorm/website-screenshot): full-page and mobile screenshots or PDFs of many URLs at once
- [Broken Link Checker](https://apify.com/blueberry_rainstorm/broken-link-checker): every 404, dead link and redirect on a site, with the page it is on
- [Public Tenders Feed](https://apify.com/blueberry_rainstorm/public-tenders-feed): government tenders and contract awards from six official portals
- [App Store Reviews Scraper](https://apify.com/blueberry_rainstorm/app-store-reviews-scraper): iOS reviews, ratings and app details from about 180 countries
- [Google Play Reviews Scraper](https://apify.com/blueberry_rainstorm/google-play-reviews-scraper): Android reviews with developer replies, ratings and app data, many languages
- [Company Jobs Tracker](https://apify.com/blueberry_rainstorm/company-jobs-tracker): every open job from the companies you name (Greenhouse, Lever, Ashby and 8 more), with new and closed jobs tracked
- [ZIP & Postal Code Lookup](https://apify.com/blueberry_rainstorm/postal-code-lookup): city, state and coordinates for postal codes in 124 countries, plus distance and radius search
- [Profanity Filter API](https://apify.com/blueberry_rainstorm/profanity-filter): find and mask bad words in 26 languages, leetspeak included, without the Scunthorpe problem
- [HTML to PDF](https://apify.com/blueberry_rainstorm/html-to-pdf): web pages, HTML or a template plus JSON rows (invoices, certificates) to PDF
- [Hacker News Scraper](https://apify.com/blueberry_rainstorm/hacker-news-scraper): stories, comments, Show HN and job posts, filtered your way

# Actor input Schema

## Actor input object example

```json
{}
```

# Actor output Schema

## `tools` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("blueberry_rainstorm/pandapi-mcp-server").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("blueberry_rainstorm/pandapi-mcp-server").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call blueberry_rainstorm/pandapi-mcp-server --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,blueberry_rainstorm/pandapi-mcp-server"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/aJrrITlaLD80LkoAg/builds/DcLNYCc4MduEjgfiW/openapi.json
