### Recommended Agent Workflow

Source: https://zpi.web.id/mcp

Illustrates the recommended 3-step workflow for an agent using MCP tools. This workflow involves searching for scrapers, optionally getting the schema, and then running the scraper.

```bash
# The recommended 3-step workflow for your agent:
search_scrapers query="instagram profile"      # 1) find an endpoint
get_scraper_schema scraper="..." endpoint="..." # 2) only if flagged needsSchemaCall
run_scraper scraper="..." endpoint="profile" params={ "username": "zaadevofc" }
```

--------------------------------

### SDK Client Initialization and Usage

Source: https://zpi.web.id/mcp

Demonstrates how to initialize the MCP client and use its methods like `listTools` and `callTool`.

```APIDOC
## SDK client
From TypeScript, skip the client config entirely — `zpi-sdk/mcp` is a zero-dependency MCP client for the same server: JSON-RPC over Streamable HTTP, protocol version `2025-06-18`, session tracked via the `mcp-session-id` header. The initialize handshake runs lazily on first call.
mcp.ts
```typescript
import { createMcpClient } from "zpi-sdk/mcp";

const mcp = createMcpClient({
  apiKey: "zpi_...",
  baseURL: "https://api.zpi.web.id",
});
const tools = await mcp.listTools();
const result = await mcp.callTool("run_scraper", {
  scraper: "instagram-scraper",
  endpoint: "profile",
  params: { username: "zaadevofc" },
});
```

`listTools()` returns the 8 tool definitions; `callTool(name, args)` invokes one. RPC failures throw `ZpiMcpError` (with `code` and `data`). See the SDK docs for the full client reference.
```

--------------------------------

### Create MCP Client and Call Tools (TypeScript)

Source: https://zpi.web.id/mcp

Demonstrates creating a zero-dependency MCP client in TypeScript and making calls to list tools and execute a scraper. The client initializes lazily on the first call. RPC failures throw ZpiMcpError.

```typescript
import { createMcpClient } from "zpi-sdk/mcp";

const mcp = createMcpClient({
  apiKey: "zpi_...",
  baseURL: "https://api.zpi.web.id",
});
const tools = await mcp.listTools();
const result = await mcp.callTool("run_scraper", {
  scraper: "instagram-scraper",
  endpoint: "profile",
  params: { username: "zaadevofc" },
});
```

--------------------------------

### Continue MCP Configuration

Source: https://zpi.web.id/mcp

Configuration for Continue using 'mcpServers' with 'type: streamable-http'. Ensure 'docs.continue.dev' for verification.

```json
{
  "mcpServers": [
    {
      "name": "zapi",
      "type": "streamable-http",
      "url": "https://mcp.zpi.web.id/mcp",
      "requestOptions": {
        "headers": {
          "Authorization": "Bearer zpi_xxx"
        }
      }
    }
  ]
}
```

--------------------------------

### Claude Desktop/Claude.ai MCP Configuration with mcp-remote

Source: https://zpi.web.id/mcp

Configuration for Claude Desktop/Claude.ai using 'mcp-remote' as a stdio bridge. Ensure 'command' and 'args' are correctly formatted, with '--header' and its value as separate array elements.

```json
{
  "mcpServers": {
    "zapi": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.zpi.web.id/mcp",
        "--header",
        "Authorization: Bearer zpi_xxx"
      ]
    }
  }
}
```

--------------------------------

### JetBrains AI Assistant MCP Configuration

Source: https://zpi.web.id/mcp

Configuration for JetBrains AI Assistant using 'context_servers' for MCP servers.

```json
{
  "context_servers": {
    "zapi": {
      "url": "https://mcp.zpi.web.id/mcp",
      "headers": {
        "Authorization": "Bearer zpi_xxx"
      }
    }
  }
}
```

--------------------------------

### bulk_submit

Source: https://zpi.web.id/mcp

Submits a batch job for processing. Requires a Pro+ plan and `bulkEnabled` on the target endpoint. Returns immediately with a job ID.

```APIDOC
### bulk_submit
bills per itempro plan or higher
Submits a batch job. Requires a Pro+ plan _and_ `bulkEnabled` on the target endpoint, with per-tier item caps. Returns immediately with `{ jobId, status: "queued", total }` — it never waits; poll with `bulk_status`.
Param| Type| Required| Purpose  
---|---|---|---
scraper| string| yes| Scraper slug.  
endpoint| string| yes| Endpoint slug.  
urls| array| yes| URL strings or per-item param objects; duplicates are removed.  
idempotencyKey| string| no| Same key returns the same job — no double submission.  
```

--------------------------------

### VS Code / Copilot MCP Configuration

Source: https://zpi.web.id/mcp

Configuration for VS Code and GitHub Copilot using 'servers' with 'type: http' for MCP servers.

```json
{
  "servers": {
    "zapi": {
      "type": "http",
      "url": "https://mcp.zpi.web.id/mcp",
      "headers": {
        "Authorization": "Bearer zpi_xxx"
      }
    }
  }
}
```

--------------------------------

### Antigravity/Windsurf Client MCP Configuration

Source: https://zpi.web.id/mcp

Configuration for Antigravity and Windsurf clients using the 'serverUrl' key for MCP servers.

```json
{
  "mcpServers": {
    "zapi": {
      "serverUrl": "https://mcp.zpi.web.id/mcp",
      "headers": {
        "Authorization": "Bearer zpi_xxx"
      }
    }
  }
}
```

--------------------------------

### Cursor Client MCP Configuration

Source: https://zpi.web.id/mcp

Configuration for the Cursor client using the 'url' key for MCP servers.

```json
{
  "mcpServers": {
    "zapi": {
      "url": "https://mcp.zpi.web.id/mcp",
      "headers": {
        "Authorization": "Bearer zpi_xxx"
      }
    }
  }
}
```

--------------------------------

### Gemini CLI MCP Configuration

Source: https://zpi.web.id/mcp

Configuration for the Gemini CLI using the 'httpUrl' key for MCP servers.

```json
{
  "mcpServers": {
    "zapi": {
      "httpUrl": "https://mcp.zpi.web.id/mcp",
      "headers": {
        "Authorization": "Bearer zpi_xxx"
      }
    }
  }
}
```

--------------------------------

### get_account

Source: https://zpi.web.id/mcp

Retrieves account information including tier, plan status, expiration date, and API key details. Does not return the API key secret.

```APIDOC
### get_account
read-only · free
No input. Returns your `tier`, `planStatus` (`free | active | expired`), `planExpiresAt`, and the API key label (`{ name, keyPrefix, enabled }`). The key secret is never returned. Quota numbers live in `get_usage`, not here. 
```

--------------------------------

### get_usage

Source: https://zpi.web.id/mcp

Provides a summary of API usage, including total requests, requests and errors in the last 24 hours, success rate, and quota details.

```APIDOC
### get_usage
read-only · free
No input. Returns a summary (`{ totalRequests, requests24h, errors24h, successRate24h }`) plus your quota (`{ tier, used, limit, remaining, resetAt }`— `resetAt` is the 1st of next month, UTC). Check it before `run_scraper` to avoid burning quota blind. 
```

--------------------------------

### run_scraper

Source: https://zpi.web.id/mcp

Executes a specified scraper endpoint with provided parameters. This tool bills per call and clients should not auto-approve its execution.

```APIDOC
### run_scraper
bills per call
Executes one scraper endpoint. Marked `readOnlyHint: false` — clients should **not auto-approve** it. Path params in `params` fill the URL template automatically and the HTTP method is chosen for you.
Param| Type| Required| Purpose  
---|---|---|---
scraper| string| yes| Scraper slug.  
endpoint| string| yes| Endpoint slug.  
params| object| no| Endpoint params; path params (username, slug, …) go here too.  
Success returns `{ data, project, cache, meta }` where `meta` is `{ billed, costUnits, remaining, resetAt }`. Failures set `isError` with a code from the error table — including `plan_upgrade_required` when the endpoint's `minPlan` is above your tier. 
```

--------------------------------

### Add MCP Transport via CLI

Source: https://zpi.web.id/mcp

Use this command to add the MCP transport with a specific URL and authorization header.

```bash
claude mcp add --transport http zapi https://mcp.zpi.web.id/mcp \
  --header "Authorization: Bearer zpi_xxx"
```

--------------------------------

### Zapi MCP Endpoint and Authentication Headers

Source: https://zpi.web.id/mcp

This snippet shows the Zapi MCP server endpoint and the three acceptable headers for authentication using an API key.

```text
# Zapi MCP endpoint (Streamable HTTP)
https://mcp.zpi.web.id/mcp

# Auth via header — any of these three:
Authorization: Bearer zpi_xxx
x-api-key: zpi_xxx
api-key: zpi_xxx
```

--------------------------------

### search_scrapers

Source: https://zpi.web.id/mcp

Performs a natural-language fuzzy search over the catalog of available scrapers and endpoints. Returns zero results with did-you-mean suggestions if no matches are found.

```APIDOC
### search_scrapers
read-only · free
Natural-language fuzzy search over the catalog. Zero results return did-you-mean suggestions. Each row includes the endpoint's params inline plus `minPlan` and `bulkEnabled`. Categories: `ai, bypass-tools, downloader, food, games, search-tools, social-media, web-tools`.
Param| Type| Required| Purpose  
---|---|---|---
query| string| no| Free-text search, e.g. "instagram profile".  
category| string| no| Filter to one category.  
cursor| string| no| Pagination cursor.  
```

--------------------------------

### list_categories

Source: https://zpi.web.id/mcp

Lists all available categories in the scraper catalog, along with the count of scrapers within each category. Useful for scoping searches.

```APIDOC
### list_categories
read-only · free
No input. Returns every catalog category with its scraper count — useful for scoping before a search. 
```

--------------------------------

### get_scraper_schema

Source: https://zpi.web.id/mcp

Retrieves the full parameter schema for a specific scraper endpoint. Useful for understanding the required and optional parameters for an endpoint.

```APIDOC
### get_scraper_schema
read-only · free
Full parameter schema for one endpoint: fields with `name / type / required / example`, plus `minPlan` and `bulkEnabled`. Unknown scraper or endpoint returns an error steering back to `search_scrapers`.
Param| Type| Required| Purpose  
---|---|---|---
scraper| string| yes| Scraper slug.  
endpoint| string| yes| Endpoint slug.  
```

--------------------------------

### bulk_status

Source: https://zpi.web.id/mcp

Polls the status of a bulk submission job using its job ID. Returns details about the job's progress, success, and failures.

```APIDOC
### bulk_status
read-only · free
Polls one job. Returns `{ jobId, status, total, succeeded, failed, scraperSlug, endpointSlug, items }` where each item is `{ url, status, error? }`. Unknown or other-account jobs return `job_not_found` — job ids can't be enumerated.
Param| Type| Required| Purpose  
---|---|---|---
jobId| string| yes| Id from bulk_submit.  
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.