Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ZapifyAPI MCP Server What's the SSL status for zapifyapi.com?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Official MCP (Model Context Protocol) server for ZapifyAPI — gives AI agents access to 32 agent-ready tools across image conversion, text analysis, network diagnostics, developer utilities, and data conversion.
Selected from ZapifyAPI's catalogue of 40+ APIs: the tools exposed here are the ones that work well under agent control, with inputs a model can construct and outputs it can reason about.
Sign up at zapifyapi.com (free)
Go to Dashboard → MCP
Create an MCP token (choose permissions and spending limits)
Copy the token (starts with mcp_)
Add to your claude_desktop_config.json:
{
"mcpServers": {
"zapifyapi": {
"command": "npx",
"args": ["@zapifyapi/mcp-server"],
"env": {
"ZAPIFYAPI_TOKEN": "mcp_your_token_here"
}
}
}
}Add to .kiro/settings/mcp.json:
{
"mcpServers": {
"zapifyapi": {
"command": "npx",
"args": ["@zapifyapi/mcp-server"],
"env": {
"ZAPIFYAPI_TOKEN": "mcp_your_token_here"
}
}
}
}ZAPIFYAPI_TOKEN=mcp_your_token_here npx @zapifyapi/mcp-serverRelated MCP server: IPGeolocation MCP Server
convert_image_to_webp — Convert PNG/JPEG to WebP
add_watermark — Add text watermark to image
translate_text — Translate between 50+ languages
analyze_sentiment — Detect tone (positive/negative/neutral)
extract_keywords — Extract keywords with relevance scores
check_profanity — Detect and censor profanity
validate_email — Validate email format
parse_user_agent — Parse UA into components
ip_geolocation — Locate an IP address
dns_lookup — Query DNS records (A, MX, TXT, etc)
check_ssl — Check SSL cert validity and expiry
scan_ports — Scan open ports on a host
whois_lookup — Domain WHOIS data
http_headers — Fetch response headers for a URL
generate_qr_code — QR code from text/URL
generate_password — Secure random passwords
generate_hash — MD5/SHA1/SHA256/SHA512
validate_json — Validate and prettify JSON
generate_uuid — Random v4 UUIDs
decode_jwt — Decode JWT payload
test_regex — Test regex against text
convert_color — HEX/RGB/HSL conversion
base64_encode_decode — Base64 encode/decode
markdown_to_html — Markdown to HTML
convert_currency — Real-time currency rates
convert_units — Length, weight, temperature
convert_timezone — Time between zones
csv_to_json — Parse CSV to JSON
extract_url_metadata — Title, OG tags from URL
get_country_info — Country details
get_random_joke — Programming jokes
get_random_quote — Tech quotes
Variable | Required | Description |
| Yes | Your MCP token (get from dashboard) |
| No | API base URL (default: |
Your AI agent connects to this MCP server via stdio
Agent discovers tools via tools/list
Agent calls a tool (e.g., dns_lookup with { domain: "google.com" })
This server sends a POST to https://api.zapifyapi.com/v1/<your_token> with { _tool: "dns lookup", domain: "google.com" }
The gateway routes to the correct API handler and returns results
Points are deducted from your project balance
JSON results are returned as text content. Binary results — converted images, QR codes — are returned as native MCP image content, base64-encoded with the correct MIME type, so the agent receives the actual file rather than a description of it.
Rate-limited requests (HTTP 429) are retried up to three times with exponential backoff and jitter. If the retries are exhausted, or any other error occurs, the error message includes your remaining point balance where the API reports it, so the agent can tell you why a call failed.
Your token is read from the ZAPIFYAPI_TOKEN environment variable and is never accepted as a tool argument, so a model cannot be prompted into echoing it into a transcript.
The server makes no network calls other than to your configured ZAPIFYAPI_URL.
Scope each MCP token in the dashboard to the APIs you actually want the agent to reach, and set a spending limit. Treat an MCP token like any other credential.
When creating an MCP token in the dashboard, you can configure:
All APIs — agent can use any API in the store
Specific APIs — limit to a whitelist of APIs
Auto-create — agent can use APIs not yet added to your project (auto-provisions them)
Spending limit — cap ZP usage per period (e.g., 1000 ZP per month)
Each tool call costs ZapPoints (1-50 ZP depending on the API). The free plan includes 1,000 ZP/month. See zapifyapi.com/pricing for plans.
Website: https://zapifyapi.com
Dashboard: https://zapifyapi.com/dashboard
API Docs: https://zapifyapi.com/docs
MIT
Add a text watermark to an image.
Inputs: binaryData (required), watermark_text (required).
Detect positive/negative/neutral sentiment in text.
Inputs: text (required).
Encode text to Base64 or decode Base64 to text.
Inputs: input (required), action (required).
Detect and censor profanity in text.
Inputs: text (required).
Check SSL certificate validity, issuer, and expiry for a domain.
Inputs: domain (required).
Convert color between HEX, RGB, and HSL.
Inputs: color (required).
Convert between currencies with real-time exchange rates.
Inputs: to (required), from (required), amount.
Convert a PNG or JPEG image to WebP format. Input: base64 encoded image data.
Inputs: binaryData (required).
Convert time between timezones.
Inputs: to_tz (required), from_tz (required), time.
Convert between units (length, weight, temperature).
Inputs: to (required), from (required), value (required).
Parse CSV text into structured JSON.
Inputs: csv (required), delimiter.
Decode a JWT token (header + payload) without verification.
Inputs: token (required).
Query DNS records for a domain (A, AAAA, MX, TXT, NS, CNAME).
Inputs: domain (required), type.
Extract main keywords from text with relevance scoring.
Inputs: text (required), max.
Extract title, description, OG tags from a URL.
Inputs: url (required).
Generate MD5/SHA1/SHA256/SHA512 hash of text.
Inputs: text (required), algorithm.
Generate secure random passwords.
Inputs: count, length, numbers, symbols, +2 more.
Generate a QR code from text or URL.
Inputs: text (required).
Generate random v4 UUIDs.
Inputs: count.
Get country information (capital, population, languages, flag).
Inputs: country (required).
Get a random programming joke.
Inputs: no named parameters.
Get a random tech/programming quote.
Inputs: no named parameters.
Fetch HTTP response headers for a URL.
Inputs: url (required).
Get geographic location of an IP address.
Inputs: target_ip (required).
Convert Markdown text to HTML.
Inputs: markdown (required).
Parse a User-Agent string into browser, OS, device info.
Inputs: user_agent (required).
Scan ports on a host (up to 20 ports).
Inputs: host (required), ports.
Test a regex pattern against text and return matches.
Inputs: text (required), pattern (required), flags.
Translate text between languages. Supports 50+ languages.
Inputs: to (required), text (required), from.
Validate email format and check if domain is disposable.
Inputs: email (required).
Validate and format a JSON string.
Inputs: json (required), indent.
Get WHOIS registration data for a domain.
Inputs: domain (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 32 tools
Each tool has a distinct resource and action, with no two tools overlapping in function. Even the multiple convert_* tools target different domains (currency, units, timezone, image format, color).
Most tools follow a verb_noun snake_case pattern (convert_currency, generate_password, validate_email), but a few break the pattern (csv_to_json, markdown_to_html, ip_geolocation, http_headers, base64_encode_decode). The deviations are minor and the set remains readable.
With 32 tools, this server far exceeds the typical 3-15 tool range for MCP servers. The large number is overwhelming and suggests a lack of focus, though each tool is individually useful.
The tools span a wide range of utilities but are shallow within each category. For example, image processing is limited to WebP conversion and watermarking, and network tools lack ping or HTTP request functionality. There are notable gaps for a general-purpose utility API.
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
All 20 YourAITools agent APIs in one MCP server. Most tools free; pay with credits or x402.
Official MCP server for subfeed.app — the cloud for agents. 15+ tools for AI agents to register, build, and deploy other agents. Zero human required. Start here: subfeed.app/skill.md
AI tool directory MCP server, live since July 2026. Tools, agents, models, companies, services.
