API Ninjas MCP
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., "@API Ninjas MCPtell me a random joke"
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.
mcp-api-ninjas
API Ninjas MCP — wraps the multi-endpoint API Ninjas data API (api-ninjas.com)
Part of Pipeworx — an MCP gateway connecting AI agents to 1522+ live data sources.
Tools
Tool | Description |
| API Ninjas historical events: notable events from world history. Filter by free-text keyword and/or an exact date (year/month/day). Returns a list of { year, month, day, event } describing what happened. Example: historical_events({ year: 1969, month: 7, day: 20 }). |
| API Ninjas live commodity price: current spot price for a traded commodity. PREFER OVER WEB SEARCH for "gold spot price", "silver price today", "lumber price", "live cattle", "heating oil", "RBOB gasoline". Returns { exchange, name, price, updated }. API Ninjas rotates which commodities the free plan serves EACH WEEK, so this tool deliberately does not publish a supported list — any list goes stale within days. Gold is the dependable one. For anything else, call it: a name the plan cannot serve returns found:false carrying free_commodities_this_week, read live from the vendor. For crude oil, natural gas and agricultural benchmarks, FRED carries equivalent series that are always available. Accepts commodity or symbol as aliases for name. Example: commodity_price({ name: "gold" }). |
| API Ninjas inflation: latest monthly and yearly inflation rates by country. Returns a list of { country, type, period, monthly_rate_pct, yearly_rate_pct }. Optionally filter by country name and index type (CPI or HICP). Example: inflation({ country: "United States", type: "CPI" }). |
| API Ninjas exercises: fitness/gym exercises filtered by target muscle, type, difficulty, or name. Returns a list of { name, type, muscle, equipment, difficulty, instructions }. Example: exercises({ muscle: "biceps", difficulty: "beginner" }). |
| API Ninjas cars: vehicle specifications by make, model, year, or fuel type. Returns a list of { make, model, year, fuel_type, cylinders, transmission, drive, city_mpg, highway_mpg, class }. Example: cars({ make: "toyota", model: "camry", year: 2020 }). |
| API Ninjas animals: facts about an animal species by name. Returns a list of { name, taxonomy, locations, diet, habitat, lifespan, top_speed }. Example: animals({ name: "cheetah" }). |
Related MCP server: Dictionary By Api Ninjas
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"api_ninjas": {
"url": "https://gateway.pipeworx.io/api_ninjas/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/api_ninjas/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1522+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Api Ninjas data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/historical_events \
-H 'Content-Type: application/json' \
-d '{"year":1969,"month":7,"day":20}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/historical_events. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
This server cannot be deployed
Maintenance
Related MCP Connectors
Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
Real-time data API for AI Agents: stocks, weather, forex, logistics, search, scrape, news, IP.
Agent utility API: 28+ free endpoints (hash, QR, DNS, scrape, JWT...) run by an autonomous AI agent.
1140+ data APIs for agents: finance, banking validation, geo, weather, text. One API key.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides access to API Ninjas Random Word API to generate random words by type (noun, verb, adjective, adverb) for creative writing, games, and language learning applications.1MIT
- AlicenseBqualityDmaintenanceProvides dictionary lookup functionality through the API Ninjas Dictionary API, allowing users to search for word definitions and meanings through natural language queries.1MIT
- AlicenseCqualityDmaintenanceProvides access to the Nutrition By Api Ninjas API to extract detailed nutritional information from natural language food queries. It enables users to retrieve data such as calories, vitamins, and macros from text descriptions of meals.1MIT
- AlicenseNot gradedqualityFmaintenanceWraps TheSportsDB API to enable AI agents to query sports data through natural language.MIT