What is this server for?
It exposes POKEAPI Pokémon data as a tool callable by any MCP client, such as LLM agents or custom MCP applications.
@AkhrHysd
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-pokeapi-server": {
"command": "npx",
"args": [
"tsc"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
A Model Context Protocol (MCP) server that provides Pokémon information by integrating with the public POKEAPI. It uses JSON-RPC 2.0 over stdio, making it suitable for LLM applications and MCP clients that need to query Pokémon data.
Install dependencies with npm install, build with npx tsc, then start the server with npx ts-node src/index.ts. From an MCP client, send JSON‑RPC requests over stdin/stdout—first list_tools to discover the tool, then call_tool with the tool name getPokemonInfo and an argument nameOrId (a Pokémon name or numeric ID).
getPokemonInfo for all queriesIt exposes POKEAPI Pokémon data as a tool callable by any MCP client, such as LLM agents or custom MCP applications.
One tool: `getPokemonInfo`, which returns the Pokémon’s name, ID, height, weight, and types given a name or numeric ID.
Run `npm install` to install dependencies, then `npx tsc` to compile TypeScript. Start the server with `npx ts-node src/index.ts`.
Send an MCP `call_tool` request with `name: "getPokemonInfo"` and `arguments: { "nameOrId": "pikachu" }` (or any valid Pokémon name/ID). The result is a JSON object with the Pokémon’s details.
It uses JSON‑RPC 2.0 over standard input/output (stdio). No HTTP or WebSocket transport is provided.

Model Context Protocol Servers

The article (der, die, das) of 90,000 German nouns, compounds included, plus a checker that finds wrong articles in German text (“mit der Zug” → dem). Uses dictionary data, not AI guessing. Free, no login.
Hindsight: Agent Memory That Learns

Model Context Protocol Servers
不止于 CSS
Comments