What tools does PokeAPI MCP Server provide?
It provides two tools: `pokemon_info` (returns basic Pokémon info) and `pokemon_sprite` (returns a sprite image URL). Both accept a Pokémon name or ID.
@katakyo
基本信息
This project is an MCP server built with mcp_rb for retrieving Pokémon information.
`name_or_id` (Pokémon name or ID)
`name_or_id` (Pokémon name or ID)
PokeAPI MCP Server is a Model Context Protocol (MCP) server built with mcp_rb that retrieves Pokémon information from the PokeAPI. It provides a simple interface for Claude to interact with the Pokémon database.
Install Ruby dependencies with bundle install, then start the server with ruby poke_api.rb. Configure Claude Desktop to point to the server’s poke_api.rb file and enable the pokemon_info and pokemon_sprite tools.
It provides two tools: `pokemon_info` (returns basic Pokémon info) and `pokemon_sprite` (returns a sprite image URL). Both accept a Pokémon name or ID.
It requires Ruby, the `mcp` gem, and standard libraries `net/http`, `json`, and `uri`.
Add the server to your Claude Desktop config file with command `ruby`, args pointing to the `poke_api.rb` file, and `alwaysAllow` set to `["pokemon_info", "pokemon_sprite"]`.
No. The server fetches all data from the remote PokeAPI and does not persist any data locally.
The README does not specify the transport protocol. It is configured to run as a local command via standard input/output in Claude Desktop.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

AI-native payments for tools and APIs. Discover, pay for, execute, and publish monetized APIs directly from your agent, settled per call in USDC over x402, through the Model Context Protocol. payments · finance · x402 ·

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
评论