Pokemon MCP Server
Click on "Install 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., "@Pokemon MCP Serverwhat are the stats and evolution chain for charizard?"
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.
Pokemon MCP Server
A Model Context Protocol (MCP) server that provides access to Pokemon data through the PokeAPI. This server allows Claude and other MCP-compatible clients to fetch detailed information about Pokemon, including stats, types, moves, and evolution chains.
Features
Pokemon Overview: Get comprehensive information about any Pokemon including name, types, base stats, and description
Move Details: Fetch detailed information about Pokemon moves including power, PP, type, and damage class
Evolution Chains: Retrieve complete evolution chains for any Pokemon
Related MCP server: Pokédex MCP Server
Prerequisites
Node.js 18 or higher
npm or yarn package manager
Installation
Clone this repository:
git clone <your-repository-url>
cd pokemon-mcpInstall dependencies:
npm installBuild the project:
npm run buildUsage
Development
To run the server in development mode:
npm run devProduction
After building, you can run the compiled server:
node build/index.jsAvailable Tools
1. Get Pokemon Overviews
Tool Name:
get_pokemon_overviewsDescription: Get overview information for multiple Pokemon
Parameters:
pokemonNames: Array of Pokemon names (e.g., ['pikachu', 'charizard'])
Returns: Name, types, base stats, and description for each Pokemon
2. Get Move Detail
Tool Name:
get_move_detailDescription: Get detailed information about a specific Pokemon move
Parameters:
move: Move name (e.g., 'hyper beam', 'thunder bolt')
Returns: Move name, power, PP, type, category, and damage class
3. Get Evolution Chain
Tool Name:
get_evolution_chainDescription: Get the complete evolution chain for a Pokemon
Parameters:
pokemonName: Pokemon name (e.g., 'bulbasaur')
Returns: Complete evolution chain from base form to final evolution
Connecting to Claude Desktop
To use this MCP server with Claude Desktop, you need to configure it in your Claude Desktop settings.
Configuration
Open Claude Desktop
Navigate to Settings → Developer → Edit Config
Add the following configuration to your
claude_desktop_config.json:
{
"mcpServers": {
"pokemon": {
"command": "node",
"args": ["/path/to/your/pokemon-mcp/build/index.js"],
"env": {}
}
}
}Important: Replace /path/to/your/pokemon-mcp/ with the actual absolute path to your project directory.
Alternative: Using npx (if published)
If you've published this as an npm package, you can use:
{
"mcpServers": {
"pokemon": {
"command": "npx",
"args": ["pokemon-mcp"],
"env": {}
}
}
}Verification
Restart Claude Desktop after updating the configuration
Look for the 🔌 icon in the Claude interface, which indicates MCP servers are connected
You should see "pokemon" listed as an available MCP server
Test the connection by asking Claude about Pokemon information
Example Usage with Claude
Once connected, you can ask Claude questions like:
"Can you get information about Pikachu and Charizard?"
"What are the details of the move Thunder Bolt?"
"Show me the evolution chain for Squirtle"
"Compare the stats of Bulbasaur, Charmander, and Squirtle"
API Data Source
This server fetches data from PokeAPI, a free and open Pokemon API. The server includes caching to improve performance and reduce API calls. For this project specifically, we are using pokedex-promise-v2
Project Structure
pokemon-mcp/
├── src/
│ ├── index.ts # Main MCP server implementation
│ └── pokemonHelper.ts # Pokemon API helper functions
├── build/ # Compiled JavaScript output
├── package.json
├── tsconfig.json
└── README.mdDevelopment Scripts
npm run dev- Run the server in development mode with hot reloadnpm run build- Compile TypeScript to JavaScript
Dependencies
@modelcontextprotocol/sdk- MCP SDK for building MCP serverspokedex-promise-v2- Promise-based PokeAPI wrapperzod- Schema validation library
Troubleshooting
Server Not Connecting
Ensure the path in your Claude Desktop config is correct and absolute
Verify that the build directory exists and contains compiled JavaScript
Check that Node.js is installed and accessible from the command line
Pokemon Not Found
Ensure Pokemon names are spelled correctly (case-insensitive)
Use the official Pokemon names (e.g., "nidoran-f" for female Nidoran)
Move Not Found
Move names should use hyphens instead of spaces (e.g., "hyper-beam" instead of "hyper beam")
The server automatically converts spaces to hyphens, but using the correct format is recommended
License
ISC
Contributing
Feel free to submit issues and enhancement requests!
Available Tools
1 toolget-pokemon-statsC
tool to fetch the stats of a pokemon
| Name | Required | Description | Default |
|---|---|---|---|
| pokemon | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'fetch the stats,' implying a read-only operation, but doesn't specify details like rate limits, error handling, authentication needs, or what 'stats' includes (e.g., numeric values, types). This leaves significant gaps in understanding the tool's behavior beyond basic functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise ('tool to fetch the stats of a pokemon'), using only one sentence without unnecessary words. It's front-loaded with the core purpose. However, it could be slightly more polished (e.g., 'Fetches the stats of a Pokémon').
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (1 parameter, no output schema, no annotations), the description is incomplete. It lacks details on what 'stats' entails, potential errors, or return format, leaving the agent with insufficient context to use the tool effectively beyond basic invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 1 parameter with 0% description coverage, so the schema provides no semantic information. The description adds minimal value by implying the parameter is for specifying a pokemon, but doesn't clarify format (e.g., name, ID), constraints, or examples. This is insufficient to compensate for the low schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'tool to fetch the stats of a pokemon' states a clear verb ('fetch') and resource ('stats of a pokemon'), making the purpose understandable. However, it uses vague language ('tool to fetch' instead of more specific phrasing like 'retrieves' or 'returns') and doesn't differentiate from siblings (though none exist). It avoids tautology by not just restating the name 'get-pokemon-stats'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool, such as prerequisites, alternatives, or specific contexts. It merely states what it does without indicating scenarios where it's appropriate or not. With no sibling tools, differentiation isn't needed, but usage context is still missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
- First observed
get-pokemon-stats
TDQS
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as fetching Pokémon stats, making it distinct by default.
The single tool name 'get-pokemon-stats' follows a clear verb_noun pattern (get_stats), and there are no other tools to create inconsistency. The naming is straightforward and predictable.
A single tool for a Pokémon server feels thin and incomplete for the domain, which typically involves multiple operations like listing, searching, or managing Pokémon. This minimal set is inadequate for most agent workflows.
The tool surface is severely incomplete for a Pokémon domain. It only allows fetching stats, with no capabilities for listing Pokémon, getting details beyond stats, searching, or other CRUD operations, leading to significant gaps and agent failures.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Provide detailed Pokémon data and information through a standardized MCP interface. Enable LLMs an…
Look up Pokémon, moves, abilities, items, natures, and type matchups from PokéAPI v2.
Look up Pokemon TCG Pocket cards, sets, packs, and evaluate decks with battle simulations.
111Teamfight Tactics data & AI coaching for Claude and ChatGPT — 19 tools, built-in Riot key.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI models to access comprehensive Pokémon data from PokéAPI and simulate battles between any two Pokémon with realistic mechanics including type effectiveness, stat-based damage calculations, and status effects.1-
- AlicenseBqualityDmaintenanceEnables AI agents to access comprehensive Pokémon data through PokeAPI, including detailed Pokémon information, type effectiveness charts, encounter locations, and search capabilities. Provides a complete toolkit for retrieving stats, abilities, sprites, battle mechanics, and wild encounter data for all Pokémon.42311MIT
- AlicenseBqualityDmaintenanceEnables users to retrieve Pokémon statistics, sprite images, and complete information using the PokeAPI. Supports querying by Pokémon name or ID number to get base stats, various sprite URLs including shiny variants, and comprehensive Pokémon data.513Apache 2.0
- AlicenseBqualityDmaintenanceEmpowers AI assistants to fetch and explore comprehensive Pokémon data from PokeAPI via 47 tools covering Pokémon, moves, items, game mechanics, and more.471661ISC
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/JayDevelops/poke-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server