home / mcp / mcp character tools mcp server
Provides 14+ character and text analysis tools to support character-level insights for LLMs.
Configuration
View docs{
"mcpServers": {
"aaryan-kapoor-mcp-character-tools": {
"command": "npx",
"args": [
"mcp-character-tools"
]
}
}
}You have MCP Character Tools, a server that provides 14+ character and text analysis utilities to help large language models work with individual characters and counts. It makes character-level operations reliable for tasks like counting specific letters, computing frequencies, breaking words into characters, and more. This MCP server helps you gain precise character-level insight that tokenization can miss, enabling more accurate analysis and prompting workflows.
Install and run the MCP Character Tools server, then connect your MCP client to perform character- and text-focused analyses. You can interact with the suite of tools to count letters, find substrings, get character at specific positions, reverse text, compare texts, and perform word-by-word analyses. The server exposes a set of tools that you can invoke from your MCP client to process text inputs and retrieve structured results.
Prerequisites: Node.js (including npm) should be installed on your system.
# Via npx (recommended)
npx mcp-character-tools
# Via npm (global install)
npm install -g mcp-character-tools
mcp-character-tools
# From source
git clone https://github.com/Aaryan-Kapoor/mcp-character-tools
cd mcp-character-tools
npm install
npm run build
npm startConfiguration notes for connecting from your MCP client are provided below. If you are using Claude Desktop, you can add the server to your configuration with the appropriate command and arguments as shown in examples.
Count a specific letter in the input text.
Count multiple letters at once in the input text.
Count occurrences of a substring within the text.
Compute the frequency distribution of letters in the text.
Break text into its individual characters.
Return the character at a given index.
Get the nth character of a string (1-based).
Return the exact length of the input text.
Reverse the text and detect palindromes.
Compare two texts and report differences.
Provide a word-by-word breakdown of a sentence.
Count across multiple input words in one pass.
List words commonly miscounted and why.
Determine if a given word is tricky to count or analyze.