
MCP Expr Lang
MCP Expr Lang
README
MCP Expr-Lang
A powerful expression evaluation tool for Claude Desktop using the Model Context Protocol (MCP).
Overview
MCP Expr-Lang provides a seamless integration between Claude AI and the powerful expr-lang expression evaluation engine. This tool allows you to perform complex data manipulations, calculations, and transformations directly within your Claude conversations.
With MCP Expr-Lang, you can:
- Evaluate mathematical expressions
- Transform and filter arrays and objects
- Sort complex data structures
- Perform string manipulations
- Use conditional logic
- And much more!
Installation
Installing via Smithery
To install MCP Expr-Lang for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @ivan-saorin/mcp-expr-lang --client claude
Prerequisites
- Go 1.18 or higher
- Claude Desktop application
- Git
Step 1: Clone the Repository
git clone https://github.com/ivan-saorin/mcp-expr-lang.git
cd mcp-expr-lang
Step 2: Install Dependencies
go mod download
Step 3: Build the Application
For Windows
go build -o bin/server.exe
For macOS/Linux
go build -o bin/server
chmod +x bin/server
Step 4: Configure Claude Desktop
- Open Claude Desktop
- Go to Settings
- Navigate to the "Advanced" section
- Add the following configuration to your
config.json
:
For Windows
{
"mcpServers": {
"eval": {
"command": "C:\\path\\to\\mcp-expr-lang\\bin\\server.exe"
}
}
}
For macOS/Linux
{
"mcpServers": {
"eval": {
"command": "/path/to/mcp-expr-lang/bin/server"
}
}
}
- Save the configuration and restart Claude Desktop
Usage
Once installed, you can use the eval
tool directly in your conversations with Claude. Simply ask Claude to evaluate an expression using the tool.
Basic Example
User: Use eval to calculate "10 + 5 * 3"
Claude: [Uses eval tool]
Result: 10 + 5 * 3 = 25
Complex Example
User: We have users = [{"Name": "John", "Age": 30},{"Name": "Ivan", "Age": 51},{"Name": "Eve", "Age": 15}]
Use eval to calculate "sortBy(users, .Age, "desc")"
Claude: [Uses eval tool]
Result: The expression returns the users sorted by age in descending order:
[
{"Age": 51, "Name": "Ivan"},
{"Age": 30, "Name": "John"},
{"Age": 15, "Name": "Eve"}
]
For more examples please see EXAMPLES
Features
MCP Expr-Lang supports all features of the expr-lang engine, including:
- Arithmetic operations: Addition, subtraction, multiplication, division, modulo, exponentiation
- String operations: Concatenation, length, uppercase/lowercase conversion
- Boolean operations: AND, OR, NOT, comparison operators
- Array operations: Mapping, filtering, reducing, sorting
- Object manipulation: Property access, transformation
- Conditional logic: Ternary operators, if-else expressions
- Built-in functions: Mathematical, string, array, and date functions
For a complete guide to the expression language syntax and capabilities, see the expr-lang documentation.
Troubleshooting
Common Issues
-
Tool not appearing in Claude: Make sure the path in your
config.json
is correct and Claude Desktop has been restarted. -
Execution errors: Check that the expression syntax is correct according to the expr-lang documentation.
-
Permission issues (macOS/Linux): Ensure the server binary has execution permissions (
chmod +x bin/server
).
Getting Help
If you encounter any issues or have questions:
- Check the Issues section on GitHub
- Open a new issue if your problem hasn't been reported
Contributing
Contributions are welcome! If you'd like to improve MCP Expr-Lang:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add some amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- expr-lang for the powerful expression evaluation engine
- mcp-golang for the Model Context Protocol implementation
- Claude AI for the AI assistant platform
Made with ❤️ by Ivan Saorin
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.