Server data from the Official MCP Registry
Secure Python sandbox for data optimization and Matplotlib rendering via x402 microtransactions.
About
Secure Python sandbox for data optimization and Matplotlib rendering via x402 microtransactions.
Security Report
This MCP server has critical security vulnerabilities that make it unsuitable for production use. The primary risk is the `execute_code_securely` tool, which accepts arbitrary Python code and sends it to a remote endpoint without any validation, sanitization, or sandboxing on the client side. Combined with the requirement to store a private EVM key in environment variables (which the code reads unsafely), this creates multiple attack vectors for credential theft, data exfiltration, and unauthorized financial transactions. The server also lacks input validation, error handling, and audit logging for security-sensitive operations. Supply chain analysis found 8 known vulnerabilities in dependencies (2 critical, 4 high severity). Package verification found 1 issue.
4 files analyzed · 20 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
What You'll Need
Set these up before or after installing:
How to Install
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-codelad1304-agentic-compute": {
"env": {
"EVM_PRIVATE_KEY": "your-evm-private-key-here"
},
"args": [
"agentic-compute-mcp-codelad1304"
],
"command": "uvx"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
agentic-compute-mcp
Agentic API Platform: MCP Bridge
mcp-name: io.github.codelad1304/agentic-compute
A high-performance Model Context Protocol (MCP) server providing premium computational services to autonomous AI agents. This bridge connects Claude and other MCP-compatible LLMs to secure, cloud-hosted endpoints for advanced mathematical optimization and data visualization.
Built with FastMCP and FastAPI, this system leverages the x402 protocol for automated Machine-to-Machine (M2M) microtransactions on the Base network (USDC settlement).
Features
Native MCP Integration: Instantly expose computational tools to Claude Desktop and other MCP clients.
M2M Monetization (x402): Seamless crypto-based settlement per API call. Agents automatically pay for compute using USDC on Base.
Bypass LLM UI Limits: Overcomes LLM token limits by processing massive data structures (like Base64 image matrices) efficiently in the backend.
Available Tools (Endpoints)
This MCP server currently exposes the following premium tools to AI agents:
- execute_code (Cost: 0.10 USDC)
-
Executes arbitrary, agent-generated Python code in a highly secure, isolated remote Azure sandbox.
-
Capabilities: Protects the host machine from untrusted code execution while returning standard output (stdout) and standard error (stderr) directly to the agent.
- sanitize_csv (Cost: 0.25 USDC)
-
Cleans and normalizes raw, unstructured CSV data into strict JSON arrays.
-
Capabilities: Automatically normalizes headers, handles null values, and drops empty rows, preparing messy data for immediate mathematical modeling.
- optimize_ga (Cost: 0.50 USDC)
-
Runs a high-performance Genetic Algorithm (GA) to optimize data models (Polynomial, Logistic, Exponential).
-
Capabilities: Smart parameter initialization, proportional mutation to prevent premature convergence, and high-accuracy curve fitting (achieves <1% MAPE).
-
Ideal for: Load forecasting, predictive modeling, and complex hyperparameter tuning.
- generate_plot (Cost: 0.30 USDC)
-
A Matplotlib-based rendering engine that generates production-ready charts and graphs.
-
Capabilities: Bypasses LLM token generation limits by natively drawing data and returning lightweight base64 image streams directly to the host machine.
-
Ideal for: Visualizing optimization results, time-series data, and mathematical models.
Installation & Setup
- Install via PyPI:
pip install agentic-compute-mcp-codelad1304
- Configure Environment Variables: Create a .env file or export the following variable in your terminal to allow your local MCP client to process agentic payments:
export EVM_PRIVATE_KEY=your_private_key_here
Using with Claude Desktop
- To install this server for Claude Desktop, add the following to your claude_desktop_config.json:
{
"mcpServers": {
"agentic-compute": {
"command": "agentic-compute-mcp",
"args": [],
"env": {
"EVM_PRIVATE_KEY": "your_private_key_here"
}
}
}
}
License
This project is licensed under the MIT License - see the LICENSE file for details.
mcp-name: io.github.codelad1304/agentic-compute
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Git
Freeby Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MarkItDown
Freeby Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
FinAgent
Freeby mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.