Server data from the Official MCP Registry
Ai Gateway tools for AI agents. Capabilities: route request, list models, cost estimator. Bu...
Ai Gateway tools for AI agents. Capabilities: route request, list models, cost estimator. Bu...
This MCP server has critical security vulnerabilities that make it unsafe to deploy. The server imports an external auth middleware from a hardcoded, non-standard path (`~/clawd/meok-labs-engine/shared`) that is not version-controlled or auditable, creating a supply chain risk. Additionally, the server lacks input validation on all user-facing parameters, making it vulnerable to injection attacks. The authentication mechanism is opaque and cannot be verified. While the server's intended functionality (model routing and cost estimation) is reasonable for a developer tool, the architectural issues and missing security controls are severe. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
6 files analyzed · 14 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-csoai-org-ai-gateway-mcp": {
"args": [
"-y",
"ai-gateway-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
Add .well-known/mcp discovery, CI workflow, persistence layer
Installation · Docs · Report Bug
pip install ai-gateway-mcp
# or
npm install -g @meok-ai/ai-gateway-mcp
See the project repository for full documentation and examples.
MIT © CSOAI
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.