Runtime proxy for MCP security, cost governance & audit
Runtime proxy for MCP security, cost governance & audit
Runtime enforcement, policy control, and full audit trail for every AI action.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"mastyf-ai": {
"command": "npx",
"args": ["-y", "fails"],
"env": {
"OLLAMA_BASE_URL": "your-value",
"MASTYF_AI_LLM_PROVIDER": "your-value",
"MASTYF_AI_LLM_MODEL": "your-value",
"MASTYF_AI_DB_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| OLLAMA_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| MASTYF_AI_LLM_PROVIDER | Configuration value read at startup. | Optional |
| MASTYF_AI_LLM_MODEL | Configuration value read at startup. | Optional |
| MASTYF_AI_DB_PATH | Filesystem location the server is allowed to use. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
Run `mcp-server-autoprovisioner init`, or update configuration as follows
Integrates with GitHub's API through the Model Context Protocol (MCP).
一个用于分析 GitHub 用户 Star 项目的 MCP (Model Context Protocol) 服务器。