Grade Claude Code, Gemini CLI and Cursor configs for risky permissions; get public config stats.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Headline aggregate numbers from the latest weekly snapshot of public AI agent configs on GitHub.
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Headline aggregate numbers from the latest weekly snapshot of public AI agent configs on GitHub.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}Agent tools ranked by how safely their public configs are set up, with sample sizes and method.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}Grade an AI coding agent permissions config (Claude Code .claude/settings.json, Gemini CLI .gemini/settings.json, mcp.json, or Codex CLI config.toml). Returns a letter grade, findings, a safer config and README badge Markdown. Inputs are not stored or logged.
| Argument | Type | Description |
|---|---|---|
| tool | string | Which tool the config is for |
| config* | string | The config file contents as JSON text, or TOML for Codex config.toml (max 100 KB) |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"config"
],
"properties": {
"tool": {
"enum": [
"claude_code",
"gemini_cli",
"mcp_json",
"cursor_mcp",
"codex"
],
"type": "string",
"default": "claude_code",
"description": "Which tool the config is for"
},
"config": {
"type": "string",
"maxLength": 100000,
"minLength": 1,
"description": "The config file contents as JSON text, or TOML for Codex config.toml (max 100 KB)"
}
}
}