Each one does a single mundane job well, runs as a form, a JSON endpoint and an MCP tool, and never calls a model. Use them free. Pay $5 a month if you want them without limits.
Finds the AI-writing tells in a piece of text (em-dashes, "not just X but Y", triads, stock words, hidden characters) and hands back a cleaned copy.
Free: 20 runs a day, 3,000 chars each. API: POST /api/tells. MCP: check_tells.
What an MCP server's tools/list costs in tokens on every session start, per tool, with the expensive ones named.
Free: 10 runs a day. API: POST /api/manifest-cost. MCP: manifest_cost.
Lints a CLAUDE.md, AGENTS.md or MEMORY.md: the 200-line cap, duplicate rules, contradictions, leftover TODOs, hidden characters.
Free: 20 runs a day. API: POST /api/agent-md-lint. MCP: lint_agent_md.
Turns an MCP endpoint into the install snippet for Claude Code, Claude Desktop, Cursor, Codex and VS Code, and checks the server answers.
Free: 30 runs a day. API: POST /api/mcp-install. MCP: mcp_install_snippets.
Reads a site's robots.txt the way GPTBot, ClaudeBot and the rest do, reports who is allowed, and drafts an llms.txt.
Free: 10 runs a day. API: POST /api/ai-crawlers. MCP: check_ai_crawlers.
Every tool, right here or over the API and MCP, with a daily cap per tool per IP (10 to 30 runs, listed above). Enough to check a post, lint a file, or size up a server before you add it.
/mcp.