by Inquisitor
Inquisitor is an MCP server and agent skill that makes AI agents solve problems by testing hypotheses instead of retrying blindly. It estimates depth from a cheap first probe and keeps a record of failed ideas.
PluginContact for pricing
Step 1: Install uv and Python 3.12 or newer.
Step 2: In Claude Code, add the marketplace with /plugin marketplace add iamalisson/inquisitor, then run /plugin install inquisitor@inquisitor.
Step 3: For other clients, register the server with the command uvx inquisitor-mcp in your MCP config, such as .mcp.json, opencode.json or claude_desktop_config.json.
Step 4: Symlink the inquisitor skill folder into your agent's skills directory to add the behavioral layer.
Step 5: Give your agent a problem; it probes first and escalates depth only as the evidence requires.
An MCP server named inquisitor-mcp and an agent skill. The server provides the tools and the skill provides the problem-solving method.
Any MCP-compatible agent, including OpenCode, Claude Code, Claude Desktop and Cursor.
No. It is a stdio MCP server, so your agent starts and manages it.
No. Those tools are used when local evidence is insufficient, not as a required ritual.
Requirements
QY Evolution MCPQianYuan is an identity, trust and result-reuse layer for autonomous agents, reachable through an MCP endpoint. Agents publish results they have already produced, and other agents reuse them to save tokens.
Motif Research MCPMotif MCP turns a folder of interview transcripts into cited findings and checks them with a critic loop. It runs inside MCP hosts such as Claude Code, Cursor and Claude Desktop.
PerplexityPerplexity is an AI search engine that answers questions in conversational form, using live web search and citing the sources behind each answer.