"author:Merlin-Bedford" matching MCP servers:

Enables AI agents to perform keyless web search through a self-hosted SearXNG instance, returning engine-transparent results and configuration guidance when JSON output is disabled.

Enables agents to repair the malformed JSON that language models actually emit — stripping code fences and prose, normalizing smart quotes, trailing commas, single-quoted strings and unquoted keys — and to check that required keys are present, all deterministically and offline before re-asking the model.

Enables AI agents to convert plain-text outlines into complete, standalone, offline HTML presentations, with slide counts and byte metrics. Also validates outlines for slide and bullet constraints before building.