
Infobroker is an MCP server that puts web search, page extraction, citations and claim verification behind one set of tools. Twenty-one of its providers work without configuration.
PluginContact for pricing
Step 1: Install Node.js 24 or newer.
Step 2: Start the server with npx -y infobroker, or clone the repository and run npm install and npm run start.
Step 3: Add the server to your MCP client config; for OpenCode, also point instructions and skills.paths at the package to activate the bundled skills.
Step 4: Optionally set environment variables such as INFOBROKER_BRAVE_API_KEY to enable keyed providers.
Step 5: Ask your assistant to search, fetch a page, get citations or verify a claim.
No. Twenty-one providers work with no configuration. Brave, Exa, Tavily and Yep unlock with keys, and SearXNG can be self-hosted.
It searches several independent sources, extracts claims and reconciles them. The report separates confirmed, contested and unverified findings and gives confidence scores.
Searches, fetches and verification results are cached in a local knowledge base. Retrieval uses an embedding model on your machine, and the README says content is not sent to a third party.
Node.js 24 or newer.
Requirements
World Model MCPWorld Model MCP is a local MCP server from PuterVision that keeps a persistent 3D and 2D spatial model of entities for AI agents. It tracks objects, simulates movement and checks collisions without any LLM in the loop.GAIAGAIA is a benchmark of more than 450 questions with unambiguous answers for evaluating LLMs that use tools, search and prompting. It is for teams measuring how well AI assistants handle multi-step tasks.EgoProEgoPro is Lightwheel's 10,000-hour egocentric dataset pairing synchronized head and wrist video with 3D hand pose. It is for teams training embodied AI on human demonstrations.