# kortex-search

> kortex-search — kbjama8-kortex-search. Use this tool when you need to conduct comprehensive research across multiple sources, including web, social, code, video, and academic platforms. Kortex-search solves the problem of information overload by fusing 18 sources, re-ranking results, and filtering for freshness, providing a unified and diverse set of relevant answers. It takes in search queries and returns synthesized answers via stdio/HTTP interface, making it suitable for use cases where in-depth research is required, such as coding projects or academic studies.

Canonical page: https://skillsregistry.net/skills/kbjama8-kortex-search  
JSON: https://api.skillsregistry.net/v1/skills/kbjama8-kortex-search

## Description

Unified web-search & research MCP server: fuses 18 sources (web, social, code, video, academic) via weighted RRF, re-ranks with a cross-encoder, MMR-diversifies, freshness-filters, Redis-caches — then synthesizes cited answers with DeepSeek. stdio/HTTP, lazy models. Client-agnostic: Works with Claude Code, OpenCode or any other MCP host.

## Trust

- **Trust score (0–1):** 0.26
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/kbjama8/kortex-search)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "kbjama8-kortex-search"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kbjama8-kortex-search` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kbjama8-kortex-search/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt