# Vectara

> Use this tool when you need to integrate Retrieval-Augmented Generation (RAG) capabilities into conversational AI interfaces, solving problems such as generating human-like responses and providing accurate search results. Vectara MCP Server takes in API queries and authentication credentials, and outputs search results and generated responses, allowing for customization of generation parameters. It is ideal for developers seeking to enhance AI assistants with powerful RAG functionality without directly managing complex APIs.

Canonical page: https://skillsregistry.net/skills/vectara-rag  
JSON: https://api.skillsregistry.net/v1/skills/vectara-rag

## Description

Vectara MCP Server provides a bridge between AI assistants and Vectara's Retrieval-Augmented Generation (RAG) capabilities. Built by Ofer Mendelevitch, it offers two primary tools: one for running RAG queries that return both search results and generated responses, and another for semantic search without generation. The server handles authentication with Vectara's API, manages context configuration for search results, and supports customization of generation parameters including language selection and citation formatting. It's particularly valuable for developers who need to integrate powerful RAG functionality into conversational AI interfaces without managing the complexities of Vectara's API directly.

## Trust

- **Trust score (0–1):** 0.84
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/vectara-rag)
- **Repository:** <https://github.com/vectara/vectara-mcp>

## 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": "vectara-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vectara-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vectara-rag/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