Integration

Vectara integration

Enterprise-grade generative AI search platform with built-in RAG capabilities. Build semantic search, question answering, and conversational AI applications with neural retrieval and LLM-powered summarization.

Connect Vectara How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Vectara.Built from the 12 Vectara tools below, on the connection you add once.

Common Vectara use cases

Build chatbots
Remove unused indexes
Simple semantic search
Upload PDFs for search
View indexed documents
Create new search index
List all search indexes
Remove outdated content
Semantic document search
Check corpus configuration

What you can do with Vectara

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Corpus, 5 operations

create_corpusCreate corpusPOSTCreates a new corpus for indexing and searching documents.
delete_corpusDelete corpusDELETEPermanently deletes a corpus and all indexed documents.
get_corpusGet corpusGETRetrieves detailed information about a specific corpus.
query_corpusQuery corpusPOSTPerforms advanced search with optional RAG generation on a single corpus.
search_corpusSearch corpusGETPerforms a simple search on a single corpus.

Document, 3 operations

delete_documentDelete documentDELETERemoves a document from a corpus.
index_documentIndex documentPOSTIndexes a document into a corpus for semantic search.
list_documentsList documentsGETLists all documents indexed in a corpus.

Chat, 1 operation

chatChatPOSTStarts a conversational search session using Vectara's deprecated create-chat endpoint.

Corpora, 1 operation

list_corporaList corporaGETRetrieves all corpora (document collections) in your Vectara account.

File, 1 operation

upload_fileUpload filePOSTUploads a file for automatic parsing and indexing.

Query, 1 operation

queryQueryPOSTPerforms semantic search with optional RAG generation.

Use Vectara from Claude Code, Cursor or Codex

Connect Vectara in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Vectara operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Vectara

Create your workspace
Sign up free. Nothing to install.
Connect Vectara once
Add your Vectara connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Vectara integration FAQ

What can you do with the Vectara integration?

LiveContext exposes 12 operations on Vectara, covering corpus, document, chat and corpora. Common uses include Build chatbots, Remove unused indexes and Simple semantic search.