Integration

Azure AI Search integration

Azure AI Search data plane REST API, formerly Azure Cognitive Search. Run keyword, vector, hybrid and semantic queries over an index, look up and push documents, get suggestions and autocomplete terms, and manage indexes, indexers and data sources. Requests go directly to the search service's own host and every call carries an api-version query parameter plus the api-key header holding an admin or query key.

Connect Azure AI Search How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Azure AI Search.Built from the 17 Azure AI Search tools below, on the connection you add once.

Common Azure AI Search use cases

fetching the full record behind a search hit
removing an experimental index after a migration
finding the indexer name that feeds a given index
adding a new retrievable field to an existing index
keeping a search index in sync with a source database
monitoring how close an index is to its storage quota
showing matching products while a user is still typing
completing a shopper's query in a search-as-you-type box
discovering which index to query before running a search
alerting when a nightly indexer run ends with failed items

What you can do with Azure AI Search

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.

Index, 6 operations

create_indexCreate indexPOSTCreates a search index from a field definition.
create_or_update_indexCreate or update indexPUTCreates or replaces an index definition.
delete_indexDelete indexDELETEDeletes an index and everything in it.
get_indexGet indexGETRetrieves an index definition.
get_index_statisticsGet index statisticsGETReturns document count and storage size for an index.
list_indexesList indexesGETLists every index on the service.

Indexer, 4 operations

get_indexer_statusGet indexer statusGETReturns an indexer's current state and recent run history.
list_indexersList indexersGETLists every indexer on the service.
reset_indexerReset indexerPOSTResets an indexer's change tracking state.
run_indexerRun indexerPOSTTriggers an indexer run on demand.

Document, 3 operations

index_documentsIndex documentsPOSTPushes a batch of document uploads, merges or deletions into an index.
lookup_documentLookup documentGETLooks up one document by its index key.
search_documentsSearch documentsPOSTSearches an index and returns the matching documents.

Data source, 1 operation

list_data_sourcesList data sourcesGETLists the data sources indexers can read from.

Service, 1 operation

get_service_statisticsGet service statisticsGETReturns service-wide usage counters and quotas.

Suggestion, 1 operation

suggestSuggestPOSTReturns type-ahead document suggestions for a partial query.

Term, 1 operation

autocompleteAutocompletePOSTCompletes partially typed query terms.

Use Azure AI Search from Claude Code, Cursor or Codex

Connect Azure AI Search in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Azure AI Search 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 Azure AI Search

Create your workspace
Sign up free. Nothing to install.
Connect Azure AI Search once
Add your Azure AI Search 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.

Azure AI Search integration FAQ

What can you do with the Azure AI Search integration?

LiveContext exposes 17 operations on Azure AI Search, covering index, indexer, document and data source. Common uses include fetching the full record behind a search hit, removing an experimental index after a migration and finding the indexer name that feeds a given index.