Integration

Google Cloud Natural Language integration

Google Cloud Natural Language API v1 for text understanding: sentiment analysis at document and sentence level, entity extraction with Wikipedia linking, entity-level sentiment, syntax parsing, content classification into a taxonomy of categories, and text moderation for harmful content.

Connect Google Cloud Natural Language How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Google Cloud Natural Language.Built from the 7 Google Cloud Natural Language tools below, on the connection you add once.

Common Google Cloud Natural Language use cases

routing angry support tickets first
extracting subject-verb-object triples
routing inbound content to the right team
tagging articles with the companies they mention
screening user-generated comments before publishing
finding which product feature drives negative reviews
enriching a document with entities and sentiment in one hop
auto-tagging a knowledge base
extracting product names from reviews
cutting API round trips in a bulk pipeline

What you can do with Google Cloud Natural Language

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.

Annotation, 1 operation

annotate_textAnnotate textPOSTRuns sentiment, entity, syntax, classification and moderation analysis in a single call.

Category, 1 operation

classify_textClassify textPOSTClassifies a text into Google's hierarchical content category taxonomy.

Entity, 1 operation

analyze_entitiesAnalyze entitiesPOSTExtracts people, places, organizations and other entities from a text.

Entity sentiment, 1 operation

analyze_entity_sentimentAnalyze entity sentimentPOSTExtracts entities and the sentiment expressed towards each one.

Moderation, 1 operation

moderate_textModerate textPOSTScores a text against harmful-content categories for moderation.

Sentiment, 1 operation

analyze_sentimentAnalyze sentimentPOSTScores the sentiment of a text at document and sentence level.

Syntax, 1 operation

analyze_syntaxAnalyze syntaxPOSTParses a text into sentences and tokens with part-of-speech and dependency information.

Use Google Cloud Natural Language from Claude Code, Cursor or Codex

Connect Google Cloud Natural Language in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Google Cloud Natural Language 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 Google Cloud Natural Language

Create your workspace
Sign up free. Nothing to install.
Connect Google Cloud Natural Language once
Add your Google Cloud Natural Language 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.

Google Cloud Natural Language integration FAQ

What can you do with the Google Cloud Natural Language integration?

LiveContext exposes 7 operations on Google Cloud Natural Language, covering annotation, category, entity and entity sentiment. Common uses include routing angry support tickets first, extracting subject-verb-object triples and routing inbound content to the right team.