Integration

Cohere integration

Enterprise-grade natural language processing API for text understanding and generation. Access embedding models for semantic search, classification and clustering capabilities, text generation, and retrieval-augmented generation. Designed for building scalable NLP applications with production-ready reliability.

Connect Cohere How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Cohere.Built from the 27 Cohere tools below, on the connection you add once.

Common Cohere use cases

model selection
job monitoring
data management
model discovery
model verification
capability check
result retrieval
resource management
RAG setup
token counting

What you can do with Cohere

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.

Connector, 4 operations

create_connectorCreate connectorPOSTCreates a connector for RAG retrieval. Configure external data sources for grounded chat responses.
delete_connectorDelete connectorDELETEDeletes a connector. Remove RAG data sources that are no longer needed.
get_connectorGet connectorGETGets details of a specific connector. Retrieve configuration and status of RAG data sources.
list_connectorsList connectorsGETLists all connectors for RAG. View configured data sources for grounded chat responses.

Dataset, 4 operations

create_datasetCreate datasetPOSTCreates a dataset for batch embedding. Upload documents for processing with embed jobs.
delete_datasetDelete datasetDELETEDeletes a dataset. Remove uploaded or generated datasets to free storage.
get_datasetGet datasetGETGets details of a specific dataset. Retrieve metadata, validation status, and download links.
list_datasetsList datasetsGETLists all datasets. View uploaded and generated datasets with metadata and status.

Embed job, 4 operations

cancel_embed_jobCancel embed jobPOSTCancels a running embed job. Stop batch embedding operations that are no longer needed.
create_embed_jobCreate embed jobPOSTCreates a batch embedding job for large datasets. Process 100K+ documents efficiently with optimized batching.
get_embed_jobGet embed jobGETGets details of a specific embed job. Check status, progress, and results of batch embedding operations.
list_embed_jobsList embed jobsGETLists all embedding jobs. View history of batch embedding jobs with their status and metadata.

Text, 3 operations

classifyClassifyPOSTClassifies text into categories. Few-shot classification using examples to categorize new inputs with confidence scores.
generateGeneratePOSTGenerates text completions with Cohere. Create multiple text generations from prompts with likelihood scoring.
summarizeSummarizePOSTSummarizes text content. Generate concise summaries with configurable length, format, and extractiveness level.

Finetuned model, 2 operations

get_finetuned_modelGet finetuned modelGETGets details of a fine-tuned model. Retrieve training configuration, status, and performance metrics.
list_finetuned_modelsList finetuned modelsGETLists all fine-tuned models. View custom models trained on your data with status and metadata.

Model, 2 operations

get_modelGet modelGETGets details of a specific Cohere model. Retrieve capabilities, context length, and supported endpoints for a model.
list_modelsList modelsGETLists available Cohere models. View all accessible models including generation, embedding, and reranking models.

Token, 2 operations

detokenizeDetokenizePOSTConverts tokens back to text. Transform token ID arrays into human-readable text for debugging and analysis.
tokenizeTokenizePOSTTokenizes text into tokens. Convert text to token IDs for understanding model input processing and cost estimation.

Api key, 1 operation

check_api_keyCheck api keyPOSTValidates API key. Verify that your Cohere API key is valid and active.

Audio, 1 operation

transcribe_audioTranscribe audioPOSTTranscribes audio to text with Cohere Transcribe. Convert speech recordings into accurate written text.

Chat, 1 operation

chatChatPOSTGenerates conversational responses with Cohere. Create AI chat interactions with RAG connectors and web search integration.

Document, 1 operation

rerankRerankPOSTReranks documents by query relevance. Use neural reranking to improve search result ordering with relevance scores.

Embedding, 1 operation

embedEmbedPOSTGenerates text embeddings with Cohere. Convert text to vectors optimized for search_document or search_query contexts.

Language, 1 operation

detect_languageDetect languagePOSTDetects language of text. Identify the language of input texts with confidence scores for routing and processing.

Use Cohere from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Cohere once
Add your Cohere 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.

Cohere integration FAQ

What can you do with the Cohere integration?

LiveContext exposes 27 operations on Cohere, covering connector, dataset, embed job and text. Common uses include model selection, job monitoring and data management.