AI & ML22 toolsPaste one API key
Cohere integration for AI agents
Cohere provides enterprise language and multimodal AI models for chat, embeddings, reranking, classification, and related workflows.
Use it from your agent
One ClawLink account serves every agent you run. Pick the guide for yours, or connect Cohere once and call the same tools from all of them.
Cohere for OpenClawInstall, pair, connect, first prompt
Cohere for Hermes AgentInstall, pair, connect, first promptMCPClaude Code, Cursor, any MCP clientCLI login or the remote MCP serverSetup
Connect Cohere through ClawLink's hosted setup.
- Auth: Paste one API key. The credential stays on the ClawLink server; your agent holds only a ClawLink key you can revoke.
- Where: the ClawLink dashboard, or ask your agent to connect it.
What your agent can do
Cohere exposes 22 tools through ClawLink. The 21 most used are listed here; your agent sees all of them.
| Tool | What it does | Kind |
|---|---|---|
cohere_check_api_key | Check whether the connected Cohere API key is valid and return its organization and owner | Read |
cohere_get_batch | Retrieve one asynchronous Cohere batch's status and counters by batch ID | Read |
cohere_get_dataset | Retrieve one Cohere dataset by ID, including its asynchronous validation state, schema, files | Read |
cohere_get_dataset_usage | Read the organization's Cohere dataset-storage consumption in bytes | Read |
cohere_get_embed_job | Retrieve one Cohere asynchronous embedding job's current status, model, and input and output | Read |
cohere_get_model | Retrieve a Cohere model's endpoint compatibility, context size, features, tokenizer, and | Read |
cohere_list_batches | Return one page of asynchronous Cohere batches and their statuses without creating or | Read |
cohere_list_datasets | Return one offset-based page of Cohere datasets, optionally filtered by type, validation | Read |
cohere_list_embed_jobs | List Cohere asynchronous embedding jobs and their current statuses | Read |
cohere_list_models | Discover Cohere model names and capabilities, optionally filtered to an endpoint or its default | Read |
cohere_cancel_batch | Cancel one in-progress Cohere batch | Write |
cohere_cancel_embed_job | Irreversibly cancel one active Cohere asynchronous embed job by ID | Write |
cohere_chat | Generate one non-streaming Cohere chat response from an ordered conversation, optionally using | Read |
cohere_create_batch | Start one asynchronous Cohere batch from an existing validated batch request dataset and return | Write |
cohere_create_dataset | Upload a Cohere dataset and start asynchronous validation | Write |
cohere_create_embed_job | Start one asynchronous Cohere embedding job for a validated embed-input dataset and return | Write |
cohere_detokenize_tokens | Convert ordered Cohere token IDs back to text using the tokenizer for an explicit matching model | Read |
cohere_embed_inputs | Create v2 embeddings from exactly one input form: text strings, image data URIs, or structured | Read |
cohere_rerank_documents | Rank text documents by relevance to a query and return the highest-scoring source documents | Read |
cohere_tokenize_text | Convert text into token IDs with an explicit Cohere model | Read |
cohere_transcribe_audio | Transcribe an uploaded audio file to text with a Cohere transcription model | Read |
