Cohere MCP integration for AI agents.
Connect AI agents to Cohere through 3 structured actions, including chat, embed texts, and rerank documents. Review authentication, inputs, workflows, and sa…
- ACTION CONTRACTS
- 3
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Cohere integration exposes
The Cohere Agent App exposes 3 provider-backed actions for ai work. Its current contract lets an authorized agent generate a synchronous text response using the cohere chat api, generate embeddings for text inputs using the cohere embed api, and rank text documents by relevance to a query using the cohere rerank api. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Cohere account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Cohere capabilities.
Showing 3 of 3 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
chatREVIEWGenerate a synchronous text response using the Cohere Chat API.
INPUTS: model / messages / tools / strict_tools / documents
embed_textsREVIEWGenerate embeddings for text inputs using the Cohere Embed API.
INPUTS: model / input_type / texts / max_tokens / output_dimension
rerank_documentsREVIEWRank text documents by relevance to a query using the Cohere Rerank API.
INPUTS: model / query / documents / top_n / max_tokens_per_doc
INPUT CONTRACTS
Know what the action needs before it runs.
chat
modelREQUIRED- The name of a compatible Cohere chat model.
messagesREQUIRED- The ordered conversation messages to send to Cohere.
toolsOPTIONAL- Function tools available to the model.
strict_toolsOPTIONAL- Whether tool calls must strictly follow the tool definition.
documentsOPTIONAL- Documents that the model can cite while generating the response.
embed_texts
modelREQUIRED- The Cohere embedding model identifier.
input_typeREQUIRED- The type of input passed to the embedding model.
textsREQUIRED- Text strings for the model to embed.
max_tokensOPTIONAL- The maximum number of tokens to embed per input.
output_dimensionOPTIONAL- The number of dimensions for embed-v4 and newer models.
rerank_documents
modelREQUIRED- The Cohere rerank model identifier.
queryREQUIRED- The search query used to rank documents.
documentsREQUIRED- Texts that will be compared to the query.
top_nOPTIONAL- Maximum number of rerank results to return.
max_tokens_per_docOPTIONAL- Maximum tokens to keep per document before ranking.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Chat
Generate a synchronous text response using the Cohere Chat API. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
chatVerify with Embed Texts
Generate embeddings for text inputs using the Cohere Embed API. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
embed_textsSAFETY BOUNDARY
Operate Cohere with explicit limits
- Authorize Cohere with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned Cohere data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Cohere rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Cohere task completed successfully.
CONNECTION MODEL
API key
Cohere API key used with the Authorization Bearer header. Create or copy one from https://dashboard.cohere.com/api-keys.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 0
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 3
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Cohere.