Can I use Cohere as a CLI?

Yes. KosmoKrator exposes a Cohere CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Cohere through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Cohere tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Cohere credentials stored?

Cohere credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Cohere MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

data

Cohere MCP, CLI, and Lua Integration for AI Agents

Cohere integration docs for AI agents: MCP gateway setup, Cohere CLI commands, Lua API reference, credentials, and function schemas.

Cohere for agents

Credentials can be configured manually in web or CLI hosts.

Use this integration from Lua code mode, the headless integrations CLI, or the KosmoKrator MCP gateway. The same package metadata powers all three surfaces.

Agent Surfaces

Cohere CLIHeadless setup, JSON output, direct function calls. Cohere MCPExpose selected tools to local MCP clients. Cohere LuaAgent-facing namespace and Lua reference. FeedbackReport missing tools, auth issues, or bad metadata.

Machine-Readable Metadata

integration_slug: cohere
route_slug: cohere
package: cohere
auth_strategy: api_key
cli_setup_supported: true
cli_runtime_supported: true
mcp_gateway_supported: true
lua_supported: true

Function Catalog

Function	Type	Parameters	Description
`cohere.cohere_chat`	Read `read`	21	Generate a non-streaming response with Cohere v2 Chat. Supports messages, documents, tools, citations, JSON response format, safety mode, sampling controls, and reasoning configuration.
`cohere.cohere_embed`	Read `read`	10	Create Cohere v2 embeddings for texts, image data URIs, or mixed inputs. Use input_type to match the downstream task such as search_document, search_query, classification, clustering, or image.
`cohere.cohere_rerank`	Read `read`	6	Rerank a list of documents for a search query using Cohere v2 Rerank. Documents may be strings; structured data should be converted to YAML strings before calling.
`cohere.cohere_tokenize`	Read `read`	2	Tokenize text with the tokenizer used by a Cohere model. Use this before budgeting prompts or debugging token boundaries.
`cohere.cohere_detokenize`	Read `read`	2	Convert Cohere model token IDs back to text with the tokenizer used by a specific model.
`cohere.cohere_list_models`	Read `read`	4	List Cohere models with optional pagination and endpoint/default filters.
`cohere.cohere_get_model`	Read `read`	1	Get Cohere model metadata including compatible endpoints, deprecation state, context length, features, and sampling defaults.
`cohere.cohere_create_embed_job`	Write `write`	5	Start a Cohere embed job for a validated embed-input dataset. Use list/get embed job to track completion and read output_dataset_id.
`cohere.cohere_list_embed_jobs`	Read `read`	0	List Cohere embed jobs for the authenticated user.
`cohere.cohere_get_embed_job`	Read `read`	1	Get details for a Cohere embed job, including status and output_dataset_id when complete.
`cohere.cohere_cancel_embed_job`	Write `write`	1	Cancel an active Cohere embed job. Cohere may bill for work already processed, and partial results are not returned.
`cohere.cohere_create_dataset`	Write `write`	12	Upload a dataset file to Cohere. For embed jobs, use type=embed-input and a JSONL/CSV/TXT file that matches Cohere dataset rules.
`cohere.cohere_list_datasets`	Read `read`	5	List Cohere datasets with optional datasetType, before, after, limit, and offset filters.
`cohere.cohere_get_dataset`	Read `read`	1	Get a Cohere dataset by ID, including validation status, schema, dataset parts, and metrics.
`cohere.cohere_delete_dataset`	Write `write`	1	Delete a Cohere dataset by ID. Cohere also automatically expires datasets after its retention period.
`cohere.cohere_get_dataset_usage`	Read `read`	0	Get Cohere organization dataset storage usage in bytes.
`cohere.cohere_create_audio_transcription`	Read `read`	5	Transcribe an audio file with Cohere v2 Audio Transcriptions. Provide file content directly; supported extensions include flac, mp3, mpeg, mpga, ogg, and wav.
`cohere.cohere_classify`	Read `read`	5	Classify text with Cohere v1 Classify. Upstream marks this endpoint deprecated; prefer newer chat or embedding workflows unless you need legacy classify compatibility.