Can I use Anthropic as a CLI?

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

Can I expose Anthropic through MCP?

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

Where are Anthropic credentials stored?

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

Can I deny write access for Anthropic MCP tools?

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

Anthropic CLI for AI Agents

Use the Anthropic CLI from KosmoKrator to call Anthropic tools headlessly, return JSON, inspect schemas, and automate workflows from coding agents, scripts, and CI.

7 functions 6 read 1 write API key auth

Submit Anthropic feedback View package source

Anthropic CLI Setup

Anthropic can be configured headlessly with `kosmokrator integrations:configure anthropic`.

# Install KosmoKrator first if it is not available on PATH.
curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash

# Configure and verify this integration.
kosmokrator integrations:configure anthropic --set api_key="$ANTHROPIC_API_KEY" --enable --read allow --write ask --json
kosmokrator integrations:doctor anthropic --json
kosmokrator integrations:status --json

Credentials

Authentication type: API key api_key. Configure credentials once, then use the same stored profile from scripts, coding CLIs, Lua code mode, and the MCP gateway.

Key	Env var	Type	Required	Label
`api_key`	`ANTHROPIC_API_KEY`	Secret `secret`	yes	API Key
`url`	`ANTHROPIC_URL`	URL `url`	no	API Base URL

Call Anthropic Headlessly

Use the generic call form when another coding CLI or script needs a stable universal interface.

kosmo integrations:call anthropic.anthropic_list_messages '{
  "model": "example_model",
  "limit": 1,
  "before_id": "example_before_id",
  "after_id": "example_after_id"
}' --json

Use the provider shortcut form for shorter human-facing commands.

kosmo integrations:anthropic anthropic_list_messages '{
  "model": "example_model",
  "limit": 1,
  "before_id": "example_before_id",
  "after_id": "example_after_id"
}' --json

Agent Discovery Commands

These commands return structured output for coding agents that need to inspect capabilities before choosing a function.

kosmo integrations:docs anthropic --json
kosmo integrations:docs anthropic.anthropic_list_messages --json
kosmo integrations:schema anthropic.anthropic_list_messages --json
kosmo integrations:search "Anthropic" --json
kosmo integrations:list --json

All CLI Functions

Every function below can be called headlessly. The generic form is stable across all integrations; the provider shortcut is shorter but specific to Anthropic.

`anthropic.anthropic_list_messages`

Read read

List messages in the Anthropic conversation history. Returns paginated message resources with optional filtering by model, date, and ID.

Parameters: model, limit, before_id, after_id

Generic CLI call

kosmo integrations:call anthropic.anthropic_list_messages '{"model":"example_model","limit":1,"before_id":"example_before_id","after_id":"example_after_id"}' --json

Provider shortcut

kosmo integrations:anthropic anthropic_list_messages '{"model":"example_model","limit":1,"before_id":"example_before_id","after_id":"example_after_id"}' --json

`anthropic.anthropic_create_message`

Write write

Send a prompt to Claude and receive an AI-generated response. Supports multi-turn conversations, system prompts, temperature control, and configurable output length.

Parameters: model, messages, max_tokens, system, temperature, top_p, stop_sequences, stream

Generic CLI call

kosmo integrations:call anthropic.anthropic_create_message '{"model":"example_model","messages":"example_messages","max_tokens":1,"system":"example_system","temperature":1,"top_p":1,"stop_sequences":"example_stop_sequences","stream":true}' --json

Provider shortcut

kosmo integrations:anthropic anthropic_create_message '{"model":"example_model","messages":"example_messages","max_tokens":1,"system":"example_system","temperature":1,"top_p":1,"stop_sequences":"example_stop_sequences","stream":true}' --json

`anthropic.anthropic_list_models`

Read read

List available Anthropic AI models. Returns model identifiers, creation dates, and display names.

Parameters: limit, before_id, after_id

Generic CLI call

kosmo integrations:call anthropic.anthropic_list_models '{"limit":1,"before_id":"example_before_id","after_id":"example_after_id"}' --json

Provider shortcut

kosmo integrations:anthropic anthropic_list_models '{"limit":1,"before_id":"example_before_id","after_id":"example_after_id"}' --json

`anthropic.anthropic_get_model`

Read read

Get detailed information about a specific Anthropic model, including its display name, creation date, and capabilities.

Parameters: id

Generic CLI call

kosmo integrations:call anthropic.anthropic_get_model '{"id":"example_id"}' --json

Provider shortcut

kosmo integrations:anthropic anthropic_get_model '{"id":"example_id"}' --json

`anthropic.anthropic_list_workspaces`

Read read

List Anthropic workspaces. Returns workspace identifiers, names, and configuration details.

Parameters: limit, before_id, after_id

Generic CLI call

kosmo integrations:call anthropic.anthropic_list_workspaces '{"limit":1,"before_id":"example_before_id","after_id":"example_after_id"}' --json

Provider shortcut

kosmo integrations:anthropic anthropic_list_workspaces '{"limit":1,"before_id":"example_before_id","after_id":"example_after_id"}' --json

`anthropic.anthropic_get_workspace`

Read read

Get detailed information about a specific Anthropic workspace, including its name, configuration, and usage settings.

Parameters: id

Generic CLI call

kosmo integrations:call anthropic.anthropic_get_workspace '{"id":"example_id"}' --json

Provider shortcut

kosmo integrations:anthropic anthropic_get_workspace '{"id":"example_id"}' --json

`anthropic.anthropic_get_current_user`

Read read

Get the authenticated user's profile and account information.

Parameters: none

Generic CLI call

kosmo integrations:call anthropic.anthropic_get_current_user '{}' --json

Provider shortcut

kosmo integrations:anthropic anthropic_get_current_user '{}' --json

Function Schemas

Use these parameter tables when building CLI payloads without calling integrations:schema first.

`anthropic.anthropic_list_messages`

List messages in the Anthropic conversation history. Returns paginated message resources with optional filtering by model, date, and ID.

Operation: Read read
Schema command: kosmo integrations:schema anthropic.anthropic_list_messages --json

Parameter	Type	Required	Description
`model`	string	no	Filter messages by model ID (e.g., "claude-sonnet-4-20250514").
`limit`	integer	no	Maximum number of messages to return per page (default: 20, max: 1000).
`before_id`	string	no	Message ID used for cursor-based pagination — return messages before this ID.
`after_id`	string	no	Message ID used for cursor-based pagination — return messages after this ID.

`anthropic.anthropic_create_message`

Send a prompt to Claude and receive an AI-generated response. Supports multi-turn conversations, system prompts, temperature control, and configurable output length.

Operation: Write write
Schema command: kosmo integrations:schema anthropic.anthropic_create_message --json

Parameter	Type	Required	Description
`model`	string	yes	The model to use (e.g., "claude-sonnet-4-20250514", "claude-haiku-4-20250414").
`messages`	array	yes	Array of message objects with "role" ("user" or "assistant") and "content" (string or array of content blocks).
`max_tokens`	integer	no	Maximum number of tokens to generate in the response (default: 4096).
`system`	string	no	System prompt to set the behavior and context for Claude.
`temperature`	number	no	Controls randomness in generation (0.0–1.0). Lower values are more deterministic.
`top_p`	number	no	Nucleus sampling parameter (0.0–1.0). Limits cumulative probability of tokens considered.
`stop_sequences`	array	no	Array of strings that will cause the model to stop generating if encountered.
`stream`	boolean	no	Whether to stream the response incrementally (default: false).

`anthropic.anthropic_list_models`

List available Anthropic AI models. Returns model identifiers, creation dates, and display names.

Operation: Read read
Schema command: kosmo integrations:schema anthropic.anthropic_list_models --json

Parameter	Type	Required	Description
`limit`	integer	no	Maximum number of models to return per page (default: 20, max: 1000).
`before_id`	string	no	Model ID used for cursor-based pagination — return models before this ID.
`after_id`	string	no	Model ID used for cursor-based pagination — return models after this ID.

`anthropic.anthropic_get_model`

Get detailed information about a specific Anthropic model, including its display name, creation date, and capabilities.

Operation: Read read
Schema command: kosmo integrations:schema anthropic.anthropic_get_model --json

Parameter	Type	Required	Description
`id`	string	yes	The model identifier (e.g., "claude-sonnet-4-20250514").

`anthropic.anthropic_list_workspaces`

List Anthropic workspaces. Returns workspace identifiers, names, and configuration details.

Operation: Read read
Schema command: kosmo integrations:schema anthropic.anthropic_list_workspaces --json

Parameter	Type	Required	Description
`limit`	integer	no	Maximum number of workspaces to return per page (default: 20, max: 1000).
`before_id`	string	no	Workspace ID used for cursor-based pagination — return workspaces before this ID.
`after_id`	string	no	Workspace ID used for cursor-based pagination — return workspaces after this ID.

`anthropic.anthropic_get_workspace`

Get detailed information about a specific Anthropic workspace, including its name, configuration, and usage settings.

Operation: Read read
Schema command: kosmo integrations:schema anthropic.anthropic_get_workspace --json

Parameter	Type	Required	Description
`id`	string	yes	The workspace identifier.

`anthropic.anthropic_get_current_user`

Get the authenticated user's profile and account information.

Operation: Read read
Schema command: kosmo integrations:schema anthropic.anthropic_get_current_user --json

Parameter	Type	Required	Description
No parameters.

Permissions

Headless calls still follow the integration read/write permission policy. Configure read/write defaults with integrations:configure. Add --force only for trusted automation that should bypass that policy.