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 Headless Automation

Use the Anthropic CLI for headless automation with headless JSON commands, schema discovery, credentials, and permission controls.

7 functions 6 read 1 write API key auth

Submit Anthropic feedback View package source

Anthropic CLI for Headless Automation

Use KosmoKrator as a non-interactive integration runtime for local automations and wrappers.

Use headless automation when another tool needs a stable local command surface. The Anthropic CLI uses the same integration registry as the TUI, Lua runtime, and MCP gateway, but returns predictable command output for automation.

Command Shape

# Anthropic CLI for Headless Automation
kosmokrator integrations:configure anthropic --set api_key="$ANTHROPIC_API_KEY" --enable --read allow --write ask --json
kosmo integrations:call anthropic.anthropic_list_messages '{"model":"example_model","limit":1,"before_id":"example_before_id","after_id":"example_after_id"}' --json

Discovery Before Execution

Agents and scripts can inspect Anthropic docs and schemas 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

Useful Anthropic CLI Functions

Function	Type	Parameters	Description
`anthropic.anthropic_list_messages`	Read	model, limit, before_id, after_id	List messages in the Anthropic conversation history. Returns paginated message resources with optional filtering by model, date, and ID.
`anthropic.anthropic_create_message`	Write	model, messages, max_tokens, system, temperature, top_p, stop_sequences, stream	Send a prompt to Claude and receive an AI-generated response. Supports multi-turn conversations, system prompts, temperature control, and configurable output length.
`anthropic.anthropic_list_models`	Read	limit, before_id, after_id	List available Anthropic AI models. Returns model identifiers, creation dates, and display names.
`anthropic.anthropic_get_model`	Read	id	Get detailed information about a specific Anthropic model, including its display name, creation date, and capabilities.
`anthropic.anthropic_list_workspaces`	Read	limit, before_id, after_id	List Anthropic workspaces. Returns workspace identifiers, names, and configuration details.
`anthropic.anthropic_get_workspace`	Read	id	Get detailed information about a specific Anthropic workspace, including its name, configuration, and usage settings.
`anthropic.anthropic_get_current_user`	Read	none	Get the authenticated user's profile and account information.

Automation Notes

Use --json for machine-readable output.
Keep credentials out of argv by using environment variables or stored KosmoKrator configuration.
Configure read/write policy before unattended runs; use --force only for trusted automation.
Use the MCP gateway instead when the agent needs dynamic tool discovery inside a conversation.

Related Anthropic CLI Pages

CI Anthropic CLI for CI. Cron Jobs Anthropic CLI for cron jobs. Shell Scripts Anthropic CLI for shell scripts. Coding Agents Anthropic CLI for coding agents.