KosmoKrator

productivity

Cerebras MCP Gateway for AI Agents

Expose Cerebras tools to Claude Code, Cursor, Codex, and other MCP clients through the local KosmoKrator MCP gateway.

Cerebras MCP Gateway

Expose Cerebras to MCP clients with `kosmokrator mcp:serve --integration=cerebras`.

If the client has never used KosmoKrator before, install it first, then register this integration as a stdio MCP server.

Install KosmoKrator 
curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash
Install gateway entry 
kosmokrator mcp:gateway:install --integration=cerebras --write=deny --json
MCP configuration 
{
  "mcpServers": {
    "kosmokrator-cerebras": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=cerebras",
        "--write=deny"
      ]
    }
  }
}
Serve manually 
kosmokrator mcp:serve --integration=cerebras --write=deny

Client Notes

Use one scoped MCP gateway entry, then adapt the config location to the client or framework.

Claude Code Connect local KosmoKrator integrations to Claude Code through one scoped MCP gateway entry. Claude Code can launch the local kosmo binary directly from the project MCP config.
Cursor Expose selected local integrations to Cursor through KosmoKrator without configuring each service as its own MCP server. Use the same KosmoKrator install and integration credentials that power terminal and headless runs.
Codex Use KosmoKrator as a local MCP proxy for Codex so coding sessions can reach selected integrations with explicit write policy. Keep write access denied or ask-based unless the workspace is trusted.
OpenAI Agents SDK Attach KosmoKrator integration tools to OpenAI Agents SDK workflows through a local MCP gateway. Use headless JSON commands for CI-style execution and MCP for agent tool discovery.
Claude Agent SDK Give Claude Agent SDK workflows access to KosmoKrator integrations through a local MCP server. Use a narrow integration list so the agent does not load unrelated tools.
Vercel AI SDK Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts. Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.
LangChain Bridge LangChain agents to local KosmoKrator integration tools through MCP or headless CLI calls. Keep the gateway scoped to the integration and operation class needed by the chain.
LangGraph Run KosmoKrator integration calls from LangGraph nodes while preserving local credentials and permissions. Headless CLI calls fit repeatable graph edges; MCP fits exploratory agent nodes.
CrewAI Expose KosmoKrator integrations to CrewAI workers as scoped local tools. Use per-worker integration scopes to avoid giving every worker every tool.
Generic MCP Clients Connect any stdio-compatible MCP client to local KosmoKrator integration tools. Start with read-only write policy and expand only for trusted projects.

MCP Tool Names

KosmoKrator exposes integration tools through the gateway with stable names.

MCP toolSource functionType
integration__cerebras__cerebras_cancel_batch cerebras.cerebras_cancel_batch Write write
integration__cerebras__cerebras_chat_completions cerebras.cerebras_chat_completions Read read
integration__cerebras__cerebras_completions cerebras.cerebras_completions Read read
integration__cerebras__cerebras_create_batch cerebras.cerebras_create_batch Write write
integration__cerebras__cerebras_delete_file cerebras.cerebras_delete_file Write write
integration__cerebras__cerebras_delete_model_version cerebras.cerebras_delete_model_version Write write
integration__cerebras__cerebras_deploy_model_to_endpoint cerebras.cerebras_deploy_model_to_endpoint Read read
integration__cerebras__cerebras_list_batches cerebras.cerebras_list_batches Read read
integration__cerebras__cerebras_list_endpoints cerebras.cerebras_list_endpoints Read read
integration__cerebras__cerebras_list_files cerebras.cerebras_list_files Read read
integration__cerebras__cerebras_list_model_architectures cerebras.cerebras_list_model_architectures Read read
integration__cerebras__cerebras_list_model_versions cerebras.cerebras_list_model_versions Read read
integration__cerebras__cerebras_list_models cerebras.cerebras_list_models Read read
integration__cerebras__cerebras_list_public_models cerebras.cerebras_list_public_models Read read
integration__cerebras__cerebras_retrieve_batch cerebras.cerebras_retrieve_batch Read read
integration__cerebras__cerebras_retrieve_endpoint_status cerebras.cerebras_retrieve_endpoint_status Read read
integration__cerebras__cerebras_retrieve_file cerebras.cerebras_retrieve_file Read read
integration__cerebras__cerebras_retrieve_file_content cerebras.cerebras_retrieve_file_content Read read
integration__cerebras__cerebras_retrieve_metrics cerebras.cerebras_retrieve_metrics Read read
integration__cerebras__cerebras_retrieve_model cerebras.cerebras_retrieve_model Read read
integration__cerebras__cerebras_retrieve_model_version_status cerebras.cerebras_retrieve_model_version_status Read read
integration__cerebras__cerebras_retrieve_public_model cerebras.cerebras_retrieve_public_model Read read
integration__cerebras__cerebras_update_model_version_aliases cerebras.cerebras_update_model_version_aliases Write write
integration__cerebras__cerebras_upload_file cerebras.cerebras_upload_file Read read
integration__cerebras__cerebras_upload_model_version cerebras.cerebras_upload_model_version Read read

Write Access

Start with --write=deny for read-only MCP clients. Use --write=ask or --write=allow only when the client and workspace are trusted.