Can I use BlandAI as a CLI?

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

Can I expose BlandAI through MCP?

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

Where are BlandAI credentials stored?

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

Can I deny write access for BlandAI MCP tools?

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

communication

BlandAI MCP Integration for Vercel AI SDK

Connect BlandAI to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

5 functions 4 read 1 write API key auth

Submit BlandAI feedback View package source

Connect BlandAI to Vercel AI SDK

Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.

Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with --write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.

BlandAI MCP Config for Vercel AI SDK

Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.

{
  "mcpServers": {
    "kosmokrator-blandai": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=blandai",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=blandai --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only BlandAI instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

BlandAI Tools Visible to Vercel AI SDK

Vercel AI SDK sees stable MCP tool names generated from the BlandAI integration catalog.

MCP tool	Source function	Type	Description
`integration__blandai__blandai_make_call`	`blandai.blandai_make_call`	Write	Initiate an AI-powered phone call via BlandAI. The AI agent will follow the provided task instructions and speak using the specified voice.
`integration__blandai__blandai_get_call`	`blandai.blandai_get_call`	Read	Retrieve details for a specific BlandAI phone call, including status, transcript, duration, and metadata.
`integration__blandai__blandai_list_calls`	`blandai.blandai_list_calls`	Read	List BlandAI phone calls with optional pagination. Returns call summaries including status, duration, and phone numbers.
`integration__blandai__blandai_analyze_call`	`blandai.blandai_analyze_call`	Read	Analyze a BlandAI call transcript with a custom prompt. Extract insights, summarize the conversation, or evaluate call outcomes.
`integration__blandai__blandai_get_current_user`	`blandai.blandai_get_current_user`	Read	Get the authenticated BlandAI user's account information. Useful for verifying credentials and checking account details.

Related BlandAI Pages

BlandAI CLIUse direct JSON commands instead of MCP discovery. BlandAI MCPFull gateway reference and MCP tool names. KosmoKrator for Vercel AI SDKClient-level gateway setup.