Can I use Exa AI as a CLI?

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

Can I expose Exa AI through MCP?

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

Where are Exa AI credentials stored?

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

Can I deny write access for Exa AI MCP tools?

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

Exa AI MCP Integration for Vercel AI SDK

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

5 functions 5 read 0 write API key auth

Submit Exa AI feedback View package source

Connect Exa AI 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.

Exa AI MCP Config for Vercel AI SDK

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

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

Run the Gateway Manually

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

Why Use KosmoKrator Here

Scoped tools

Expose only Exa AI 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.

Exa AI Tools Visible to Vercel AI SDK

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

MCP tool	Source function	Type	Description
`integration__exa__exa_search`	`exa.exa_search`	Read	Perform a neural search query across the web using Exa AI. Returns a list of relevant pages with titles, URLs, and scores. Supports filtering by category, date range, and autoprompt mode.
`integration__exa__exa_find_similar`	`exa.exa_find_similar`	Read	Find web pages similar to a given URL. Useful for discovering related content, competitors, or alternative resources. Returns a list of similar pages with titles, URLs, and scores.
`integration__exa__exa_get_contents`	`exa.exa_get_contents`	Read	Retrieve the full text contents and optional highlights for a list of Exa document IDs. Use this after a search or findSimilar call to get the actual page content.
`integration__exa__exa_search_and_contents`	`exa.exa_search_and_contents`	Read	Search the web and retrieve full page contents in one call. Combines search and content retrieval into a single request for efficiency. Returns results with both metadata and full text content.
`integration__exa__exa_get_current_user`	`exa.exa_get_current_user`	Read	Get the currently authenticated Exa user's profile information, including email and API usage details. Useful for verifying credentials.

Related Exa AI Pages

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