Can I use LinkedIn as a CLI?

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

Can I expose LinkedIn through MCP?

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

Where are LinkedIn credentials stored?

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

Can I deny write access for LinkedIn MCP tools?

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

marketing

LinkedIn MCP Integration for Vercel AI SDK

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

7 functions 6 read 1 write Manual OAuth token auth

Submit LinkedIn feedback View package source

Connect LinkedIn 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.

LinkedIn MCP Config for Vercel AI SDK

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

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

Run the Gateway Manually

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

Why Use KosmoKrator Here

Scoped tools

Expose only LinkedIn 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.

LinkedIn Tools Visible to Vercel AI SDK

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

MCP tool	Source function	Type	Description
`integration__linkedin__linkedin_list_posts`	`linkedin.linkedin_list_posts`	Read	List LinkedIn UGC posts for an author. Returns post IDs, lifecycle state, and creation timestamps. Use author, count, and start for filtering and pagination.
`integration__linkedin__linkedin_get_post`	`linkedin.linkedin_get_post`	Read	Retrieve a LinkedIn UGC post by its ID. Returns the full post including content, lifecycle state, and visibility.
`integration__linkedin__linkedin_create_post`	`linkedin.linkedin_create_post`	Write	Create a new LinkedIn UGC post. Requires an author URN and text content. Returns the created post with its ID and lifecycle state.
`integration__linkedin__linkedin_list_organizations`	`linkedin.linkedin_list_organizations`	Read	List LinkedIn organizations (company pages) the authenticated user has access to. Returns organization IDs, names, and roles.
`integration__linkedin__linkedin_get_organization`	`linkedin.linkedin_get_organization`	Read	Retrieve a LinkedIn organization (company page) by its ID. Returns the organization's name, description, website, and other profile data.
`integration__linkedin__linkedin_list_ad_accounts`	`linkedin.linkedin_list_ad_accounts`	Read	List LinkedIn ad accounts the authenticated user has access to. Returns ad account IDs, names, statuses, and currency information.
`integration__linkedin__linkedin_get_current_user`	`linkedin.linkedin_get_current_user`	Read	Retrieve the currently authenticated LinkedIn user profile. Returns the user's ID, localized name, and profile metadata. Useful for identifying which account or token is in use.