Use AgentsKit from Codex, Claude Code, and Cursor

You should not need a separate interface to use an AgentsKit tool or agent while coding. @agentskit/mcp exposes the same server over STDIO to Codex, Claude Code, Cursor, and other MCP hosts. The host configuration changes; the AgentsKit command does not.

The verified default exposes fetch and search. It does not enable shell, filesystem, SQLite, or a model provider, and it needs no credential to start.

#Codex

Add the server with the CLI:

codex mcp add agentskit -- npx -y @agentskit/mcp@0.3.3 --tools fetch,search
codex mcp list

Or commit a project-scoped .codex/config.toml in a trusted project:

[mcp_servers.agentskit]
command = "npx"
args = ["-y", "@agentskit/mcp@0.3.3", "--tools", "fetch,search"]
default_tools_approval_mode = "prompt"

Codex CLI, the IDE extension, and the desktop app share this configuration. Use /mcp to inspect the connected server.

#Claude Code

Create a project-scoped server:

claude mcp add --scope project --transport stdio agentskit -- npx -y @agentskit/mcp@0.3.3 --tools fetch,search
claude mcp list

The equivalent .mcp.json is:

{
  "mcpServers": {
    "agentskit": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@agentskit/mcp@0.3.3", "--tools", "fetch,search"]
    }
  }
}

Claude Code asks for approval before using a project-scoped server. Review the command, approve it, and use /mcp to check its status.

#Cursor

Create .cursor/mcp.json:

{
  "mcpServers": {
    "agentskit": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@agentskit/mcp@0.3.3", "--tools", "fetch,search"]
    }
  }
}

Restart or reload Cursor, then inspect the MCP settings to confirm that the server and its tools are available.

#Expose a complete Registry agent

The same bridge can publish a bounded Registry agent as one MCP tool. Extend the server arguments rather than changing host-specific code:

OPENROUTER_API_KEY=your-key \
  npx -y @agentskit/mcp@0.3.3 \
  --tools fetch,search \
  --agents code-review \
  --provider openrouter \
  --model openrouter/free \
  --max-steps 8

Keep provider credentials in environment variables. Do not put --api-key in a committed MCP configuration because command arguments can be visible to other local processes.

#Verify the path

The repository proof first launches the built CLI over real child-process STDIO and verifies that --tools fetch,search exposes fetch_url and web_search. The package test also initializes an in-memory client, lists a bounded echo tool, calls it, and closes both ends:

pnpm --filter @agentskit/mcp... build
node packages/mcp/fixtures/run-coding-agent-hosts.mjs
pnpm --filter @agentskit/mcp exec vitest run tests/coding-agent-hosts.test.ts

Both proofs are offline and credential-free. Their sources are under packages/mcp/fixtures/.

#Security boundary

• --allow-shell is absent, so shell execution stays disabled.
• Filesystem access is absent until you pass both filesystem and --fs-root.
• Provider calls are absent until you select an agent, provider, model, and key.
• Host approval remains enabled; the recipe does not bypass Codex or Claude trust prompts.

#Sources

• Codex MCP configuration
• Claude Code MCP configuration
• Cursor MCP configuration
• MCP architecture
• AgentsKit MCP package

#See also

• MCP bridge (bidirectional)
• Mandatory sandbox
• Provider swap