Openclaw MCP vs Sub Agents MCP

A side-by-side look at the Openclaw MCP and Sub Agents MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Openclaw MCP logoOpenclaw MCPCoding Agents · Local subprocess (stdio)MCP server for OpenClaw AI assistant integration. Enables Claude to delegate tasks to OpenClaw agents with sync/async tools, OAuth 2.1 auth, and SSE transport for Claude.ai.68GreatAuth: api key requiredSub Agents MCP logoSub Agents MCPCoding Agents · Local subprocess (stdio)MCP server for delegating tasks to specialized AI assistants in Cursor and other tools49FairAuth: not declared

Verdict: choose Openclaw MCP for coding agents work as a local process; choose Sub Agents MCP for coding agents as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Openclaw MCP logoChoose Openclaw MCP when

  • You need dedicated capabilities in the Coding Agents domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: API key required.
  • You have the keys it needs: OPENCLAW_URL, OPENCLAW_GATEWAY_TOKEN, OPENCLAW_AGENT_ID, OPENCLAW_MODEL, OPENCLAW_TIMEOUT_MS, AUTH_ENABLED, MCP_CLIENT_ID, MCP_CLIENT_SECRET.
  • You want tools like openclaw_chat, openclaw_status, openclaw_chat_async.
Explore Openclaw MCP

Sub Agents MCP logoChoose Sub Agents MCP when

  • You need dedicated capabilities in the Coding Agents domain.
  • You prefer a local stdio subprocess transport.
  • You have the keys it needs: AGENTS_DIR, AGENT_TYPE, CLI_API_KEY, AGENT_MODEL, AGENT_PERMISSION, SESSION_ENABLED.
Explore Sub Agents MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecOpenclaw MCP logoOpenclaw MCPSub Agents MCP logoSub Agents MCP
CategoryCoding AgentsCoding Agents
Quality signal68/100 · Great49/100 · Fair
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthAPI key requiredNot declared
PricingFreeBYOK (pay the provider)
Required env varsOPENCLAW_URLOPENCLAW_GATEWAY_TOKENOPENCLAW_AGENT_IDOPENCLAW_MODELOPENCLAW_TIMEOUT_MSAUTH_ENABLEDMCP_CLIENT_IDMCP_CLIENT_SECRETAGENTS_DIRAGENT_TYPECLI_API_KEYAGENT_MODELAGENT_PERMISSIONSESSION_ENABLED
Verified ownerCommunity listingCommunity listing
GitHub stars18899
Directory activity 8 views 0 installs 0 upvotes 1 views 0 installs 0 upvotes
Tools7Not listed

Tools & capabilities

Openclaw MCP tools 7

  • openclaw_chatSend a message to OpenClaw and get a response
  • openclaw_statusGet OpenClaw gateway status and health information
  • openclaw_chat_asyncSend a message to OpenClaw asynchronously. Returns a task_id immediately that can be polled for results. Use this for potentially long-running conversations.
  • openclaw_task_statusCheck the status of an async task. Returns status, and result if completed.
  • openclaw_task_listList all tasks. Optionally filter by status, session, or instance.
  • openclaw_task_cancelCancel a pending task. Only works for tasks that haven't started yet.
  • openclaw_instancesList all configured OpenClaw instances. Shows instance names, URLs, and which is the default. Use instance names in other tools to target a specific OpenClaw gateway.

Sub Agents MCP tools

No tool names declared yet. Check the project README from the listing page.

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Openclaw MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "freema-openclaw-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "openclaw-mcp"
      ],
      "env": {
        "OPENCLAW_URL": "YOUR_OPENCLAW_URL_HERE",
        "OPENCLAW_GATEWAY_TOKEN": "YOUR_OPENCLAW_GATEWAY_TOKEN_HERE",
        "OPENCLAW_AGENT_ID": "YOUR_OPENCLAW_AGENT_ID_HERE",
        "OPENCLAW_MODEL": "YOUR_OPENCLAW_MODEL_HERE",
        "OPENCLAW_TIMEOUT_MS": "YOUR_OPENCLAW_TIMEOUT_MS_HERE",
        "AUTH_ENABLED": "YOUR_AUTH_ENABLED_HERE",
        "MCP_CLIENT_ID": "YOUR_MCP_CLIENT_ID_HERE",
        "MCP_CLIENT_SECRET": "YOUR_MCP_CLIENT_SECRET_HERE"
      }
    }
  }
}

Sub Agents MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "sub-agents-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "sub-agents-mcp"
      ],
      "env": {
        "AGENTS_DIR": "YOUR_AGENTS_DIR_HERE",
        "AGENT_TYPE": "YOUR_AGENT_TYPE_HERE",
        "CLI_API_KEY": "YOUR_CLI_API_KEY_HERE",
        "AGENT_MODEL": "YOUR_AGENT_MODEL_HERE",
        "AGENT_PERMISSION": "YOUR_AGENT_PERMISSION_HERE",
        "SESSION_ENABLED": "YOUR_SESSION_ENABLED_HERE"
      }
    }
  }
}

Frequently asked questions

Openclaw MCP is categorized under Coding Agents and uses a local stdio subprocess. Sub Agents MCP belongs to Coding Agents and uses a local stdio subprocess. Pick Openclaw MCP for coding agents work and Sub Agents MCP for coding agents.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Openclaw MCP is listed as free. Auth: api key required. Sub Agents MCP is bring-your-own-key: usage is billed by the API provider you supply a key for. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add freema-openclaw-mcp and sub-agents-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Openclaw MCP has a quality signal of 68/100 (Great) with 8 views, 0 installs and 188 GitHub stars. Sub Agents MCP has 49/100 (Fair) with 1 views, 0 installs and 99 GitHub stars.