Skip to main content
Agent commands. Your AI agent uses MCP nodes in workflows. You manage MCP servers with pflow mcp commands.
MCP (Model Context Protocol) lets you extend pflow with external tools. When you add an MCP server, its tools become pflow nodes that your agent can use in workflows.

​
How it works

  1. Add an MCP server with pflow mcp add
  2. Sync tools with pflow mcp sync (or let auto-sync handle it)
  3. Tools become nodes named mcp-{server}-{tool}
  4. Agent uses them like any other node
# Add a GitHub MCP server
pflow mcp add github.mcp.json

# Tools are now available
pflow mcp tools github
# mcp-github-create_issue
# mcp-github-list_repos
# mcp-github-search_code

​
Node naming

MCP tools become nodes with the pattern mcp-{server}-{tool}:
ServerToolNode name
githubcreate_issuemcp-github-create_issue
slacksend_messagemcp-slack-send_message
filesystemread_filemcp-filesystem-read_file

​
Parameters

MCP node parameters come directly from the tool’s input schema. Each MCP server defines its own tools with their own parameters. To see a tool’s parameters: 
pflow registry describe mcp-github-create_issue

​
Output

All MCP nodes write to:
KeyTypeDescription
resultanyTool execution result
{server}_{tool}_resultanySame result with unique key
errorstrError message (only on failure)
For dict results, top-level fields are also extracted directly: 
// Tool returns: {"issue_url": "...", "issue_number": 123}
// Shared store contains:
{
  "result": {"issue_url": "...", "issue_number": 123},
  "github_create_issue_result": {"issue_url": "...", "issue_number": 123},
  "issue_url": "...",
  "issue_number": 123
}

​
Example workflow

{
  "nodes": [
    {
      "id": "create_issue",
      "type": "mcp-github-create_issue",
      "params": {
        "repository": "myorg/myrepo",
        "title": "Bug: ${error_summary}",
        "body": "${error_details}"
      }
    },
    {
      "id": "notify",
      "type": "mcp-slack-send_message",
      "params": {
        "channel": "#alerts",
        "text": "Created issue: ${create_issue.issue_url}"
      }
    }
  ]
}

​
Setup

To use MCP tools, first add MCP servers to pflow. See Adding MCP servers for configuration format, authentication, and examples. pflow supports both local (stdio) and remote (HTTP) MCP servers. Both work identically in workflows - same naming, parameters, and output structure.

​
Error handling

MCP nodes return error action on:
  • Connection failure: Server not reachable
  • Tool error: Tool reported an error (via isError flag)
  • Timeout: Request took too long (default 30 seconds)
The node does not retry automatically - MCP calls start a server subprocess, and retries would cause resource conflicts.

​
Auto-sync

When you run a workflow, pflow automatically syncs MCP tools if the server configuration has changed. You don’t need to manually run pflow mcp sync after adding servers. Manual sync is useful for:
  • Testing connection immediately after adding a server
  • Debugging connection issues
  • Forcing re-discovery without running a workflow