Class: Phronomy::Tool::McpTool::StdioTransport

Inherits:
Object
  • Object
show all
Defined in:
lib/phronomy/tool/mcp_tool.rb

Overview

Minimal stdio transport implementing a subset of the MCP JSON-RPC protocol. Keeps the child process alive for the lifetime of this transport instance so that session state (registered resources, tool context, etc.) is preserved across multiple calls.

Instance Method Summary collapse

Constructor Details

#initialize(command, read_timeout: 30, env: nil, cwd: nil, startup_timeout: nil) ⇒ StdioTransport

Returns a new instance of StdioTransport.

Parameters:

  • command (String) —

    shell command to spawn the MCP server process

  • read_timeout (Integer) (defaults to: 30) —

    seconds to wait for the server's JSON-RPC response before raising Phronomy::ToolError. Mirrors the +read_timeout+ option on HttpTransport. Defaults to 30 seconds.

  • env (Hash, nil) (defaults to: nil) —

    environment variable overrides for the subprocess. When provided, only these variables are added/overridden; the parent environment is still inherited unless explicitly cleared via an empty string value.

  • cwd (String, nil) (defaults to: nil) —

    working directory for the subprocess. Defaults to the current process's working directory.

  • startup_timeout (Numeric, nil) (defaults to: nil) —

    seconds to wait for the server to emit its first line on stdout before raising Phronomy::ToolError. When nil (default), no startup check is performed.



128
129
130
131
132
133
134
135
136
137
138
139
140
141
 
# File 'lib/phronomy/tool/mcp_tool.rb', line 128

def initialize(command, read_timeout: 30, env: nil, cwd: nil, startup_timeout: nil)
  # Split the command string into an argv array so that Open3 executes
  # it directly without going through the shell, preventing injection.
  @command = Shellwords.split(command)
  @read_timeout = read_timeout
  @env = env
  @cwd = cwd
  @startup_timeout = startup_timeout
  @stdin = nil
  @stdout = nil
  @stderr = nil
  @wait_thr = nil
  @stderr_thread = nil
end

Instance Method Details

#call_tool(tool_name, args) ⇒ Object

Call a tool on the MCP server using the tools/call method.

Parameters:

  • tool_name (String)
  • args (Hash)

Returns:

  • (Object) —

    the tool result



181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
 
# File 'lib/phronomy/tool/mcp_tool.rb', line 181

def call_tool(tool_name, args)
  response = rpc_call("tools/call", {name: tool_name, arguments: args})
  if response["error"]
    err_msg = response.dig("error", "message") || response["error"].to_s
    raise Phronomy::ToolError, "MCP server returned error: #{err_msg}"
  end
  content = response.dig("result", "content")

  # MCP content is an array of content blocks; extract text blocks.
  if content.is_a?(Array)
    texts = content.select { |c| c["type"] == "text" }.map { |c| c["text"] }
    (texts.length == 1) ? texts.first : texts
  else
    content
  end
end

#close ⇒ Object

Shut down the child process and close its IO streams.



144
145
146
147
148
149
150
151
152
153
154
155
156
157
 
# File 'lib/phronomy/tool/mcp_tool.rb', line 144

def close
  @stdin&.close
  @stdout&.close
  @stderr&.close
  @stdin = nil
  @stdout = nil
  @stderr = nil
  stderr_thread = @stderr_thread
  wait_thr = @wait_thr
  @stderr_thread = nil
  @wait_thr = nil
  stderr_thread&.join(1)
  wait_thr&.join(5)
end

#fetch_tool(tool_name) ⇒ Hash

Retrieve the tool definition from the server using the MCP tools/list method.

Parameters:

  • tool_name (String)

Returns:

  • (Hash) —

    { description:, parameters: }

Raises:

  • (ArgumentError) 


163
164
165
166
167
168
169
170
171
172
173
174
 
# File 'lib/phronomy/tool/mcp_tool.rb', line 163

def fetch_tool(tool_name)
  response = rpc_call("tools/list", {})
  tools = response.dig("result", "tools") || []
  defn = tools.find { |t| t["name"] == tool_name }
  raise ArgumentError, "Tool #{tool_name.inspect} not found on MCP server #{@command.inspect}" unless defn

  required_names = defn.dig("inputSchema", "required") || []
  {
    description: defn["description"],
    parameters: parse_schema_params(defn.dig("inputSchema", "properties") || {}, required_names: required_names)
  }
end