fast-agent-mcp 0.1.11__py3-none-any.whl → 0.1.13__py3-none-any.whl

mcp_agent/resources/examples/internal/prompt_category.py

@@ -1,5 +1,5 @@
 from mcp.server.fastmcp import FastMCP
-from mcp.server.fastmcp.prompts.base import UserMessage, AssistantMessage
+from mcp.server.fastmcp.prompts.base import AssistantMessage, UserMessage
 
 mcp = FastMCP("MCP Root Tester")
 

mcp_agent/resources/examples/internal/prompt_sizing.py

@@ -1,6 +1,6 @@
-from pydantic import Field
 from mcp.server.fastmcp import FastMCP
-from mcp.server.fastmcp.prompts.base import UserMessage, AssistantMessage
+from mcp.server.fastmcp.prompts.base import AssistantMessage, UserMessage
+from pydantic import Field
 
 mcp = FastMCP("MCP Prompt Tester")
 
@@ -23,9 +23,7 @@ def sizing_prompt():
     description="set up the sizing protocol with metric or imperial units",
 )
 def sizing_prompt_units(
-    metric: bool = Field(
-        description="Set to True for Metric, False for Imperial", default=True
-    ),
+    metric: bool = Field(description="Set to True for Metric, False for Imperial", default=True),
 ):
     if metric:
         return [

mcp_agent/resources/examples/internal/sizer.py

@@ -1,4 +1,5 @@
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 fast = FastAgent("Sizer Prompt Test")
@@ -10,7 +11,7 @@ fast = FastAgent("Sizer Prompt Test")
     servers=["sizer", "category"],
     use_history=True,
 )
-async def main():
+async def main() -> None:
     async with fast.run() as agent:
         await agent()
 

mcp_agent/resources/examples/internal/social.py

@@ -1,4 +1,5 @@
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
@@ -56,7 +57,7 @@ Social Media report ready to review with the Human.
         "human_review_and_post",
     ],
 )
-async def main():
+async def main() -> None:
     async with fast.run() as agent:
         # using chain workflow
         await agent.post_writer.prompt()

mcp_agent/resources/examples/mcp_researcher/researcher-eval.py

@@ -41,7 +41,7 @@ Summarize your evaluation as a structured response with:
     min_rating="EXCELLENT",
     name="Researcher_Evaluator",
 )
-async def main():
+async def main() -> None:
     async with agents.run() as agent:
         await agent.prompt("Researcher_Evaluator")
 

mcp_agent/resources/examples/prompting/__init__.py

@@ -1,3 +1,3 @@
 """
 Prompting examples package for MCP Agent.
-"""
+"""

mcp_agent/resources/examples/prompting/agent.py

@@ -1,4 +1,5 @@
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
@@ -13,7 +14,7 @@ fast = FastAgent("FastAgent Example")
     #    model="gpt-4o",
     #    instruction="You are a helpful AI Agent", servers=["prompts","basic_memory"], model="haiku"
 )
-async def main():
+async def main() -> None:
     # use the --model command line switch or agent arguments to change model
     async with fast.run() as agent:
         await agent()

mcp_agent/resources/examples/prompting/image_server.py

@@ -6,8 +6,8 @@ Simple MCP server that responds to tool calls with text and image content.
 import logging
 from pathlib import Path
 
-from mcp.server.fastmcp import FastMCP, Context, Image
-from mcp.types import TextContent, ImageContent
+from mcp.server.fastmcp import Context, FastMCP, Image
+from mcp.types import ImageContent, TextContent
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -18,9 +18,7 @@ app = FastMCP(name="ImageToolServer", debug=True)
 
 
 @app.tool(name="get_image", description="Returns an image with a descriptive text")
-async def get_image(
-    image_name: str = "default", ctx: Context = None
-) -> list[TextContent | ImageContent]:
+async def get_image(image_name: str = "default", ctx: Context = None) -> list[TextContent | ImageContent]:
     """
     Returns an image file along with a descriptive text.
 
@@ -45,12 +43,8 @@ async def get_image(
 if __name__ == "__main__":
     # Check if the default image exists
     if not Path("image.jpg").exists():
-        logger.warning(
-            "Default image file 'image.jpg' not found in the current directory"
-        )
-        logger.warning(
-            "Please add an image file named 'image.jpg' to the current directory"
-        )
+        logger.warning("Default image file 'image.jpg' not found in the current directory")
+        logger.warning("Please add an image file named 'image.jpg' to the current directory")
 
     # Run the server using stdio transport
     app.run(transport="stdio")

mcp_agent/resources/examples/researcher/researcher-eval.py

@@ -41,7 +41,7 @@ Summarize your evaluation as a structured response with:
     min_rating="EXCELLENT",
     name="Researcher_Evaluator",
 )
-async def main():
+async def main() -> None:
     async with agents.run() as agent:
         await agent.prompt("Researcher_Evaluator")
 

mcp_agent/resources/examples/researcher/researcher-imp.py

@@ -1,4 +1,5 @@
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 agents = FastAgent(name="Enhanced Researcher")
@@ -162,7 +163,7 @@ The researcher should be able to understand exactly why they received their rati
     min_rating="EXCELLENT",
     name="EnhancedResearcher",
 )
-async def main():
+async def main() -> None:
     async with agents.run() as agent:
         # Start with a warm-up to set expectations and explain the research approach
         await agent.Researcher.send(
@@ -180,9 +181,7 @@ async def main():
         # Start the main research workflow
         await agent.prompt("EnhancedResearcher")
 
-        print(
-            "\nWould you like to ask follow-up questions to the Researcher? (Type 'STOP' to end)"
-        )
+        print("\nWould you like to ask follow-up questions to the Researcher? (Type 'STOP' to end)")
         await agent.prompt("Researcher", default="STOP")
 
 

mcp_agent/resources/examples/researcher/researcher.py

@@ -1,6 +1,7 @@
 import asyncio
 
 from mcp_agent.core.fastagent import FastAgent
+
 # from rich import print
 
 agents = FastAgent(name="Researcher Agent")
@@ -16,7 +17,7 @@ The interpreter has numpy, pandas, matplotlib and seaborn already installed
     """,
     servers=["brave", "interpreter", "filesystem", "fetch"],
 )
-async def main():
+async def main() -> None:
     research_prompt = """
 Produce an investment report for the company Eutelsat. The final report should be saved in the filesystem in markdown format, and
 contain at least the following: 

mcp_agent/resources/examples/workflows/agent_build.py

@@ -3,6 +3,7 @@ This demonstrates creating multiple agents and an orchestrator to coordinate the
 """
 
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 from mcp_agent.workflows.llm.augmented_llm import RequestParams
 
@@ -62,7 +63,7 @@ if needed. Remind the Human of this.
     request_params=RequestParams(maxTokens=8192),
     max_iterations=5,
 )
-async def main():
+async def main() -> None:
     async with fast.run() as agent:
         CODER_WARMUP = """
 - Read this paper: https://www.anthropic.com/research/building-effective-agents" to understand how 

mcp_agent/resources/examples/workflows/chaining.py

@@ -1,4 +1,5 @@
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
@@ -21,7 +22,7 @@ fast = FastAgent("Agent Chaining")
     name="post_writer",
     sequence=["url_fetcher", "social_media"],
 )
-async def main():
+async def main() -> None:
     async with fast.run() as agent:
         # using chain workflow
         await agent.post_writer.prompt()

mcp_agent/resources/examples/workflows/evaluator.py

@@ -3,6 +3,7 @@ This demonstrates creating an optimizer and evaluator to iteratively improve con
 """
 
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
@@ -49,7 +50,7 @@ fast = FastAgent("Evaluator-Optimizer")
     min_rating="EXCELLENT",  # Strive for excellence
     max_refinements=3,  # Maximum iterations
 )
-async def main():
+async def main() -> None:
     async with fast.run() as agent:
         job_posting = (
             "Software Engineer at LastMile AI. Responsibilities include developing AI systems, "

mcp_agent/resources/examples/workflows/human_input.py

@@ -3,6 +3,7 @@ Agent which demonstrates Human Input tool
 """
 
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
@@ -14,7 +15,7 @@ fast = FastAgent("Human Input")
     instruction="An AI agent that assists with basic tasks. Request Human Input when needed.",
     human_input=True,
 )
-async def main():
+async def main() -> None:
     async with fast.run() as agent:
         # this usually causes the LLM to request the Human Input Tool
         await agent("print the next number in the sequence")

mcp_agent/resources/examples/workflows/orchestrator.py

@@ -3,6 +3,7 @@ This demonstrates creating multiple agents and an orchestrator to coordinate the
 """
 
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
@@ -47,7 +48,7 @@ fast = FastAgent("Orchestrator-Workers")
     agents=["finder", "writer", "proofreader"],
     plan_type="iterative",
 )
-async def main():
+async def main() -> None:
     async with fast.run() as agent:
         await agent()
         await agent.author(

mcp_agent/resources/examples/workflows/parallel.py

@@ -3,6 +3,7 @@ Parallel Workflow showing Fan Out and Fan In agents, using different models
 """
 
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
@@ -65,7 +66,7 @@ and whispers of a hidden agenda linger among the villagers.
     fan_in="grader",
     name="parallel",
 )
-async def main():
+async def main() -> None:
     # Use the app's context manager
     async with fast.run() as agent:
         await agent.parallel(f"student short story submission: {SHORT_STORY}")

mcp_agent/resources/examples/workflows/router.py

@@ -6,6 +6,7 @@ Demonstrates router's ability to either:
 """
 
 import asyncio
+
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
@@ -43,7 +44,7 @@ SAMPLE_REQUESTS = [
     model="sonnet",
     agents=["code_expert", "general_assistant", "fetcher"],
 )
-async def main():
+async def main() -> None:
     async with fast.run() as agent:
         for request in SAMPLE_REQUESTS:
             await agent.route(request)

mcp_agent/resources/examples/workflows/sse.py

@@ -10,7 +10,7 @@ fa = FastAgent("My Application")
 @fa.agent("analyst", "hello, world", servers=["fetch"])
 
 # Run the application with MCP server
-async def main():
+async def main() -> None:
     await fa.run_with_mcp_server(
         transport="sse",  # Use "sse" for web server, "stdio" for command line
         port=8000,

mcp_agent/telemetry/usage_tracking.py

@@ -1,10 +1,11 @@
 import logging
+
 from mcp_agent.config import get_settings
 
 logger = logging.getLogger(__name__)
 
 
-def send_usage_data():
+def send_usage_data() -> None:
     config = get_settings()
     if not config.usage_telemetry.enabled:
         logger.info("Usage tracking is disabled")

mcp_agent/ui/console_display.py

@@ -17,7 +17,7 @@ class ConsoleDisplay:
     This centralizes the UI display logic used by LLM implementations.
     """
 
-    def __init__(self, config=None):
+    def __init__(self, config=None) -> None:
         """
         Initialize the console display handler.
 
@@ -26,7 +26,7 @@ class ConsoleDisplay:
         """
         self.config = config
 
-    def show_tool_result(self, result: CallToolResult):
+    def show_tool_result(self, result: CallToolResult) -> None:
         """Display a tool result in a formatted panel."""
         if not self.config or not self.config.logger.show_tools:
             return
@@ -49,7 +49,7 @@ class ConsoleDisplay:
         console.console.print(panel)
         console.console.print("\n")
 
-    def show_oai_tool_result(self, result):
+    def show_oai_tool_result(self, result) -> None:
         """Display an OpenAI tool result in a formatted panel."""
         if not self.config or not self.config.logger.show_tools:
             return
@@ -70,7 +70,7 @@ class ConsoleDisplay:
         console.console.print(panel)
         console.console.print("\n")
 
-    def show_tool_call(self, available_tools, tool_name, tool_args):
+    def show_tool_call(self, available_tools, tool_name, tool_args) -> None:
         """Display a tool call in a formatted panel."""
         if not self.config or not self.config.logger.show_tools:
             return
@@ -109,25 +109,13 @@ class ConsoleDisplay:
                     tool_call_name = display_tool["name"]
             else:
                 # Handle potential object format (e.g., Pydantic models)
-                tool_call_name = (
-                    display_tool.function.name
-                    if hasattr(display_tool, "function")
-                    else display_tool.name
-                )
-
-            parts = (
-                tool_call_name.split(SEP)
-                if SEP in tool_call_name
-                else [tool_call_name, tool_call_name]
-            )
+                tool_call_name = display_tool.function.name if hasattr(display_tool, "function") else display_tool.name
+
+            parts = tool_call_name.split(SEP) if SEP in tool_call_name else [tool_call_name, tool_call_name]
 
             if selected_tool_name.split(SEP)[0] == parts[0]:
-                style = (
-                    "magenta" if tool_call_name == selected_tool_name else "dim white"
-                )
-                shortened_name = (
-                    parts[1] if len(parts[1]) <= 12 else parts[1][:11] + "…"
-                )
+                style = "magenta" if tool_call_name == selected_tool_name else "dim white"
+                shortened_name = parts[1] if len(parts[1]) <= 12 else parts[1][:11] + "…"
                 display_tool_list.append(f"[{shortened_name}] ", style)
 
         return display_tool_list
@@ -139,7 +127,7 @@ class ConsoleDisplay:
         highlight_namespaced_tool: str = "",
         title: str = "ASSISTANT",
         name: Optional[str] = None,
-    ):
+    ) -> None:
         """Display an assistant message in a formatted panel."""
         if not self.config or not self.config.logger.show_chat:
             return
@@ -150,19 +138,11 @@ class ConsoleDisplay:
             # Add human input tool if available
             tools = await aggregator.list_tools()
             if any(tool.name == HUMAN_INPUT_TOOL_NAME for tool in tools.tools):
-                style = (
-                    "green"
-                    if highlight_namespaced_tool == HUMAN_INPUT_TOOL_NAME
-                    else "dim white"
-                )
+                style = "green" if highlight_namespaced_tool == HUMAN_INPUT_TOOL_NAME else "dim white"
                 display_server_list.append("[human] ", style)
 
             # Add all available servers
-            mcp_server_name = (
-                highlight_namespaced_tool.split(SEP)[0]
-                if SEP in highlight_namespaced_tool
-                else highlight_namespaced_tool
-            )
+            mcp_server_name = highlight_namespaced_tool.split(SEP)[0] if SEP in highlight_namespaced_tool else highlight_namespaced_tool
 
             for server_name in await aggregator.list_servers():
                 style = "green" if server_name == mcp_server_name else "dim white"
@@ -181,9 +161,7 @@ class ConsoleDisplay:
         console.console.print(panel)
         console.console.print("\n")
 
-    def show_user_message(
-        self, message, model: Optional[str], chat_turn: int, name: Optional[str] = None
-    ):
+    def show_user_message(self, message, model: Optional[str], chat_turn: int, name: Optional[str] = None) -> None:
         """Display a user message in a formatted panel."""
         if not self.config or not self.config.logger.show_chat:
             return
@@ -209,7 +187,7 @@ class ConsoleDisplay:
         agent_name: Optional[str] = None,
         aggregator=None,
         arguments: Optional[dict[str, str]] = None,
-    ):
+    ) -> None:
         """
         Display information about a loaded prompt template.
 
@@ -242,22 +220,20 @@ class ConsoleDisplay:
 
         # Create content text
         content = Text()
-        messages_phrase = (
-            f"Loaded {message_count} message{'s' if message_count != 1 else ''}"
-        )
+        messages_phrase = f"Loaded {message_count} message{'s' if message_count != 1 else ''}"
         content.append(f"{messages_phrase} from template ", style="cyan italic")
         content.append(f"'{prompt_name}'", style="cyan bold italic")
 
         if agent_name:
             content.append(f" for {agent_name}", style="cyan italic")
-            
+
         # Add template arguments if provided
         if arguments:
             content.append("\n\nArguments:", style="cyan")
             for key, value in arguments.items():
                 content.append(f"\n  {key}: ", style="cyan bold")
                 content.append(value, style="white")
-                
+
         if description:
             content.append("\n\n", style="default")
             content.append(description, style="dim white")

mcp_agent/workflows/embedding/embedding_base.py

@@ -7,7 +7,6 @@ from sklearn.metrics.pairwise import cosine_similarity
 
 from mcp_agent.context_dependent import ContextDependent
 
-
 FloatArray = NDArray[float32]
 
 
@@ -32,9 +31,7 @@ class EmbeddingModel(ABC, ContextDependent):
         """Return the dimensionality of the embeddings"""
 
 
-def compute_similarity_scores(
-    embedding_a: FloatArray, embedding_b: FloatArray
-) -> Dict[str, float]:
+def compute_similarity_scores(embedding_a: FloatArray, embedding_b: FloatArray) -> Dict[str, float]:
     """
     Compute different similarity metrics between embeddings
     """

mcp_agent/workflows/embedding/embedding_cohere.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, TYPE_CHECKING
+from typing import TYPE_CHECKING, List, Optional
 
 from cohere import Client
 from numpy import array, float32
@@ -17,7 +17,7 @@ class CohereEmbeddingModel(EmbeddingModel):
         model: str = "embed-multilingual-v3.0",
         context: Optional["Context"] = None,
         **kwargs,
-    ):
+    ) -> None:
         super().__init__(context=context, **kwargs)
         self.client = Client(api_key=self.context.config.cohere.api_key)
         self.model = model

mcp_agent/workflows/embedding/embedding_openai.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, TYPE_CHECKING
+from typing import TYPE_CHECKING, List, Optional
 
 from numpy import array, float32, stack
 from openai import OpenAI
@@ -12,9 +12,7 @@ if TYPE_CHECKING:
 class OpenAIEmbeddingModel(EmbeddingModel):
     """OpenAI embedding model implementation"""
 
-    def __init__(
-        self, model: str = "text-embedding-3-small", context: Optional["Context"] = None
-    ):
+    def __init__(self, model: str = "text-embedding-3-small", context: Optional["Context"] = None) -> None:
         super().__init__(context=context)
         self.client = OpenAI(api_key=self.context.config.openai.api_key)
         self.model = model
@@ -25,20 +23,13 @@ class OpenAIEmbeddingModel(EmbeddingModel):
         }[model]
 
     async def embed(self, data: List[str]) -> FloatArray:
-        response = self.client.embeddings.create(
-            model=self.model, input=data, encoding_format="float"
-        )
+        response = self.client.embeddings.create(model=self.model, input=data, encoding_format="float")
 
         # Sort the embeddings by their index to ensure correct order
         sorted_embeddings = sorted(response.data, key=lambda x: x["index"])
 
         # Stack all embeddings into a single array
-        embeddings = stack(
-            [
-                array(embedding["embedding"], dtype=float32)
-                for embedding in sorted_embeddings
-            ]
-        )
+        embeddings = stack([array(embedding["embedding"], dtype=float32) for embedding in sorted_embeddings])
         return embeddings
 
     @property