fast-agent-mcp 0.3.11__tar.gz → 0.3.13__tar.gz

{fast_agent_mcp-0.3.11 → fast_agent_mcp-0.3.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fast-agent-mcp
-Version: 0.3.11
+Version: 0.3.13
 Summary: Define, Prompt and Test MCP enabled Agents and Workflows
 Author-email: Shaun Smith <fastagent@llmindset.co.uk>
 License:                                  Apache License
@@ -208,10 +208,10 @@ License-File: LICENSE
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.13.5
+Requires-Python: <3.14,>=3.13.5
 Requires-Dist: a2a-sdk>=0.3.6
 Requires-Dist: aiohttp>=3.11.13
-Requires-Dist: anthropic>=0.68.0
+Requires-Dist: anthropic>=0.69.0
 Requires-Dist: azure-identity>=1.14.0
 Requires-Dist: boto3>=1.35.0
 Requires-Dist: deprecated>=1.2.18
@@ -219,8 +219,8 @@ Requires-Dist: email-validator>=2.2.0
 Requires-Dist: fastapi>=0.115.6
 Requires-Dist: google-genai>=1.33.0
 Requires-Dist: keyring>=24.3.1
-Requires-Dist: mcp==1.15.0
-Requires-Dist: openai>=1.109.1
+Requires-Dist: mcp==1.16.0
+Requires-Dist: openai>=2.1.0
 Requires-Dist: opentelemetry-distro>=0.55b0
 Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.7.0
 Requires-Dist: opentelemetry-instrumentation-anthropic>=0.43.1; python_version >= '3.10' and python_version < '4.0'
@@ -249,15 +249,24 @@ Description-Content-Type: text/markdown
 ## Overview
 
 > [!TIP]
-> Documentation site is in production here : https://fast-agent.ai. Feel free to feed back what's helpful and what's not. There is also an LLMs.txt [here](https://fast-agent.ai/llms.txt)
+> Please see : https://fast-agent.ai for latest documentation. There is also an LLMs.txt [here](https://fast-agent.ai/llms.txt)
 
-**`fast-agent`** enables you to create and interact with sophisticated Agents and Workflows in minutes. It is the first framework with complete, end-to-end tested MCP Feature support including Sampling. Model support is comprehensive with native support for Anthropic, OpenAI and Google as well as Azure, Ollama, Deepseek and dozens of others via TensorZero.
+**`fast-agent`** enables you to create and interact with sophisticated multimodal Agents and Workflows in minutes. It is the first framework with complete, end-to-end tested MCP Feature support including Sampling and Elicitations.
 
-![multi_model_trim](https://github.com/user-attachments/assets/c8bf7474-2c41-4ef3-8924-06e29907d7c6)
+<!-- ![multi_model_trim](https://github.com/user-attachments/assets/c8bf7474-2c41-4ef3-8924-06e29907d7c6) -->
 
 The simple declarative syntax lets you concentrate on composing your Prompts and MCP Servers to [build effective agents](https://www.anthropic.com/research/building-effective-agents).
 
-`fast-agent` is multi-modal, supporting Images and PDFs for both Anthropic and OpenAI endpoints via Prompts, Resources and MCP Tool Call results. The inclusion of passthrough and playback LLMs enable rapid development and test of Python glue-code for your applications.
+Model support is comprehensive with native support for Anthropic, OpenAI and Google providers as well as Azure, Ollama, Deepseek and dozens of others via TensorZero. Structured Outputs, PDF and Vision support is simple to use and well tested. Passthrough and Playback LLMs enable rapid development and test of Python glue-code for your applications.
+
+<img width="800"  alt="MCP Transport Diagnostics" src="https://github.com/user-attachments/assets/e26472de-58d9-4726-8bdd-01eb407414cf" />
+
+
+`fast-agent` is the only tool that allows you to inspect Streamable HTTP Transport usage - a critical feature for ensuring reliable, compliant deployments. OAuth is supported with KeyRing storage for secrets. Use the `fast-agent auth` command to manage.
+
+
+
+
 
 > [!IMPORTANT]
 >

{fast_agent_mcp-0.3.11 → fast_agent_mcp-0.3.13}/README.md

@@ -10,15 +10,24 @@
 ## Overview
 
 > [!TIP]
-> Documentation site is in production here : https://fast-agent.ai. Feel free to feed back what's helpful and what's not. There is also an LLMs.txt [here](https://fast-agent.ai/llms.txt)
+> Please see : https://fast-agent.ai for latest documentation. There is also an LLMs.txt [here](https://fast-agent.ai/llms.txt)
 
-**`fast-agent`** enables you to create and interact with sophisticated Agents and Workflows in minutes. It is the first framework with complete, end-to-end tested MCP Feature support including Sampling. Model support is comprehensive with native support for Anthropic, OpenAI and Google as well as Azure, Ollama, Deepseek and dozens of others via TensorZero.
+**`fast-agent`** enables you to create and interact with sophisticated multimodal Agents and Workflows in minutes. It is the first framework with complete, end-to-end tested MCP Feature support including Sampling and Elicitations.
 
-![multi_model_trim](https://github.com/user-attachments/assets/c8bf7474-2c41-4ef3-8924-06e29907d7c6)
+<!-- ![multi_model_trim](https://github.com/user-attachments/assets/c8bf7474-2c41-4ef3-8924-06e29907d7c6) -->
 
 The simple declarative syntax lets you concentrate on composing your Prompts and MCP Servers to [build effective agents](https://www.anthropic.com/research/building-effective-agents).
 
-`fast-agent` is multi-modal, supporting Images and PDFs for both Anthropic and OpenAI endpoints via Prompts, Resources and MCP Tool Call results. The inclusion of passthrough and playback LLMs enable rapid development and test of Python glue-code for your applications.
+Model support is comprehensive with native support for Anthropic, OpenAI and Google providers as well as Azure, Ollama, Deepseek and dozens of others via TensorZero. Structured Outputs, PDF and Vision support is simple to use and well tested. Passthrough and Playback LLMs enable rapid development and test of Python glue-code for your applications.
+
+<img width="800"  alt="MCP Transport Diagnostics" src="https://github.com/user-attachments/assets/e26472de-58d9-4726-8bdd-01eb407414cf" />
+
+
+`fast-agent` is the only tool that allows you to inspect Streamable HTTP Transport usage - a critical feature for ensuring reliable, compliant deployments. OAuth is supported with KeyRing storage for secrets. Use the `fast-agent auth` command to manage.
+
+
+
+
 
 > [!IMPORTANT]
 >

fast_agent_mcp-0.3.13/examples/new-api/fastagent.config.yaml

@@ -0,0 +1,8 @@
+mcp:
+  servers:
+    filesystem:
+      command: "npx"
+      args: ["-y", "@modelcontextprotocol/server-filesystem", "."]
+    fetch:
+      command: "uvx"
+      args: ["mcp-server-fetch"]

fast_agent_mcp-0.3.13/examples/new-api/simple_mcp.py

@@ -0,0 +1,47 @@
+"""
+Demonstration of changing MCP settings dynamically.
+
+Technically applicable to any setting, but MCP I found to be the most difficult due to MCP Aggregation at the startup.
+"""
+
+import asyncio
+
+from fast_agent.agents.agent_types import AgentConfig
+from fast_agent.agents.mcp_agent import McpAgent
+from fast_agent.core.core_app import Core
+from fast_agent.llm.model_factory import ModelFactory
+
+
+async def main():
+    core: Core = Core()
+    await core.initialize()
+
+    # Create agent configuration
+    config = AgentConfig(
+        name="dynamic_bot",
+        model="gpt-4o-mini",
+        servers=[  # Do not forget to add the servers here
+            "fetch",
+        ],
+    )
+
+    agent = McpAgent(
+        config,
+        connection_persistence=True,
+        context=core.context,
+    )
+
+    # Attach the LLM
+    await agent.attach_llm(ModelFactory.create_factory("gpt-4o-mini"))
+    await agent.initialize()  # MCP Agents need to be initialized before use
+
+    # Test the agent
+    result = await agent.send(
+        "Tell me about fast-agent framework. Find info at https://fast-agent.ai/ and summarize it."
+    )
+    print(result)
+    await core.cleanup()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

fast_agent_mcp-0.3.13/examples/tool-use-agent/agent.py

@@ -0,0 +1,33 @@
+import asyncio
+
+from fast_agent import FastAgent
+from fast_agent.agents.agent_types import AgentConfig
+from fast_agent.agents.tool_agent import ToolAgent
+from fast_agent.context import Context
+
+
+def get_video_call_transcript(video_id: str) -> str:
+    return "Assistant: Hi, how can I assist you today?\n\nCustomer: Hi, I wanted to ask you about last invoice I received..."
+
+
+class CustomToolAgent(ToolAgent):
+    def __init__(
+        self,
+        config: AgentConfig,
+        context: Context | None = None,
+    ):
+        tools = [get_video_call_transcript]
+        super().__init__(config, tools, context)
+
+
+fast = FastAgent("Example Tool Use Application")
+
+
+@fast.custom(CustomToolAgent)
+async def main() -> None:
+    async with fast.run() as agent:
+        await agent.default.generate("What is the topic of the video call no.1234?")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

fast_agent_mcp-0.3.13/examples/tool-use-agent/fastagent.config.yaml

@@ -0,0 +1,7 @@
+execution_engine: asyncio
+default_model: gpt-4.1
+
+logger:
+  type: file
+  level: error
+  truncate_tools: true

{fast_agent_mcp-0.3.11 → fast_agent_mcp-0.3.13}/hatch_build.py

@@ -25,17 +25,17 @@ class CustomBuildHook(BuildHookInterface):
             print("Fast-agent build: Cleared existing resources/setup directory")
 
         # Define source to target mappings
+        # Examples:
+        #  examples/workflows -> src/fast_agent/resources/examples/workflows
+        #  examples/mcp/elicitations -> src/fast_agent/resources/examples/mcp/elicitations
+        EXAMPLES_DIR = Path("src") / "fast_agent" / "resources" / "examples"
         example_mappings = {
-            # examples/workflows -> src/fast_agent/resources/examples/workflows
-            "examples/workflows": "src/fast_agent/resources/examples/workflows",
-            # examples/researcher -> src/fast_agent/resources/examples/researcher
-            "examples/researcher": "src/fast_agent/resources/examples/researcher",
-            # examples/data-analysis -> src/fast_agent/resources/examples/data-analysis
-            "examples/data-analysis": "src/fast_agent/resources/examples/data-analysis",
-            # examples/mcp/state-transfer -> src/fast_agent/resources/examples/mcp/state-transfer
-            "examples/mcp/state-transfer": "src/fast_agent/resources/examples/mcp/state-transfer",
-            "examples/mcp/elicitations": "src/fast_agent/resources/examples/mcp/elicitations",
-            "examples/tensorzero": "src/fast_agent/resources/examples/tensorzero",
+            "examples/workflows": EXAMPLES_DIR / "workflows",
+            "examples/researcher": EXAMPLES_DIR / "researcher",
+            "examples/data-analysis": EXAMPLES_DIR / "data-analysis",
+            "examples/mcp/state-transfer": EXAMPLES_DIR / "mcp" / "state-transfer",
+            "examples/mcp/elicitations": EXAMPLES_DIR / "mcp" / "elicitations",
+            "examples/tensorzero": EXAMPLES_DIR / "tensorzero",
         }
 
         # Define setup template mapping (editable templates -> packaged resources)

{fast_agent_mcp-0.3.11 → fast_agent_mcp-0.3.13}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "fast-agent-mcp"
-version = "0.3.11"
+version = "0.3.13"
 description = "Define, Prompt and Test MCP enabled Agents and Workflows"
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -12,10 +12,10 @@ classifiers = [
     "License :: OSI Approved :: Apache Software License",
     "Operating System :: OS Independent"
 ]
-requires-python = ">=3.13.5"
+requires-python = ">=3.13.5,<3.14"
 dependencies = [
     "fastapi>=0.115.6",
-    "mcp==1.15.0",
+    "mcp==1.16.0",
     "opentelemetry-distro>=0.55b0",
     "opentelemetry-exporter-otlp-proto-http>=1.7.0",
     "pydantic-settings>=2.7.0",
@@ -23,8 +23,8 @@ dependencies = [
     "pyyaml>=6.0.2",
     "rich>=14.1.0",
     "typer>=0.15.1",
-    "anthropic>=0.68.0",
-    "openai>=1.109.1",
+    "anthropic>=0.69.0",
+    "openai>=2.1.0",
     "azure-identity>=1.14.0",
     "boto3>=1.35.0",
     "prompt-toolkit>=3.0.52",

{fast_agent_mcp-0.3.11 → fast_agent_mcp-0.3.13}/src/fast_agent/agents/llm_agent.py

@@ -170,7 +170,7 @@ class LlmAgent(LlmDecorator):
                 combined += segment
             additional_message_text = combined
 
-        message_text = message.last_text() or ""
+        message_text = message
 
         # Use provided name/model or fall back to defaults
         display_name = name if name is not None else self.name

{fast_agent_mcp-0.3.11 → fast_agent_mcp-0.3.13}/src/fast_agent/agents/llm_decorator.py

@@ -314,6 +314,13 @@ class LlmDecorator(AgentProtocol):
         # Otherwise treat the string as plain content (ignore arguments here)
         return await self.send(prompt)
 
+    def clear(self, *, clear_prompts: bool = False) -> None:
+        """Reset conversation state while optionally retaining applied prompt templates."""
+
+        if not self._llm:
+            return
+        self._llm.clear(clear_prompts=clear_prompts)
+
     async def structured(
         self,
         messages: Union[

{fast_agent_mcp-0.3.11 → fast_agent_mcp-0.3.13}/src/fast_agent/agents/tool_agent.py

@@ -1,4 +1,4 @@
-from typing import Any, Callable, Dict, List
+from typing import Any, Callable, Dict, List, Sequence
 
 from mcp.server.fastmcp.tools.base import Tool as FastMCPTool
 from mcp.types import CallToolResult, ListToolsResult, Tool
@@ -35,7 +35,7 @@ class ToolAgent(LlmAgent):
     def __init__(
         self,
         config: AgentConfig,
-        tools: list[FastMCPTool | Callable] = [],
+        tools: Sequence[FastMCPTool | Callable] = [],
         context: Context | None = None,
     ) -> None:
         super().__init__(config=config, context=context)