dynamic-tool-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dynamic-tool-mcpCall the add_numbers tool with a=5, b=3"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-server-tool-kit
Minimal stand-in for the Tools Framework (package dynamic-tool-mcp) expected by
agentic-assembly-framework. A FastMCP server that dynamically loads
tools from .py+.yaml pairs, plus a client satisfying AAF's McpRuntimeAdapter
contract (get_session(server_url, bearer_token) -> session.call_tool(id, input)).
Pairs with agent-impl-tool-kit, the sibling stand-in for
AAF's Agent Framework (agentic-platform) — together the two satisfy AAF's
AgenticPlatformAdapter and McpRuntimeAdapter contracts for local dev.
Run it
pip install -e .
dynamic-tool-mcp --tools-dir tools --host 127.0.0.1 --port 9100Related MCP server: my-mcp-server
Adding a tool
Drop a matching pair into the tools directory — no restart-time registration:
tools/
├── add_numbers.yaml # id, description, input_schema, function (default "run")
└── add_numbers.py # def run(input: dict) -> objectAuth
Set MCP_BEARER_TOKENS (comma-separated) to require a bearer token on every
request. Omit it to run with no auth, matching a local-dev assembly.
Client
from dynamic_tool_mcp.client import DynamicToolMcpClient
client = DynamicToolMcpClient()
session = await client.get_session("http://127.0.0.1:9100/sse")
result = await session.call_tool("add_numbers", {"a": 1, "b": 2})This server cannot be deployed
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server exposing the Backtest360 engine API as tools for AI agents.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Related MCP Servers
- AlicenseBqualityDmaintenanceA dynamic MCP server that automatically discovers Python files in a directory and exposes them as tools to any MCP-compatible AI client, allowing users to easily create and deploy custom AI tools.1MIT
- FlicenseBqualityDmaintenanceA Model Context Protocol server built with FastMCP that enables dynamic tool loading and configuration from individual Python files. It provides a flexible framework for automatically discovering, testing, and running tools via Stdio or HTTP transport modes.1-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server built with FastMCP that features dynamic tool loading and modular management via a dedicated tool directory. It supports both stdio and HTTP transport modes, enabling efficient development and deployment of custom MCP tools.-
- FlicenseBqualityDmaintenanceA Model Context Protocol server framework featuring dynamic tool loading and automatic tool discovery from a dedicated directory. It leverages FastMCP to provide a robust environment for building, configuring, and testing individual Python-based tools.1-