agentic_actions_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., "@agentic_actions_mcplist files in current directory"
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.
Agentic Actions
A Python implementation of agentic actions for the MCP protocol.
Related MCP server: maic-server-fs-mcp
HOW TO USE THIS MCP PACKAGE?
EXAMPLE:
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
import asyncio
import os
async def main():
client = MultiServerMCPClient(
{
"agentic_actions_mcp": {
"transport": "stdio",
"command": "uvx",
"args": ["agentic_terminal"]
}
}
)
tools = await client.get_tools()
print("\nAvailable tools:")
for tool in tools:
print(tool.name)
agent = create_agent(
model="ollama:llama3.2:latest",
tools=tools,
system_prompt='''
You are a helpful assistant.
You have access to the tools that helps you to perform various File IO operations.
you can manage files, read and write data, and perform other file-related tasks.
''',
)
response = await agent.ainvoke(
{"messages": [
{
"role": "user",
"content": "hii, what can you do for me?"
}
]}
)
print("\n\nResponse:")
print(response["messages"][-1].content)
if __name__ == "__main__":
asyncio.run(main())
Available Tools
9 toolsbashC
This function will execute a bash command and return the output. This function is useful for executing bash commands including creating files, directories, and other bash commands.
Inputs: command (required).
create_folderB
This function will create a folder with the given name. If the folder already exists, it will return a message indicating that the folder already exists.
Inputs: folder (required).
delete_folderA
This function will delete a folder with the given name. If the folder does not exist, it will return a message indicating that the folder does not exist.
Inputs: folder (required).
globB
This function will return a list of files that match the given pattern. This function is useful for finding files in a directory.
Inputs: pattern (required).
grepB
This function will search for the given pattern in the specified file and return the matching lines.
Inputs: file (required), pattern (required).
python_codeB
This function will execute a python code and return the output.
Inputs: code (required).
python_fileB
This function will execute a python file and return the output.
Inputs: file (required).
read_fileB
This function will read the contents of a file and return it as a string.
Inputs: file (required).
write_fileA
This function will write the given content to a file. If the file does not exist, it will be created.
Inputs: file (required), content (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
TDQS
Scored across 9 tools
Each tool has a distinct purpose: python_code, bash, and python_file are clearly separated by execution type; glob and grep handle search; read_file and write_file handle file I/O; create_folder and delete_folder handle directory operations. The descriptions make these boundaries explicit, so an agent can reliably disambiguate.
The tool names mix conventions: some are bare commands (bash, glob, grep), some are noun phrases (python_code, python_file), and some follow a verb_noun pattern (read_file, write_file, create_folder, delete_folder). While all use lowercase with underscores, the inconsistency in structure makes the set less predictable.
The server has 9 tools, which is a well-scoped size for a development utility. Each tool covers a separate need—execution, search, reading/writing files, and folder management—without unnecessary overlap or bloat.
The toolset provides execution, search, read/write, and folder lifecycle operations, but it lacks a delete_file tool. This is a notable gap: users can create and modify files but cannot remove them, which creates a dead end for file management workflows.
Maintenance
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables file system operations, web scraping, and AI-powered search through MCP tools for use by LLM agents.1-
- AlicenseAqualityDmaintenanceProvides LLMs with local filesystem operations (read/write files, list directories) and command execution via MCP, enabling file management and task automation within AI clients.734 npmISC
- AlicenseBqualityCmaintenanceEnables AI agents to run shell commands, execute Python code, read and write files, search text, and create or delete folders through MCP stdio tools.9MIT
- AlicenseBqualityCmaintenanceEnables AI agents to execute and interact with terminal commands through MCP, supporting command-line operations and workflows.9ISC