agent-state
Verified Safeby tianhuil
Overview
A Model Context Protocol (MCP) server for managing agent state and logs, facilitating interruption and resumption of long-lived agents.
Installation
uv run python main.pySecurity Notes
The server reads and writes to local files (`.agent-state.txt`, `.agent-log.txt`) within a user-provided `directory`. While the `directory` parameter is validated to be an absolute and existing directory, an upstream agent could potentially provide a valid but undesirable directory (e.g., a system directory) if not properly controlled by the calling environment. No direct malicious patterns like `eval`, hardcoded secrets, or network risks are apparent in the provided source.
Similar Servers
zeromcp
A minimal, pure Python Model Context Protocol (MCP) server for exposing tools, resources, and prompts via HTTP/SSE and Stdio transports.
mcp-python-starter
A feature-complete Model Context Protocol (MCP) server template in Python for developing AI applications and agents.
durable-mcp-python
A framework for building durable and fault-tolerant Model Context Protocol (MCP) servers in Python, enabling stateful operations and graceful recovery from disconnections or reboots.
atlantis-mcp-server
An MCP (Model Context Protocol) server for hosting and managing dynamic Python functions and third-party MCP tools, enabling AI agents to discover and utilize shared capabilities across a network.