PhiSHRI_MCP
by Stryk91
Overview
Provides persistent context 'doors' (JSON bundles) to AI models, allowing them to resume work across sessions, maintain state, and access a structured knowledge base without re-explaining everything.
Installation
./target/release/phishri-mcpEnvironment Variables
- PHISHRI_PATH
- PHISHRI_AGENT_ID
- PHISHRI_SESSION_ID
- PHISHRI_SESSION_ROOT
- PHISHRI_LOG
Security Notes
The Rust server code itself (`phishri-mcp`) appears to be a robust stdio-based application with no direct network listening, dynamic code execution (like `eval`), or hardcoded secrets. It primarily handles file I/O for its knowledge base and session data. However, the project's recommended 'Quick Install' command in the `README.md` uses PowerShell's `Invoke-Expression` (`iex`) on an external script (`install.ps1`). Executing `iex` on a remote script is a critical security vulnerability, allowing arbitrary code execution on the user's machine. This significantly lowers the overall safety rating for users following the recommended setup instructions.
Similar Servers
mcp-server-csdn
The server automatically publishes Markdown articles to the CSDN platform, acting as a tool called by a Spring AI agent.
mcp-server
Provides real-time Indian options market data and volatility analytics from GetOutpost.in to AI chat platforms like Claude for quantitative analysis and trading insights.
drilling_mcp_server
Analyzes oil and gas drilling data from CSV files, providing tools for Rate of Penetration (ROP), Mechanical Specific Energy (MSE), Non-Productive Time (NPT) calculations, and data visualization via an MCP server.
MCPify
Exposes ASP.NET Core endpoints and OpenAPI specifications as tools for Model Context Protocol (MCP) compatible AI agents.