What protocol does PhotonDB use?
PhotonDB uses a simple TCP-based protocol for communication between server and client.
@s1ddh3sh
Basic information
PhotonDB is a modern C++ rendition of a high-performance in-memory key-value database with MCP server. The data model is key-value, active development is underway to support a wide variety of value types
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
PhotonDB is a high-performance in-memory key-value database server written in C++17. It provides access to mutable data structures via a simple TCP-based protocol using a server-client model and also integrates with the Model Context Protocol (MCP) for natural-language interactions.
Start a photon server instance with ./src/server and interact via photon-cli using commands like set, get, and ZAP. For MCP interactions, use server.py with uv as the Python package manager and install it on Claude Desktop with uv run mcp install server.py.
photon-cliset, get, ZAPPhotonDB uses a simple TCP-based protocol for communication between server and client.
Clone the repository, create a build directory, run CMake (version 3.10 or newer), and then run `make` from the build directory. A C++17 compiler is required.
Yes. PhotonDB includes an MCP server implementation in `server.py` that can be installed on Claude Desktop using `uv run mcp install server.py`.
Use the command-line tool `photon-cli`, which connects to the server and accepts commands like `set`, `get`, and `ZAP`.
For the core server: CMake (3.10+) and a C++17 compiler. For MCP integration: Python with the `mcp[cli]` package and `uv` as the package manager.
A curated list of references for MLOps
Hindsight: Agent Memory That Learns

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Comments