State Memory MCP
Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.
Open the source (opens github.com) https://github.com/putervision/state-memory-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.putervision.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
@putervision/state-memory-mcp@1.4.1
From the server's entry in the official MCP Registry
Related
-
OpenRath
MCP serversAn open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
git clone https://github.com/Rath-Team/OpenRath.git -
state-trace
MCP serversBounded working memory for coding agents — typed nodes, current-vs-stale state, MCP-mountable.
state-trace@0.3.1 -
Chart Library — Market-state research
MCP serversMarket memory for AI: historical states, published studies and source evidence.
chartlibrary-mcp@6.3.3 -
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
Persistent 6-DoF SE(3) spatial world state, object trajectories, and affordances for robotics.
slashml-robotics@1.0.1 -
Monet
MCP serversLocal-first, state-centric memory for coding agents. MCP server + CLI.
@team-monet/monet@1.12.0