What it does
Recall is an MCP server that provides memory and state for AI agents. Every correction is stored together with its history, so earlier versions of the agent's recorded information remain available.
According to the publisher, the server also lets an agent resume after a crash, which suggests use in agent workflows that must survive interruptions. The publisher's description is the only source for this entry, so no further setup or usage details are listed here.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Recall
Memory and state for AI agents: every correction kept with its history, and resume after a crash.
v0.25.0As shown on registry.modelcontextprotocol.io when we last read it