$ loading_
Surface context-aware warnings for LLM agents and save new notes via MCP.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "soapstone" yet — see the docs or source repo.
Before I modify the payment module code, check whether there are existing gotcha notes and surface the key risks; if none exist, tell me nothing was found.
Returns context-relevant warnings for the payment module, such as past bugs, constraints, or areas that must not be changed.
Save a new gotcha note: before production deployment, the database migration check must be run first, or the service may fail to start because of schema mismatches. Associate this note with the deployment workflow context.
Creates a note tied to the deployment context so future agents can automatically surface it in relevant tasks.
When I query active user data, first check for any notes about the definition of 'active users' and show them before answering to avoid metric misuse.
Shows notes related to metric definitions before the analysis output, helping prevent misunderstandings of data definitions.
Turn local text notes into searchable long-term memory for AI agents.
Let AI assistants capture notes, fetch the latest entry, and summarize all notes.
Add MCP-native notes and memory to ChatGPT, Claude, and other AI tools.
Give AI a persistent notebook shared across tools and sessions.
Secure offline MCP server for searching and editing local Markdown notes
Give agents local memory, recall, search, context, and graph traversal tools.