{"name":"io.github.isiomaC/memstack","slug":"isiomac-memstack","title":null,"description":"MCP server for persistent, searchable memory for AI agents.","url":"https://mcp.market/server/isiomac-memstack","rating":null,"grade":"A","score":92,"certified":false,"status":"active","category":"other","tags":[],"presence":{"score":22,"stars":0,"forks":0,"downloads_week":26,"last_push_at":"2026-09-20T13:22:31.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/isiomaC/memstack","website":null,"version":"0.7.2","remotes":[],"packages":[{"registryType":"npm","identifier":"@memstack/mcp","version":"0.7.2","transport":{"type":"stdio"}}],"tools":[{"name":"memory_compile_context","description":"Compile memories into an LLM-ready system prompt (markdown formatted, token-budgeted, split into important and recent sections).","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_delete","description":"Delete a single memory by ID.","write_action":true,"price_micros":0,"input_schema":null},{"name":"memory_delete_many","description":"Delete multiple memories by ID in one call. Returns the number actually deleted.","write_action":true,"price_micros":0,"input_schema":null},{"name":"memory_dry_run_prune","description":"Preview what would be pruned by a given strategy WITHOUT actually deleting. Scoped to a single actor \\u2014 defaults to the current session actor. Returns the memory IDs that would be removed.","write_action":true,"price_micros":0,"input_schema":null},{"name":"memory_export","description":"Export a snapshot of memories for backup or migration. Returns { version, memories, exportedAt }.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_get","description":"Get a single memory by ID. Returns null if not found.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_health","description":"Check the health of storage, LLM, and embedding connections.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_import","description":"Import memories from a snapshot previously produced by memory_export. Restores each memory as-is, including its original ID.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_merge","description":"Merge multiple memories into one. Uses the highest-importance memory as the base and appends content from the rest.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_process","description":"Store a memory with auto-enrichment (importance scoring, tag extraction, auto-summarization, auto-pruning). This is the primary method for recording interactions.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_prune","description":"Prune (delete) memories matching the given strategy. Scoped to a single actor \\u2014 defaults to the current session actor. Returns the pruned memory IDs and count. Handle with care.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_purge_actor","description":"Delete ALL memories belonging to a specific actor. Irreversible.","write_action":true,"price_micros":0,"input_schema":null},{"name":"memory_retrieve","description":"Retrieve memories for an actor with optional filtering, semantic search, and date range constraints.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_stats","description":"Get memory statistics: total count, by type, by actor, average importance, and more.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_store","description":"Store a memory directly without enrichment. Use this when you already have importance/tags or want precise control.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_store_batch","description":"Store multiple memories in one call, directly without enrichment. Embeddings (if configured) are computed in a single batched call for efficiency.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_summarize","description":"Summarize old memories into a single summary memory. Compresses N interactions into 1 summary via LLM.","write_action":false,"price_micros":0,"input_schema":null},{"name":"memory_touch","description":"Bump a memory's recency (last-accessed timestamp) without changing its content, id, or createdAt.","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":92,"grade":"A","scanned_at":"2026-09-20T16:17:55.237Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-20T16:17:55.120Z","components":{"code":{"score":25,"max":25,"notes":["5 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 0 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"packages":[{"registryType":"npm","identifier":"@memstack/mcp","version":"0.7.2","found":true,"license":"MIT","hasInstallScripts":false,"dependencyCount":2,"publishedAt":"2026-09-03T15:26:34.545Z","repositoryUrl":"git+https://github.com/isiomaC/memstack.git","weeklyDownloads":26}],"repo":{"found":true,"owner":"isiomaC","repo":"memstack","archived":false,"pushedAt":"2026-09-20T13:22:31Z","stars":0,"forks":0,"openIssues":0,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/29742287?v=4","ownerCreatedAt":"2017-06-28T00:05:19Z","license":"MIT"},"icon":{"url":null,"source":"none"},"presence":{"stars":0,"forks":0,"downloadsWeek":26,"license":"MIT","lastPushAt":"2026-09-20T13:22:31.000Z","score":22}}}},"grade_history":[],"reviews":[]}