@memstack/mcp

MCPattested
v0.7.2UnknownMITUpdated 2d agonpmGitHub

MCP server for MemStack — AI agent memory via Model Context Protocol

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Attested build
A verified provenance attestation binds this artifact to the listed repository. Nobody has claimed the listing yet — this proves where the code was built, not who stands behind it.
12Downloads/wk
2d agoLast update
Package
AuthorUnknown
LicenseMIT
Version0.7.2
Sourcenpm+mcp-registry
Trust Status
A
85/100Trusted
Listed in Forge index+10/10
Identity verified · attested build+20/20
Ed25519 publish signature+0/5
Included automatically when the publisher runs `forge publish`
Domain verification+0/5
Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
npm Trusted Publishing (Sigstore)+5/5
npm maintainer match+0/5
Publisher: add the verified GitHub login to the npm package's maintainers (npm owner add <login>)
CVE scan · clean+30/30
Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusIdentity verified
PublisherUnverified
SignatureUnsigned
Domain
Provenance✓ Sigstore-verified · d9fb390
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface20 tools · 2 privileged
Security scan✓ Cleanv0.7.2 · todayHow well does this scan work?
PROMPTtool:memory_compile_contextReferences the system prompt
EvalsNone
IndexedSep 6, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

20 tools · 2 privileged
Statically extracted from the published packagev0.7.2 · 3h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

memory_processStore a memory with auto-enrichment (importance scoring, tag extraction, auto-summarization, auto-pruning). This is the primary method for recording interactions.

Store a memory with auto-enrichment (importance scoring, tag extraction, auto-summarization, auto-pruning). This is the primary method for recording interactions.

No input schema was published for this tool.

memory_storeStore a memory directly without enrichment. Use this when you already have importance/tags or want precise control.

Store a memory directly without enrichment. Use this when you already have importance/tags or want precise control.

No input schema was published for this tool.

memory_store_batchStore multiple memories in one call, directly without enrichment. Embeddings (if configured) are computed in a single batched call for efficiency.

Store multiple memories in one call, directly without enrichment. Embeddings (if configured) are computed in a single batched call for efficiency.

No input schema was published for this tool.

memory_getGet a single memory by ID. Returns null if not found.

Get a single memory by ID. Returns null if not found.

No input schema was published for this tool.

memory_retrieveRetrieve memories for an actor with optional filtering, semantic search, and date range constraints.

Retrieve memories for an actor with optional filtering, semantic search, and date range constraints.

No input schema was published for this tool.

memory_compile_contextCompile memories into an LLM-ready system prompt (markdown formatted, token-budgeted, split into important and recent sections).

Compile memories into an LLM-ready system prompt (markdown formatted, token-budgeted, split into important and recent sections).

NOTEReferences the system promptle memories into an LLM-ready system prompt (markdown formatted, token-bu…

No input schema was published for this tool.

memory_summarizeSummarize old memories into a single summary memory. Compresses N interactions into 1 summary via LLM.

Summarize old memories into a single summary memory. Compresses N interactions into 1 summary via LLM.

No input schema was published for this tool.

memory_prunePrune (delete) memories matching the given strategy. Scoped to a single actor — defaults to the current session actor. Returns the pruned memory IDs and count. Handle with care.

Prune (delete) memories matching the given strategy. Scoped to a single actor — defaults to the current session actor. Returns the pruned memory IDs and count. Handle with care.

No input schema was published for this tool.

memory_purge_actorDelete ALL memories belonging to a specific actor. Irreversible.

Delete ALL memories belonging to a specific actor. Irreversible.

No input schema was published for this tool.

memory_mergeMerge multiple memories into one. Uses the highest-importance memory as the base and appends content from the rest.

Merge multiple memories into one. Uses the highest-importance memory as the base and appends content from the rest.

No input schema was published for this tool.

memory_statsGet memory statistics: total count, by type, by actor, average importance, and more.

Get memory statistics: total count, by type, by actor, average importance, and more.

No input schema was published for this tool.

memory_deleteprivilegedDelete a single memory by ID.

Delete a single memory by ID.

No input schema was published for this tool.

memory_delete_manyprivilegedDelete multiple memories by ID in one call. Returns the number actually deleted.

Delete multiple memories by ID in one call. Returns the number actually deleted.

No input schema was published for this tool.

memory_touchBump a memory's recency (last-accessed timestamp) without changing its content, id, or createdAt.

Bump a memory's recency (last-accessed timestamp) without changing its content, id, or createdAt.

No input schema was published for this tool.

memory_exportExport a snapshot of memories for backup or migration. Returns { version, memories, exportedAt }.

Export a snapshot of memories for backup or migration. Returns { version, memories, exportedAt }.

No input schema was published for this tool.

memory_importImport memories from a snapshot previously produced by memory_export. Restores each memory as-is, including its original ID.

Import memories from a snapshot previously produced by memory_export. Restores each memory as-is, including its original ID.

No input schema was published for this tool.

memory_healthCheck the health of storage, LLM, and embedding connections.

Check the health of storage, LLM, and embedding connections.

No input schema was published for this tool.

memory_dry_run_prunePreview what would be pruned by a given strategy WITHOUT actually deleting. Scoped to a single actor — defaults to the current session actor. Returns the memory IDs that would be removed.

Preview what would be pruned by a given strategy WITHOUT actually deleting. Scoped to a single actor — defaults to the current session actor. Returns the memory IDs that would be removed.

No input schema was published for this tool.

memory_contextInjects compiled memory context for the current actor

Injects compiled memory context for the current actor

No input schema was published for this tool.

actorIdActor ID (defaults to session actor)

Actor ID (defaults to session actor)

No input schema was published for this tool.

20 of 20 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

MCP server for MemStack — AI agent memory via Model Context Protocol

Keywords
mcpmemoryaiagentllm
Alternatives
Comparing tool surfaces…

Dependency tree

What one Forge scan resolved from npm metadata on 2026-09-06 — observed resolution, not a publisher declaration.

60 packages resolved · 2 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

The crawl stopped at the depth-4 limit. Anything below that level was never resolved.

The crawl stopped at the 60-package limit. The rest of the tree was never resolved.

36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)

Declared but not resolved

54 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.

+42 more not listed. The counts by reason above cover all of them.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.

Topics

Related in memory & knowledge graphs