Claude Memory MCP Server
A persistent memory system for Claude using LanceDB, enabling semantic search, local embeddings, and tools to manage topics, memories, and todos across conversations.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
slaughters85j
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
all_chunks_searchSearch for relevant document chunks in the vector store across all documents. Use with caution as it can return information from irrelevant sources. Requires RAG seeding (npm run seed).
catalog_searchSearch for relevant documents in the catalog. Requires RAG seeding (npm run seed).
chunks_searchSearch for relevant document chunks in the vector store based on a source document from the catalog. Requires RAG seeding (npm run seed).
prune_stale_dataClean up old, low-importance data. Dry-run by default to preview what would be removed.
export_topicExport all memories and todos for a topic as a structured document. Useful for archiving or sharing.
add_memoryStore a distilled memory. Keep content concise (1-10 sentences). For updates to existing memories, use update_memory or set supersedes_id.
update_memoryUpdate an existing memory's content or metadata.
search_memoriesSearch memories using semantic similarity and/or filters. Returns compact results by default.
get_memoryGet full details for a single memory, including linked todos and supersession chain.
get_memory_timelineGet chronological memory history for a topic. Useful for understanding project evolution.
delete_memoryDelete a memory. Use sparingly - prefer updating importance to 0 for soft deprecation.
get_session_contextGet a summary of open items and recent activity. Call this at the start of conversations to check for unfinished work, overdue items, and recent context. Returns compact counts and lists - does not include full memory content.
add_todoCreate a new todo/action item. Link to topic and/or memory for context.
update_todoUpdate a todo's details or status.
list_todosList todos with filtering. Default returns open items sorted by priority.
delete_todoDelete a todo. Prefer setting status to 'cancelled' for audit trail.
create_topicCreate a new topic to organize memories. Topics are buckets for projects, themes, or domains.
update_topicUpdate an existing topic's metadata or status.
list_topicsList topics with optional filtering. Returns compact summaries, not full memory contents.
get_topicGet full details for a single topic, including recent memories and open todos.
delete_topicDelete a topic. Optionally reassign or delete associated memories and todos.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
@langchain/community affected by SSRF Bypass in RecursiveUrlLoader via insufficient URL origin validation
LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoader
uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided
DISABLE_EMBEDDINGS"": "true"OPENAI_API_KEY"": "sk-your-key-here"PREFER_OPENAI_EMBEDDINGS"": "true",Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
21/21 tools missing one or more hints — all_chunks_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); catalog_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); chunks_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +18 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 1 high severity in production deps — @modelcontextprotocol/sdk@1.1.1 (high), @langchain/community@0.3.24 (low)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
1/8 production deps stale: @xenova/transformers@2024-05-29 (2.2y)
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/slaughters85j/claude-memory-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check