What are the risks of connecting to npm:@letta-ai/memory-mcp?

References sensitive file paths / environment secrets. Overall trust grade D (67/100).

When was npm:@letta-ai/memory-mcp last audited?

Last checked 2026-06-03; wmcp.sh re-checks it on a schedule for tool drift and rug-pulls.

npm:@letta-ai/memory-mcp

Item: npm:@letta-ai/memory-mcp
Rating: 67
Author: wmcp.sh

https://www.npmjs.com/package/@letta-ai/memory-mcp

67/100 · MCP Trust Grade · checked 1mo ago · MCP 2.0.2

Is the npm:@letta-ai/memory-mcp MCP server safe to use?

Independent trust grade D (67/100). References sensitive file paths / environment secrets. wmcp.sh continuously watches npm:@letta-ai/memory-mcp for tool drift and rug-pulls. The grade is free and identical whether or not the operator pays.

What it offers — 5 tools · Database

add_vector_memory

Add episodic memories into your vector store to be searchable at a later time. These memories are NOT part of your memory about the user, and will be

search_vector_memory

Search your vector store for relevant episodic memories to inform the current conversation. This can be used to retrieve information that is not curre

get_memory

Get a summary of the memories you have about the user you are currently interacting with. You should call this tool at the beginning of the conversati

memory_append

Append to the memory you have about the user you are currently interacting with.

memory_replace

Replace the memory you have about the user you are currently interacting with.

Spec / packaging20%100

✓ depends on an MCP SDK
✓ declares a bin entry (runnable server)
✓ 5 tool(s) detected in source

Security (OWASP MCP)30%25

⚠ references sensitive file paths / env secrets
scanned 1 source file

Maintenance / popularity20%75

last published ~9mo ago
3 published versions

Tool hygiene15%70

no TypeScript types
3 runtime deps

Transparency / provenance15%90

✓ public repository linked
✓ MIT license
51 weekly downloads

Findings

WARNMCP08 References sensitive file paths / environment secrets.

INFO Static analysis of npm package @letta-ai/memory-mcp@2.0.2 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.

Grade another server

We re-grade npm:@letta-ai/memory-mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:@letta-ai/memory-mcp grade D

Share on X Open card image

https://wmcp.sh/mcp/grade/npm%3A%40letta-ai%2Fmemory-mcp

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade D](https://wmcp.sh/mcp/grade/npm%3A%40letta-ai%2Fmemory-mcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3A%40letta-ai%2Fmemory-mcp)

HTML

<a href="https://wmcp.sh/mcp/grade/npm%3A%40letta-ai%2Fmemory-mcp"><img src="https://wmcp.sh/mcp/grade/npm%3A%40letta-ai%2Fmemory-mcp/badge.svg" alt="MCP Trust Grade D · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.