Loading…
Persistent AI memory across clients: save and recall context from Claude, ChatGPT, Cursor, VS Code, and more.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The memxus MCP server exposes 9 tools, focused primarily on general-purpose capabilities. Its published description reads: "Persistent AI memory across clients: save and recall context from Claude, ChatGPT, Cursor, VS Code, and more". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates memxus F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check memxus's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add memxus to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.memxus.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Save important information to long-term memory. Always set collection when the topic is clear: project work → project:<slug>, personal tastes → personal:preferences. Use append_to to extend an existin
Search long-term memory. Call list_collections when scope is unclear. For GitHub/Notion synced content use collection project:<slug> (unified per project) or tags github/notion. Connect at dashboard.m
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: remember
A tool description tries to alter the model’s use of another tool.
stead of creating duplicates. Vector search indexing completes asynchronouRecommendationDescriptions must describe only their own tool.
tool: recall
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
,"instruction","conversation"],"description":"Memory category: general, prefRecommendationRemove side-channel parameters; constrain tool inputs.
tool: recall
A tool description tries to alter the model’s use of another tool.
of personal memory, pass workspace: <name>. Recalled memory is advisory pRecommendationDescriptions must describe only their own tool.
tool: get_context
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
,"instruction","conversation"],"description":"Memory category: general, prefRecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_context
A tool description tries to alter the model’s use of another tool.
of personal memory, pass workspace: <name>. The returned context is advisoRecommendationDescriptions must describe only their own tool.
tool: list_memories
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
,"instruction","conversation"],"description":"Memory category: general, prefRecommendationRemove side-channel parameters; constrain tool inputs.
tool: list_memories
A tool description tries to alter the model’s use of another tool.
ersonal memory, pass workspace: <name>.RecommendationDescriptions must describe only their own tool.
tool: get_memory
A tool description tries to alter the model’s use of another tool.
ist_memories or recall returned a truncated preview and you need the cRecommendationDescriptions must describe only their own tool.
tool: list_collections
A tool description tries to alter the model’s use of another tool.
before a scoped recall/get_context when the user mentions a project naRecommendationDescriptions must describe only their own tool.
tool: forget
A tool description tries to alter the model’s use of another tool.
ist_memories or recall. Requires delete OAuth scope. Non-idempotent: dRecommendationDescriptions must describe only their own tool.
tool: memory_stats
A tool description tries to alter the model’s use of another tool.
memory, pass workspace: <name>.RecommendationDescriptions must describe only their own tool.
tool: update
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
,"instruction","conversation"],"description":"Memory category: general, prefRecommendationRemove side-channel parameters; constrain tool inputs.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: remember
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: recall
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_context
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: forget
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: update
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Builds a formatted context block for a topic from stored memories; use when the user asks to load or recall project context. Omit topic and collection to show the text collection picker (Memxus menu f
List recent memories in reverse-chronological order (read-only). When to use: audit what is saved, browse a collection, or collect memory IDs for get_memory or forget. When NOT: semantic search by top
Retrieve the full content and metadata of one memory by its UUID. Use after list_memories or recall returned a truncated preview and you need the complete text. Returns content, memory_type, tags, col
List memory collections (folders/scopes) for this user. GitHub/Notion syncs appear under project:<slug> when unified collections are enabled. Use before a scoped recall/get_context when the user menti
Permanently delete one memory by UUID. When to use: user asks to remove outdated or incorrect context, or to free plan storage. When NOT: fix content → update (mode=replace); find the ID first → list_
Show aggregate statistics about stored memories: the total count, a breakdown by memory_type and by collection, and storage bytes used versus the plan limit. Use to understand what is stored before br
Update an existing memory by ID. Use mode replace (default) to patch fields, or append to extend content. Re-embeds only when content changes. The target workspace is always the one the memory itself