Mem0CAUTION
A memory system using mem0 for AI applications. Enables long-term memory for AI agents as a drop-in MCP server.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://badge.fury.io/js/@pinkpixel%2Fmem0-mcp) [](https://opensource.org/licenses/MIT) [](https://nodejs.org/) [](https://www.typescriptlang.org/) [](https://modelcontextprotocol.io/) [](https://mem0.ai) [](https://www.npmjs.com/package/@pinkpixel/mem0-mcp) [](https://github.com/pinkpixel-dev/mem0-mcp) [](https://smithery.ai/server/@pinkpixel-dev/mem0-mcp-server)
A Model Context Protocol (MCP) server that integrates with Mem0.ai to provide persistent memory capabilities for LLMs. It allows AI agents to store and retrieve information across sessions.
This server uses the mem0ai Node.js SDK for its core functionality.
Features 🧠
Modernized & Advanced Tools (v0.8.0)
- `add_memory`: Stores a memory from text content or structured message arrays.
- Inputs:
content(string) ormessages(array of role/content objects),userId(string),runId/sessionId(string),agentId(string),appId(string),metadata(object),infer(boolean),customInstructions(string),waitForCompletion(boolean, default: true),timeoutMs(number, default: 15000) - Behavior: Cloud V3 additions are asynchronous. By default, this tool polls the background queue until completed. Pass
waitForCompletion: falseto get theeventIdimmediately. - **`search_m
fe7834b1cec1OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mem0-mcp --env MEM0_API_KEY=${MEM0_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} --env SUPABASE_KEY=${SUPABASE_KEY} -- npx -y @pinkpixel/[email protected]{
"mcpServers": {
"mem0-mcp": {
"command": "npx",
"args": [
"-y",
"@pinkpixel/[email protected]"
],
"env": {
"MEM0_API_KEY": "${MEM0_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"SUPABASE_KEY": "${SUPABASE_KEY}"
}
}
}
}Exposed tools (16)
10 read · 4 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_memory | write | Stores a piece of text or structural messages as a memory in Mem0. |
batch_delete_memories | destructive | Performs bulk deletions of multiple memories. |
batch_update_memories | write | Performs bulk updates of text contents for multiple memories (cloud only). |
create_memory_export | write | Kicks off an async memory export query job (cloud only). |
delete_memory | destructive | Deletes a specific memory record by ID. |
get_memory | read | Gets a single memory by its ID. |
get_memory_capabilities | read | Returns the features and APIs supported by the current storage mode backend. |
get_memory_event | read | Manually retrieves detail logs of a specific background event job (cloud only). |
get_memory_export | read | Retrieves status and downloads of a memory export job (cloud only). |
get_memory_history | read | Gets the audit trail and revision log of a memory (cloud only). |
list_memories | read | Lists all memories scoped to specific identifiers with pagination. |
list_memory_events | read | Lists history logs of background memory processing events (cloud only). |
rate_memory | read | Submits quality feedback evaluation for a memory record (cloud only). |
search_memories | read | Searches stored memories based on a query. |
search_memory | read | Backward-compatible alias for search_memories. |
update_memory | write | Updates a specific memory record. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
vsce
batch_delete_memories, delete_memory
mem0ai, @types/node, typescript
Gates applied: no_behavioural_pass.
fe7834b1cec1full audit observations/trust-audit/mcp-server/pinkpixel-dev__mem0.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | fe7834b1cec1 | CAUTION | B | 89 | first audit |
Questions
What is the Mem0 MCP server?
A memory system using mem0 for AI applications. Enables long-term memory for AI agents as a drop-in MCP server.
What tools does Mem0 expose?
16 in total: 10 read-only, 4 that write, and 2 that can delete or overwrite (batch_delete_memories, delete_memory). Every one is listed on this page with its risk.
Is Mem0 safe to connect to an agent?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Mem0 need?
It reads MEM0_API_KEY, OPENAI_API_KEY and SUPABASE_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Mem0 run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @pinkpixel/mem0-mcp at 0.8.0.
How current is this page?
The grade is for one exact copy of the source (fe7834b1cec1), read on 2026-10-07. The repository is watched and re-audited when it changes.