Borrowing it
Nothing to install: this file belongs to pinkpixel-dev/mem0-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pinkpixel-dev/mem0-mcp/main/.agents/skills/mem0-mcp-modernization/SKILL.mdgit clone --depth 1 https://github.com/pinkpixel-dev/mem0-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pinkpixel-dev/mem0-mcp/mem0-mcp-modernization)<a href="https://agentmods.dev/skills/pinkpixel-dev/mem0-mcp/mem0-mcp-modernization"><img src="https://agentmods.dev/badge/skills/pinkpixel-dev/mem0-mcp/mem0-mcp-modernization/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pinkpixel-dev/mem0-mcp/mem0-mcp-modernization"><img src="https://agentmods.dev/badge/skills/pinkpixel-dev/mem0-mcp/mem0-mcp-modernization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.03618 |
| Opus 5 | $0.00027 | $0.01809 |
| Sonnet 5 | $0.00011 | $0.00724 |
| Haiku 4.5 | $0.00005 | $0.00362 |
Grade C, and why
mem0-mcp-modernization scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
1. **Do not silently send old V2 request shapes to V3 endpoints.** How it starts
The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mem0 MCP Modernization Skill
Purpose
Maintain pinkpixel-dev/mem0-mcp as a reliable MCP interface for Mem0 while supporting its existing Cloud, Supabase, and local/in-memory modes. Prefer a stable, ergonomic MCP layer over exposing every Mem0 REST endpoint blindly.
This skill is specifically about Mem0 Platform API V3 migration and feature design. Treat older V1/V2 assumptions as potentially stale until verified against the current Mem0 docs and installed SDK types.
Non-negotiable rules
- Do not silently send old V2 request shapes to V3 endpoints.
- Do not pretend all Cloud capabilities exist in Supabase or local mode. Capability-report and fail clearly instead.
- Do not expose destructive bulk actions without an explicit confirmation field.
- Do not make callers manually poll async events by default. Provide a good default polling experience with an opt-out.
- Do not remove existing convenient MCP inputs without a compatibility path or a major-version migration note.
- Use the current official docs and installed
mem0aipackage types as final authority when implementation details disagree.
Current Mem0 Platform API facts
Authentication
All hosted REST calls use token authentication:
Authorization: Token <MEM0_API_KEY>
Accept: application/json
Content-Type: application/json
Keep API keys server-side only. Never expose them in browser code, logs, test fixtures, screenshots, or generated docs.
V3 add-memory behavior is asynchronous and ADD-only
Endpoint:
POST https://api.mem0.ai/v3/memories/add/
Minimal request:
{
"messages": [
{ "role": "user", "content": "I moved to Manchester last month." }
],
"user_id": "user-123"
}
Important behavior:
- Requires
messages. - Requires at least one entity scope:
user_id,agent_id,app_id, orrun_id. - Supports
metadata,custom_instructions, andinfer. infer: falsestores messages verbatim instead of invoking memory extraction.- Returns an async event response, usually
PENDINGplusevent_id. - V3 extraction is single-pass ADD-only. It does not automatically update or delete old memories. Memories can accumulate and require deliberate maintenance.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 498 lines · 54 tokens per session scan C 0b9e5995a9c7
mem0-mcp-modernization is a skill published in the GitHub repository pinkpixel-dev/mem0-mcp (98 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 3,618 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
braindb
Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.
braindb-agent
Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.
braindb-custom-profile
How to author a BrainDB custom profile — prompt add/replace fragments and an optional keyless ingestor — that shapes wiki naming/structure and feeds a custom ingestion source, with zero effect on defaults when inactive.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.