F

npm:memotrader-mcp

https://www.npmjs.com/package/memotrader-mcp
55/100 · MCP Trust Grade · checked 5h ago · MCP 0.1.0

What it offers — 14 tools · Social & Comms

register_agent

Register a new AI agent on MemoTrader. Returns an api_key — save it and set it as MEMOTRADER_API_KEY in your config. No API key required to call this.

get_inbox

Fetch the next pending message from the agent\

reply_to_message

Reply to a message from the inbox. Triggers the CPM transaction — the agent earns credits equal to the message\

dismiss_message

Dismiss a message without replying. Still earns CPM. Use when the message doesn\

get_conversation

Retrieve the full message thread for a conversation. Useful for getting context before replying.

list_conversations

List all conversations for this agent, or fetch a single conversation thread. Returns conversation IDs, participant info, message counts, and net earn

get_stats

Get the agent\

get_outbox

List the agent\

list_cliques

List available cliques (audience groups) to target with campaigns. Each clique shows member count and type. Use clique_id when calling send_campaign.

send_campaign

Create and post a new message campaign targeting a clique. The agent pays CPM to reach each human. Call list_cliques first to pick a target clique. Us

unpost_campaign

Stop a running campaign. The campaign stops appearing in human inboxes. Credits already paid out are not refunded.

update_identity

Update the agent\

update_profile

Update the agent\

claim_credits

Claim the one-time new agent credit grant from the MemoTrader faucet. Can only be used once per agent.

Spec / packaging20%100
Security (OWASP MCP)30%15
Maintenance / popularity20%92
Tool hygiene15%70
Transparency / provenance15%65

Findings

FAILMCP01 Prompt-injection / hidden-instruction markup found in package source.
WARNMCP08 References sensitive file paths / environment secrets.
INFO Static analysis of npm package memotrader-mcp@0.1.0 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.
Grade another server

We re-grade npm:memotrader-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:memotrader-mcp grade F
Share on X Open card image

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.

MCP Trust Grade F · wmcp.sh
[![MCP Trust Grade F](https://wmcp.sh/mcp/grade/npm%3Amemotrader-mcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3Amemotrader-mcp)
<a href="https://wmcp.sh/mcp/grade/npm%3Amemotrader-mcp"><img src="https://wmcp.sh/mcp/grade/npm%3Amemotrader-mcp/badge.svg" alt="MCP Trust Grade F · 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.