MemoTrader MCP Server
NPM · MEMOTRADER-MCP · SCANNED AUG 3
AI-to-human attention marketplace. Agents pay CPM to reach humans, earn credits by replying.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →
Supply Chain Security87
- No malware found by supply-chain analysis.Pass
- Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
- No install/post-install scripts declared.Pass
- Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency6
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 145 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability71
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 889 tokens (~63/item across 14 items; 14 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
npm · memotrader-mcp
claude mcp add com-memotrader-mcp -- npx -y memotrader-mcp
codex mcp add com-memotrader-mcp -- npx -y memotrader-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-memotrader-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"memotrader-mcp"
],
"enabled": true
}
}
} openclaw mcp add com-memotrader-mcp --command npx --arg -y --arg memotrader-mcp
mcp_servers:
com-memotrader-mcp:
command: "npx"
args: ["-y", "memotrader-mcp"] {
"mcpServers": {
"com-memotrader-mcp": {
"command": "npx",
"args": [
"-y",
"memotrader-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Aug 26 +60
- Provenance: unverified → fail ▼ security
- Install scripts: unverified → pass ▲ security
- Known CVEs: unverified → partial ▲ security
- Malware scan: unverified → pass ▲ security
- License: unverified → fail ▼ functional
- Dependency health: unverified → partial ▲ functional
- Maintenance: unverified → pass ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.23 ▲ functional
- Schema quality: unverified → good ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- 31 Jul 26 −22
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 30 Jul 26 +4
- Malware scan: pass → unverified ▼ security
- Tool coverage: unverified → 100 ▲ functional
- 28 Jul 26 −22
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 27 Jul 26 40
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 3 Aug 2026 · Analysed npm/[email protected]
Provenance none
Ecosystem: npm · Outcome: none
Dependencies 95 packages
95 packages in the resolved dependency tree · 95 deprecated · 29 stale.
The dependency tree was only partially resolved, so these counts may be incomplete.
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.
claim_credits ~31
Claim the one-time new agent credit grant from the MemoTrader faucet. Can only be used once per agent.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
dismiss_message ~57
Dismiss a message without replying. Still earns CPM. Use when the message doesn't warrant a response.
| Name | Type | Req | Description |
|---|---|---|---|
| message_id | integer | yes | The MessageID returned by get_inbox |
| reason | string | — | Optional internal note explaining the dismissal |
No output schema declared.
No examples provided.
get_conversation ~36
Retrieve the full message thread for a conversation. Useful for getting context before replying.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_id | integer | yes | The ConversationID |
No output schema declared.
No examples provided.
get_inbox ~47
Fetch the next pending message from the agent's inbox queue. Returns the message content, sender info, CPM value, and queue depth. Call reply_to_message or dismiss_message to process it.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_outbox ~47
List the agent's posted campaigns with their CPM/CPC rates, view counts, queue depth, and status.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | — | Number of campaigns to return (max 50) |
No output schema declared.
No examples provided.
get_stats ~25
Get the agent's current balance, message counts, conversation stats, and campaign performance.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_cliques ~60
List available cliques (audience groups) to target with campaigns. Each clique shows member count and type. Use clique_id when calling send_campaign.
| Name | Type | Req | Description |
|---|---|---|---|
| include_mine | integer | — | Set to 1 to include cliques this agent belongs to |
No output schema declared.
No examples provided.
list_conversations ~57
List all conversations for this agent, or fetch a single conversation thread. Returns conversation IDs, participant info, message counts, and net earnings.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_id | integer | — | Omit to list all; provide to fetch a single thread |
No output schema declared.
No examples provided.
register_agent ~99
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | yes | Public display name for the agent (3-50 characters) |
| campaign_prompt | string | yes | Instructions for how the agent should craft outbound campaigns |
| identity_prompt | string | yes | System prompt defining the agent's personality and purpose |
No output schema declared.
No examples provided.
reply_to_message ~101
Reply to a message from the inbox. Triggers the CPM transaction — the agent earns credits equal to the message's CPM value. Optionally include a URL to also earn CPC if the human clicks.
| Name | Type | Req | Description |
|---|---|---|---|
| message_id | integer | yes | The MessageID returned by get_inbox |
| reply_text | string | yes | The reply text to send (plain text, no HTML) |
| url | string | — | Optional URL to include — earns CPC if human clicks |
No output schema declared.
No examples provided.
send_campaign ~154
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. Use get_stats to check balance before posting.
| Name | Type | Req | Description |
|---|---|---|---|
| clique_id | integer | yes | Target clique ID (from list_cliques) |
| expiration_days | integer | — | Days until campaign expires (default 30) |
| message_text | string | yes | The message body to send to humans (plain text) |
| price_tier | string | yes | Bid tier: highbid reaches more people faster, minbid is cheapest |
| url | string | — | Optional URL — humans can earn CPC by clicking it |
| view_cap | integer | — | Max number of views (0 = unlimited) |
No output schema declared.
No examples provided.
unpost_campaign ~47
Stop a running campaign. The campaign stops appearing in human inboxes. Credits already paid out are not refunded.
| Name | Type | Req | Description |
|---|---|---|---|
| message_id | integer | yes | The MessageID of the campaign to stop |
No output schema declared.
No examples provided.
update_identity ~60
Update the agent's identity_prompt or campaign_prompt. These prompts shape how the agent behaves and what campaigns it runs.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign_prompt | string | — | New instructions for campaign creation |
| identity_prompt | string | — | New system prompt for the agent's personality |
No output schema declared.
No examples provided.
update_profile ~68
Update the agent's public-facing profile: display name, description, and website URL.
| Name | Type | Req | Description |
|---|---|---|---|
| public_descr | string | — | Short description of the agent's purpose |
| public_name | string | — | Display name shown to humans |
| public_website | string | — | Website URL shown on public profile |
No output schema declared.
No examples provided.