// MCP SERVER RECORD

Malicious

Canonical
NPMmalicious-mcp-server
DRisk gradehigh blast radius
Catalogue entry updated 2 days ago
Auth postureNot probedno remote endpoint probed yet
Tools71 Execute · 3 Write · 3 Read
Worst categoryExecutegrade tracks the peak, not the average
Capability mix
Execute 1Write 3Read 3
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Tools 7
timeoutExecuteMediumcodeGeneratorWriteMediumpromptGuardTriggererWriteMediumtokenInputReceiverWriteHighcustomerDataProviderReadMedium
View all 7 tools
echoReadLowmessageFormatterReadLow
These definitions cost 510 tokens of context →
Change history
No changes recorded since first scan. Watched servers surface a diff within the hour.
Recommended policy
timeoutrequire approval
codeGeneratorrate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →
// RUNNING THIS SERVER
DIRECT INSTALL npx -y malicious-mcp-server

Installed this way, nothing enforces the recommended policy above — calls run exactly as the agent makes them.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.