// MCP SERVER RECORD

Search

Canonical
NPMsearch-mcp-server
FRisk gradecritical blast radius
Catalogue entry updated 2 days ago
Auth postureNot probedno remote endpoint probed yet
Tools84 Execute · 2 Write · 2 Read
Worst categoryExecutegrade tracks the peak, not the average
Capability mix
Execute 4Write 2Read 2
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Tools 8
browser_clickExecuteHighbrowser_navigateExecuteHighbrowser_tab_switchExecuteLowbrowser_typeExecuteHighbrowser_close_tabsWriteMedium
View all 8 tools
browser_scrollWriteMediumbrowser_snapshotReadLowbrowser_tabsReadLow
These definitions cost 1,704 tokens of context →
Change history
No changes recorded since first scan. Watched servers surface a diff within the hour.
Recommended policy
browser_clickrequire approval
browser_close_tabsrate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →
// RUNNING THIS SERVER
DIRECT INSTALL npx -y search-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.