D.Va Exa Web Search Free

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a simple Exa MCP search setup with no code or credentials, but it sends search requests to Exa and optional advanced mode enables broader web-research tools.

This skill appears safe for normal web/code/company search if you trust Exa and mcporter. Before installing, understand that your queries may leave your environment, and only enable the advanced exa-full tools if you want crawling, people search, and deep-research capabilities.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Search terms, company research requests, or code queries may be visible to the external provider.

Why it was flagged

The skill configures a remote MCP provider, so user queries and tool interactions are sent outside the local environment to Exa.

Skill content
mcporter config add exa https://mcp.exa.ai/mcp
Recommendation

Use it only if you are comfortable sending those queries to Exa, and avoid including secrets or confidential data unless that is permitted.

What this means

If enabled, the agent can perform broader web extraction, professional profile lookup, and remote deep-research workflows through Exa.

Why it was flagged

The optional full configuration expands the skill beyond basic search to broader retrieval and research-agent tools. This is disclosed and optional, but users should notice the wider capability.

Skill content
Six additional tools available by updating config URL: ... `crawling_exa` - Full page extraction ... `people_search_exa` - Professional profiles ... `deep_researcher_start/check` - AI research agent
Recommendation

Enable the full toolset only when needed, and keep sensitive or high-impact research tasks clearly user-directed.