Security ScoreF
0
out of 100
Vulnerabilities Found
22
Crit
15
High
112
Medi
0
Low
0
Info
Last scanned: 7/13/2026
Quality ScoreC
62
out of 100
62
Maint.
85
Popular
31
Docs
73
Compat
Maintenance62%
Popularity85%
Documentation31%
Compatibility73%
Maintenance62
Unknown
Commit Frequency65%
Release Frequency70%
Issue Response45%
Popularity85
4.7K
Stars
9.2K
Downloads
357
Forks
Stars Score100%
Downloads Score71%
Forks Score89%
Documentation31
README Quality35%
Available Documentation
API DocsExamplesChangelog
Compatibility73
MCP Spec Compliance80%
Transport Support50%
Features
TypeScript
Supported Transports
STDIO
Agentic MCP Risk Intelligence
MCPSafe checks risks unique to AI-connected MCP servers — prompt surfaces, model-controlled tools, credentials, filesystems, and network reachability.
6
agentic findings
Severe agentic exposure
Multiple MCP-native exploit paths were detected. Review before connecting this server to an AI client.
Prompt Injection Surface
0
Tool metadata can steer or hijack AI clients before a user invokes the tool.
AI → Command Execution
0
Model-selected tool arguments can reach shell/process execution.
Secret Exfiltration Path
2
Tool context combines credential access with outbound network capability.
Unbounded Filesystem
0
AI-controlled paths may access files outside the intended workspace.
Agent SSRF
4
AI-controlled URLs may reach local, metadata, or internal network services.
Vulnerabilities(149)
22Critical
15High
112Medium
Filter:
READMEExa MCP Server
View sourceExa Search MCP
AI search for AI assistants.
Embed Security Badge
Add this badge to your README or documentation
[](https://mcpsafe.org/registry/exa-search-mcp)Need more customization options?Badge Documentation
Server Information
- Source
- GITHUB
- Package
- @anthropic-ai/mcp-server-exa
- Version
- 0.2.0
- Language
- typescript
- License
- MIT
- Transport
- STDIO
- Added
- Jan 20, 2026
- Updated
- Jul 13, 2026