Install SafePrompt in Claude Code
Remote URL
claude mcp add --transport http safeprompt https://mcp.safeprompt.dev/mcp{
"mcpServers": {
"safeprompt": {
"url": "https://mcp.safeprompt.dev/mcp"
}
}
}npm
claude mcp add safeprompt -e SAFEPROMPT_API_KEY=... -- npx -y @safeprompt.dev/mcp{
"mcpServers": {
"safeprompt": {
"command": "npx",
"args": [
"-y",
"@safeprompt.dev/mcp"
],
"env": {
"SAFEPROMPT_API_KEY": "..."
}
}
}
}Replace each ... with your own value.
Frequently asked questions
What does the SafePrompt MCP server do?
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
Is the SafePrompt MCP server free?
The server is free, but you will likely need an account. The server itself is free, but it connects to a service that needs an account or API key, which may have paid tiers. Check the provider for current pricing.
Does SafePrompt run locally or remotely?
Local + Remote. Can run locally or be used as a hosted remote server.
How do I add SafePrompt to Claude Code?
Run: claude mcp add --transport http safeprompt https://mcp.safeprompt.dev/mcp
More ai agents & coding agents MCP servers
View allsemantic-scala
DmytroMitin/scala-semantic-harness
Bounded Scala compiler, build, test, type, effect, symbol, and SemanticDB evidence for agents.
Roslyn Workbench
lantean-code/roslyn-workbench-mcp
Bring Visual Studio-style C# fixes and refactorings to your AI agent with local Roslyn Code Actions.
Shield Kya
The-Pixel-Boys/shield-kya
Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.
QuantGist
QuantGist-Technologies/QuantGist_MCP
Macro events, earnings & market data from QuantGist for Claude and other AI agents.
SuperMemory
YashvantHange/SuperMemory
MCP-first agent learning: capture failures, validate lessons, retrieve context, improve.
Progi
zseta/progi
MCP-native workflow engine: teach agents your processes once, they execute them consistently.