Skip to main content
Glama
gautamvarmadatla

MCP Safety Warden

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HOSTNoBind address for HTTP transports127.0.0.1
MCP_PORTNoBind port for HTTP transports8000
SNYK_TOKENNoEnables Snyk E001 prompt-injection detection
OLLAMA_MODELNoModel name for Ollama provider (e.g. llama3.1, mistral)
MCP_TRANSPORTNoTransport mode: stdio, sse, or streamable_httpstdio
GEMINI_API_KEYNoEnables Gemini as LLM provider
GOOGLE_API_KEYNoLegacy alias for GEMINI_API_KEY
MCP_AUTH_TOKENNoBearer token for HTTP transport auth
OPENAI_API_KEYNoEnables OpenAI as LLM provider
OLLAMA_BASE_URLNoOllama API base URL (OpenAI-compatible)http://localhost:11434/v1
ANTHROPIC_API_KEYNoEnables Anthropic as LLM provider for classification and scanning
MCP_SCANNER_API_KEYNoCisco AI Defense API key for cloud ML engine
MCP_DB_ENCRYPTION_KEYNoFernet key to encrypt stored credentials at rest
MCP_SCANNER_LLM_API_KEYNoLLM key for Cisco internal AST analysis (falls back to OPENAI_API_KEY)

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gautamvarmadatla/mcpsafetywarden'

If you have feedback or need assistance with the MCP directory API, please join our Discord server