MCP Safety Warden
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Bind address for HTTP transports | 127.0.0.1 |
| MCP_PORT | No | Bind port for HTTP transports | 8000 |
| SNYK_TOKEN | No | Enables Snyk E001 prompt-injection detection | |
| OLLAMA_MODEL | No | Model name for Ollama provider (e.g. llama3.1, mistral) | |
| MCP_TRANSPORT | No | Transport mode: stdio, sse, or streamable_http | stdio |
| GEMINI_API_KEY | No | Enables Gemini as LLM provider | |
| GOOGLE_API_KEY | No | Legacy alias for GEMINI_API_KEY | |
| MCP_AUTH_TOKEN | No | Bearer token for HTTP transport auth | |
| OPENAI_API_KEY | No | Enables OpenAI as LLM provider | |
| OLLAMA_BASE_URL | No | Ollama API base URL (OpenAI-compatible) | http://localhost:11434/v1 |
| ANTHROPIC_API_KEY | No | Enables Anthropic as LLM provider for classification and scanning | |
| MCP_SCANNER_API_KEY | No | Cisco AI Defense API key for cloud ML engine | |
| MCP_DB_ENCRYPTION_KEY | No | Fernet key to encrypt stored credentials at rest | |
| MCP_SCANNER_LLM_API_KEY | No | LLM key for Cisco internal AST analysis (falls back to OPENAI_API_KEY) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessResponsive