agentic-governance-gateway
by TH07008
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Log level: trace, debug, info, warn, error | info |
| BACKEND_CWD | No | Working directory for the backend process (optional) | |
| BACKEND_ENV | No | JSON object of environment variables for the backend process | |
| CORS_ORIGIN | No | Allowed CORS origin for REST API | * |
| BACKEND_ARGS | No | JSON array of arguments for the backend command (e.g. ["mcp-server-filesystem","/workspace"]) | |
| DATABASE_URL | No | PostgreSQL connection string. When unset or 'memory', uses in-memory storage | memory |
| METRICS_PORT | No | Port for the /metrics endpoint | 9090 |
| OPA_WASM_PATH | No | Path to pre-built OPA WASM bundle. When set, OPA is the primary evaluator | |
| OPA_POLICY_DIR | No | Directory with Rego policy files | ./policies |
| WORKSPACE_ROOT | No | Root directory for path confinement (Ring 1 agents cannot write outside this) | . |
| AGENT_ALLOWLIST | No | Comma-separated list of allowed agent IDs (e.g. claude-code,cursor) | |
| BACKEND_COMMAND | No | Backend MCP server command (e.g. npx). When set, the gateway runs as a transparent proxy | |
| GATEWAY_API_KEY | No | REST API key. Required for REST API to function. Without it, all non-healthz routes return 401 | |
| MCP_SERVER_NAME | No | MCP server name reported to clients | agentic-governance-gateway |
| METRICS_ENABLED | No | Collect Prometheus metrics | true |
| DASHBOARD_ENABLED | No | Enable the HTML dashboard at /dashboard | true |
| AGENT_AUTH_ENABLED | No | Enable agent identity verification on MCP initialize | false |
| MCP_SERVER_VERSION | No | MCP server version | 0.1.0 |
| POLICY_FALLBACK_JS | No | Fall back to TypeScript evaluator when OPA unavailable | true |
| SHADOW_AGENT_POLICY | No | Policy for unknown agents: warn (log only) or deny (block) | warn |
| AGENT_TOOL_ALLOWLIST | No | Per-agent tool allowlist (format: agentId:tool1,tool2;agentId2:tool3) | |
| HITL_TIMEOUT_SECONDS | No | Review request timeout before auto-deny | 300 |
| RATE_LIMIT_PER_MINUTE | No | Max actions per agent per minute | 60 |
| DEFAULT_PRIVILEGE_RING | No | Default privilege ring for unauthenticated agents (0=full, 1=sandboxed, 2=read-only) | 1 |
| DEFAULT_DAILY_BUDGET_USD | No | Default per-agent daily budget cap | 50 |
| DEFAULT_MONTHLY_BUDGET_USD | No | Default per-agent monthly budget cap | 1000 |
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 | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/TH07008/agentic-governance-gateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server