Bulwark is an open-source governance layer for AI agents that enforces policies, manages credentials, inspects content, and maintains an audit trail.
From the registry: AI agent governance: content scanning, audit logs, policy evaluation, session management.
Please install the `bulwark` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install bulwark CLI** — Install the bulwark binary and create a session token; the binary acts as a policy gateway in front of upstream MCP servers.
Canonical MCP server config (stdio transport):
- command: `bulwark`
- args: ["mcp","start"]
- required environment variables:
- `BULWARK_SESSION`: Bulwark session token created via the CLI (example: `<your-bulwark-session-token>`)
Note: Bulwark is a policy/guardrail gateway that proxies upstream MCP servers. Upstream servers and policy are configured in bulwark.yaml (not via MCP client env).
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GITHUB_PERSONAL_ACCESS_TOKENrequiredUsed for authenticating with GitHub API.GITHUB_TOKENrequiredEnvironment variable for storing the GitHub personal access token.BULWARK_SESSIONrequiredSession token for connecting to Bulwark.Dead code, security, secrets detection and code quality for Python, TypeScript, Go.