Lock Your Claws
MCP-native identity, credential vault, and audit layer for every AI agent in the Claw ecosystem. Ed25519 keys. AES-256 encryption. Immutable audit logs. Works everywhere.
The Claw Ecosystem Has a Security Problem
Agent Identity
Ed25519 cryptographic keypairs. Every agent gets its own verifiable identity. No more shared human credentials.
Credential Vault
AES-256-GCM encrypted storage. API keys never stored in plain text or env vars. Agent-scoped access controls.
Audit Ledger
Immutable log of every credential access, scope check, and agent action. Filterable, paginated, tamper-evident.
Scope Enforcement
Least-privilege controls. Agents only access what they are authorized for. Deny-by-default with explicit grants.
Auto-Rotation
Credentials rotate on schedule. No more stale tokens in config files. Set it and forget it.
Portable Identity
Works across any MCP runtime. Claude Desktop, OpenClaw, PicoClaw, ZeroClaw, IronClaw, TinyClaw, and more.
Get Running in 60 Seconds
# Install git clone https://github.com/PalmCoast/clawlock-mcp-server.git cd clawlock-mcp-server npm install && npm run build # Add to Claude Desktop (claude_desktop_config.json) { "mcpServers": { "clawlock": { "command": "node", "args": ["./dist/index.js"] } } } # Register your first agent clawlock_register_agent(name: "my-agent", scopes: ["read:vault", "write:vault"]) # Store a credential clawlock_store_credential(agent_id: "ag_xxx", service: "openai", key: "sk-...") # Use it (decrypted on-the-fly, logged to audit) clawlock_use_credential(agent_id: "ag_xxx", credential_id: "cred_xxx")
Security Is Not Free
48-hour trial with full access. Then pick your plan.
- 5 agent identities
- Credential vault (AES-256)
- Basic audit logs
- Single user
- Email support
- 25 agent identities
- Auto-rotation
- Full audit trail with export
- Team dashboard
- API access
- Priority support
- Unlimited agents
- Compliance reporting
- SSO integration
- SLA guarantee
- Dedicated support
- Custom integrations