
Marrow AI: Control Layer for AI Agents
MCP serverPolicy check before risky agent actions, with proof recorded afterwards
Runs locally- 2 tools
- Freemium
- Security

Policy check before risky agent actions, with proof recorded afterwards
Runs locallyDaily-checked WordPress versions, plugin facts and security news for AI agents
Look up who stands behind a website or AI agent and what the agent may do
Read-only Solana wallet safety checks: risky approvals, scam tokens and reclaimable SOL
103 cheap read-only tools for agents: token safety, tx decoding, gas, ENS, DNS
Scan prompts for injection and PII, and audit LLM SDK usage from an MCP client
Scan, read and write another process's memory from an AI assistant
Runs locallySecurity verdicts and a runtime guard for agent skills and MCP servers before they run
Runs locallyGive AI agents WhatsApp, Telegram and PostgreSQL access limited by explicit scopes
Not checked yetFree read-only verification tools for agents, with a signed receipt on every call

Record signed events, AI outputs and document fingerprints, then verify them later
Gate every MCP tool call behind signed authorization and single-use capabilities
Runs locallyAfrican holidays, VAT, withholding tax, tax IDs and filing dates for 54 countries
Score a domain's DNS, email authentication and TLS posture, with fixes
Browser actions for AI agents that are classified, approved and logged
Runs locallyAllow, deny or step-up checks on AI agent writes, with a tamper-evident log
Runs locallyMCP wrapper that holds database writes until a second person approves them on their phone
Runs locallyScan a URL for AI Act issues, classify risk and issue Article 50 notices and receipts
Free x402 preflight gate and paid on-chain checks before an agent signs a transaction
Runs locallyScreen banks, wires, sanctions, wallets and transfers before an agent moves money
Versioned store for specs, plans and tasks that AI agents read and write
Not checked yetGives coding agents your API keys without letting the model ever read them
Runs locallyCheck user prompts for injection and jailbreaks with a guard that learns from your labels
Scan PDFs and Office files for malware and hidden prompt injection before an AI reads them
Mask PII and secrets in local memory before text reaches an AI model
Runs locallyAudit AI agent prompts, MCP tool schemas and agent graphs from your IDE
Read-only Trino access for agents, run as the verified user so Trino policy decides
Runs locally
Rank security scanner findings by exposure, criticality and exploitability
Runs locallyKeep API keys in your OS keychain and give coding agents only what policy allows
Runs locallyFree, keyless email checks for fake signups: disposable domains, typos, Gmail aliases