agent-custody
MCP serverGateway that checks agent tool calls against signed grants and records signed receipts
Runs locally- Freemium
- Security
Gateway that checks agent tool calls against signed grants and records signed receipts
Runs locallyMenu bar app and MCP server that stop runaway AI agent processes on a Mac
Not checked yetPre-action firewall that turns thumbs-down feedback into gates for coding agents
Runs locallyLet an AI agent pay USDC on NEAR only within owner-signed mandates, with a signed ledger
Runs locallyCheck whether a Solana or Robinhood Chain coin was bundled, or a wallet has side wallets
Not checked yetCheck x402 sellers before paying, verify USDC payments, scan Solana mints, read pages
Not checked yet
Query threat intelligence on actors, malware, CVEs and IOCs, with cited analyst briefs
Not checked yetLocal permission gate that allows or stops an agent's tool call before it runs
Runs locallyAudit remote MCP servers for OAuth 2.1 gaps, and generate tested connectors
Runs locallyKeeps API key values out of AI chats and deploys them to Cloudflare, Vercel or GitHub
Runs locallyAudit AI agent skills for safety with static, semantic, adversarial and supply-chain scans
Runs locallyEight pay-per-call web tools: verify claims, monitor pages, check links and CVEs
Not checked yetPay-per-call trust scores, co-signed receipts and data passports for agent-to-agent deals
Not checked yetKeep a per-person log of what your agent did, for whom, when and with what result
Not checked yetKubernetes MCP server where every change needs a passkey approval from your phone
Runs locally
Agent jobs: vendor KYB, SAM contractor check, sanctions and wallet screen, notary
Not checked yetChecks one inbound email and returns structured findings on scams, paid links and pitches
Runs locallyLive IP geolocation, ASN and 0-100 risk scores for Claude, ChatGPT and Cursor
Not checked yet
Hash and sign evidence of what AI agents did, mapped to AI governance frameworks
Runs locallySign media with C2PA Content Credentials and check a file's declared origin
Not checked yetGrade x402 payment endpoints and check a payment before an AI agent pays
Not checked yetClaude connector that answers GTM questions with operator evidence and timestamps
Not checked yetTool router and prompt firewall that keeps only a few MCP tools active per turn
Not checked yetCheck a Solana wallet or token and read agent identity and reputation before paying
Not checked yet
Action catalog and approval policy that let agents run server tasks without SSH
Not checked yetFree read-only server listing known security incidents and fix procedures for dev software
Not checked yet
Allow-listed SQL reads and allow-or-deny checks on writes for agents
Not checked yetScan pushed code from your agent, get a short fix-first list, rescan after changes
Not checked yetRun compliance readiness scans on your code from Claude Code, Cursor or Codex
Runs locally
Check AI-written code for leaked keys and invented packages on your own machine
Not checked yet