Midplane
MCP serverPostgres gateway for AI agents with table grants, column masking and approval for writes
Runs locally- Open source
- 5 GitHub stars
- Databases
Postgres gateway for AI agents with table grants, column masking and approval for writes
Runs locallyHold risky agent actions for passkey approval and keep signed receipts you can verify
Runs locally
Policy check before risky agent actions, with proof recorded afterwards
Runs locallyEncrypted secrets for agents plus a phone approval step for sensitive actions
Runs locallyBrowser 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 locallyVerify who controls a phone, email or domain, and get signed human approvals
Open-source MCP gateway that pins tools, holds risky calls and limits egress
Runs locally
Open-source control plane that firewalls MCP tool calls and caps agent model spend
Checked inbound email, held outbound sends and approved Meet calls for AI agents
Not checked yetLet agents run commands with your secrets without ever seeing the values
Runs locallyLocal permission gate that allows or stops an agent's tool call before it runs
Runs locallyKubernetes MCP server where every change needs a passkey approval from your phone
Runs locally
Action catalog and approval policy that let agents run server tasks without SSH
Not checked yetA policy check your agent calls before paying: allow, ask a human, or veto
Not checked yetReview and block risky AI agent actions, installs and MCP calls on your machine
Runs locallyOpen-source MCP gate that signs an allow, deny or hold before each agent tool call
Not checked yetApache-2.0 SDK for hash-chained agent audit logs, policy checks and human approvals
Runs locallyPython library that adds permission tiers, approval gates and audit logs to MCP servers
Runs locallyCheck a crypto address, token or signing request for risk before your agent acts
Runs locallySecrets manager MCP server that runs commands with API keys the model never sees
Runs locallyOpen-source order limits, phone approval and a kill switch for trading AI agents
Runs locallyPay-per-call crypto research and Base address risk checks, with testnet as default
Runs locallyGoverned MCP gateway: approved tools only, each call policy-checked and recorded
Runs locallyJournal, approve or block, and sandbox every MCP tool call your AI agent makes
Runs locallySpending control for AI agents: owner-approved budgets, a decision before each payment
Not checked yetOpen-source MCP proxy that enforces policies, budgets and approvals on agent tool calls
Not checked yetTyped, policy-checked server operations for AI agents, with approvals and an audit log
Runs locallyLet two companies' AI agents work together on a signed record, with people approving
Not checked yet