All integrations
Integration · OpenAI

Unflood for Codex

Build and release from Codex through the same connection, with a Codex plugin. Built, not yet checked live.

What your team gets

The agent stays where you built it. Unflood adds the part a team needs before relying on it.

Set it up

Setup for this host is not available yet. Get in touch to join the pilot.

Exactly what Claude can do through Unflood

Every tool declares its side effect in its MCP annotations, so Claude and your gateway know which ones change things. The table below is generated from the same declarations, and a test fails if they drift apart.

26 tools: 1 read, 22 write, 3 remove or stop.

GroupToolsSide effectWho decides
ReadqueryReadClaude, within what you may see
Build and testcreate_agent, create_tool, create, update, evaluate, ask_agent, proposeWriteYou, in the chat
Releasepackage, publish, approve, select (roll back), decideWriteA named person. Unflood's own agents are refused
Share and accessshare, delegate, connect_tool, refresh_grantsWriteYou, for the people you choose
Runrun, raise, report, emit, resolve, configureWriteYou; runs stay under their limits
Remove or stopdelete, revoke_grant, cancelRemove or stopYou; we suggest Needs approval

What Unflood does not do

  • It does not run your agents

    Claude's model runs them, on your Claude plan. Unflood holds their definitions, tests, evidence and releases.

  • It does not hold your working data

    An agent's tools reach your own systems through a grant you consent to. The data stays there.

  • It does not read your chats

    Unflood receives only what Claude sends in a tool call, nothing else from the conversation.

  • It does not approve anything

    Its own agents propose and prepare. A person approves every release.

  • It does not keep your keys in an agent

    Credentials are held as references, never written into an agent's definition.

For your security review

How the connection is secured, and who decides what.

Protocol
Remote MCP over HTTPS, one address: /mcp.
Sign-in
OAuth 2.1 with discovery (RFC 9728); each person signs in with Google or Microsoft and gets their own token.
Token scope
Each token is issued for Unflood's /mcp only (RFC 8707), and works behind your MCP gateway.
Approvals
Enforced by Unflood on every release, not by a prompt.
Audit
Who changed what, who approved it and why.
Stopping an agent
One command per agent version: it pauses triggers, revokes access and withdraws each host's copy.
Certifications
None claimed.
Read the Trust page
Claude
Turn this conversation into an agent for the finance team.
Unflood made the agent from this conversation, ran its tests and asked you to approve the release.
  • Unflood: Agent made from this conversation 3m ago
  • Unflood: Tests run on the new agent 2m ago
  • Unflood: Released with your approval 1m ago
  • Unflood: Shared with the finance team Just now

Try it on your own agent

Talk to us about a pilot for your team, built on one of your own agents.

Other integrations