Coverage map · verified 4 September 2026

What we can gate today, per agent.

The fair question from every security review: can a third party really sit between a closed agent and the world? The answer depends on the surface, so here it is surface by surface, checked against each vendor's own documentation on the date above. Where we cannot reach, the table says so.

What this map is for. Ripcord gates actions on your systems: payments, records, sends, deploys. Browsing inside a vendor's sandbox is not the threat model; the wire to your ERP is. An agent that reads and clicks all day touches your company only when it presents a key to one of your systems, and that is the moment the table is about.

Why the wiring is ours to gate

The Model Context Protocol is not a lab's property. The specification sits under the Linux Foundation's Agentic AI Foundation, licensed Apache-2.0, governed by named individuals rather than company seats, with Anthropic, OpenAI, Google, Microsoft and AWS as platinum members. Every major agent ships an MCP client. What matters for gating is who configures the servers an agent calls: the customer, in a config file or an admin console, never the lab. Ripcord's proxy stands in front of the server the customer configured, on every tool call, whichever model is inside. The July 2026 revision of the protocol even added routing headers designed for intermediaries.

What no protocol gives us: the agents' built-in tools (a coding agent's shell and file edits), the vendors' first-party connectors (called inside the vendor's own cloud), and clicks (browser and computer use). For the built-in tools, the agents' own hook systems are the way in, and the table shows which ones exist.

Coding agents

Four rungs of control, from the proxy to the admin. A tick means it works today; a tilde means it works with a caveat named in the cell; a cross means we cannot see it and say so.

Agent MCP tool calls
the proxy, today
Their built-in paths
shell, files, first-party connectors
Hold for a human
before execution
Clicks
browser and computer use
Fleet-wide
enforced by an admin
Claude Code
Anthropic · CLI, IDE, desktop, web
stdio and HTTP servers; org allowlists and a managed server listPreToolUse hook on Bash, Edit, Write, WebFetch, Agent and every MCP toolthe hook can answer allow, deny or askbrowser and desktop control are themselves MCP servers, so the same rules applymanaged hooks, managed-hooks-only lock, server allowlists
Cursor
IDE and cloud agents
enterprise allowlist by command or URL patternbeforeShellExecution and beforeMCPExecution; file writes deny-onlyask on shell and MCP calls~browser tool is MCP-based; hook coverage not documentedteam hooks from the dashboard or MDM
Codex CLI
OpenAI · CLI and IDE extension
identity-matched server allowlistPreToolUse on Bash, apply_patch and MCP: deny or rewrite~no ask in the hook yet; the hold comes from approval policybrowser and computer use live in the desktop app, not the CLIrequirements.toml: managed hooks, pinned policies
Gemini CLI
Google · CLI
mcp.allowed at system levelBeforeTool hook on shell, files, web and MCP: deny or rewrite~ask only through a static policy rule, not from the hook~experimental browser agent; hook coverage not documentedadmin policy tier overrides everything

Desktop and enterprise agents

The enterprise tiers sell permissions, roles, confirmation dialogs and audit logs for their own agent. Those are real, and they are the authorize and contain layers of the map, one vendor at a time. None of them prices an action by expected loss, routes a hold to the owner of the consequence, keeps the action reversible, or keeps a record across vendors. That is the layer beneath them, and it is reachable wherever the customer can add a connector.

Product MCP tool calls
the proxy, today
Their built-in paths
shell, files, first-party connectors
Hold for a human
before execution
Clicks
browser and computer use
Fleet-wide
enforced by an admin
Claude Cowork and Claude for Enterprise
Anthropic · desktop and web agents
custom remote connector added by an org owner; per-tool always-allow, needs-approval or blockedAnthropic's own connectors run server-side and never cross a customer MCP~inference hooks can deny the next model turn after seeing a tool call; no hold before executionbuilt-in browser, Chrome and desktop control are out of reachowner controls, OpenTelemetry stream of every tool call and approval
ChatGPT Enterprise and ChatGPT Work
OpenAI · web, desktop, workspace agents
admin-published custom MCP app, tool snapshot, per-action togglesfirst-party apps for Drive, Outlook, Teams and the rest stay inside OpenAI~none in the cloud beyond OpenAI's own auto-review; desktop hooks can deny or rewritecloud browser and computer use are not interceptablemanaged configuration, roles, lockdown mode
Microsoft Copilot Studio, Agent 365, Copilot Cowork
Microsoft 365 and Power Platform
Ripcord as an MCP server, or bring-your-own through the Agent 365 tooling gatewayPower Platform connectors and Graph actions never traverse MCPapproval is Microsoft's own UI; no third-party pre-action hookcomputer-use tool with human supervision, not interceptableDLP can block every other MCP server at server level
Google Gemini Enterprise and Agent Platform
Google Cloud
custom MCP server after an org-policy change, or registry plus Agent Gatewayfirst-party connector actions bypass the gateway, by Google's own statementAgent Gateway service extensions can inspect, modify or block gateway traffic before deliverycomputer use runs in the developer's harnessorg policies, IAM on agent identity
What this map does not claim. We cannot hold a first-party connector call inside Anthropic, OpenAI or Microsoft before it executes; we cannot see a click in a cloud browser; we cannot see what a shell command does after its text was approved. Where a vendor's own approval or hook exists, we integrate with it rather than pretend to replace it. Where nothing exists, the answer is the credential chokepoint: an agent that never holds a key cannot use a path we do not see, and the launch wizard builds agents whose only way to act is through the gateway.

Inside a hosted sandbox

Several agents now run in a virtual machine the vendor hosts, with a browser inside: ChatGPT's agent mode, Cowork's cloud mode. Nothing anyone installs sees a click in there, and we say so. What we control is the edge of the sandbox, where the agent needs authority to act on your systems.

Two things this does not cover, said plainly: an agent reading and exfiltrating through a human's session, which is identity and data-loss-prevention territory, and an employee who logs an agent in with their own password, which agent identity standards exist to make visible.

Where the agent security vendors sit

AIR, Noma, Zenity, Astrix and Operant vet what an agent is allowed to load: skills, plug-ins and MCP servers, discovered across the company and re-checked as they change. That is the supply chain, and it is worth having. Ripcord gates what the agent does with what it loaded: an approved, vetted MCP server still needs someone to say yes to the $48,200 wire, a rollback window when it was wrong, and a ledger the auditor accepts. Security stops the attacker; Ripcord stops the loss, whether the agent was poisoned, prompted or simply wrong. The two layers stack, and a vendor's vetting verdict is a signal in our scorecard, the way a new beneficiary is.

Hooks for Claude Code and Cursor, so shell and file actions get the same verdict as tool calls; both expose a pre-tool hook that can ask. Agent identity: the Enterprise-Managed Authorization extension of MCP, Okta's cross-app access and Microsoft's Entra Agent ID put the identity provider in charge of which agent may reach which server; Ripcord plugs in as the per-call decision those systems do not make. Destination-side gating: Ripcord as the approver behind Stripe Issuing authorization requests and the card networks' agent mandates, so the verdict applies wherever the money moves, whatever sandbox the agent sits in. The standard itself: an MCP working group is drafting "interceptors," a protocol-level hook for exactly this layer. We are following it and will implement the day it lands.

Sources

Governance and spec: modelcontextprotocol.io/community/governance · Linux Foundation, Agentic AI Foundation · spec 2026-07-28 changelog · interceptors working group · enterprise-managed authorization
Coding agents: Claude Code hooks · Claude Code managed settings · Cursor hooks · Cursor MCP · Codex hooks · Codex managed configuration · Gemini CLI hooks · Gemini CLI policy engine
Sandboxes, identity and money: ChatGPT agent · Cowork on Team and Enterprise · Okta Agent SSO · Stripe Issuing real-time authorizations · Agentic Commerce Protocol · Visa Intelligent Commerce Connect
Enterprise and desktop: Claude inference hooks · Cowork release notes · ChatGPT custom MCP apps · ChatGPT agent approvals · Copilot Studio MCP · Entra Agent ID · Google Agent Gateway · Okta cross-app access

Every cell was checked on 4 September 2026. Vendors move quickly; if a row is out of date, tell us and we will re-verify it. Our own protocol position and the score derivation live on the score page; the audit mapping on the compliance page.