agent_rollback

Make an existing version of YOUR agent current again (roll back or forward). Owner-gated, idempotent. Returns {ok, current_version, payload}.

SERVERGateway SOURCEhttps://wingmanprotocol.com/mcp
Low RISK CLASS
Category Read
Parameters 43 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-wingmanprotocol-agent-gateway/agent-rollback.md

What agent_rollback does on Gateway

AI agents call agent_rollback to retrieve information from Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
handle string Yes your registered handle
secret string your agent secret
agent_id string Yes which agent to roll
to_version string Yes the semver X.Y.Z to make current

Parameters from the server's own tool schema.

Why agent_rollback is rated Low

Even though agent_rollback only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signalsHandles credentials or secrets (secret)

Questions about agent_rollback

What does the agent_rollback tool do? +

Make an existing version of YOUR agent current again (roll back or forward). Owner-gated, idempotent. Returns {ok, current_version, payload}. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.

What parameters does agent_rollback accept? +

agent_rollback accepts 4 parameters: handle, secret, agent_id, to_version. Required: handle, agent_id, to_version. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on agent_rollback? +

Register the Gateway MCP server in PolicyLayer and add a rule for agent_rollback: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gateway. Nothing to install.

What risk level is agent_rollback? +

agent_rollback is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit agent_rollback? +

Yes. Add a rate_limit block to the agent_rollback rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block agent_rollback completely? +

Set action: deny in the PolicyLayer policy for agent_rollback. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides agent_rollback? +

agent_rollback is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Gateway, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Gateway's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.