post_resolve · Git Conflict MCP: Risk & Policy

WHAT IT DOES

What post_resolve does on Git Conflict MCP

AI agents use post_resolve to create or update resources in Git Conflict MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git Conflict MCP environment.

WHY IT NEEDS A POLICY

Why post_resolve needs a policy

The tool appears to be a pre-confirmation/acknowledgment step before the actual resolve_conflict action is taken. It doesn't itself modify files or execute the resolution, but rather records or confirms intent to proceed. This is most consistent with a Write action (recording a confirmation state), though the description is vague, lowering confidence.

From the tool's definition 'Execute this tool BEFORE running resolve_conflict to confirm the resolution process. This acts as a safety confirmation step.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

post_resolve Rate-limited

post_resolve stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "post_resolve": {
      "limits": [
        {
          "counter": "post_resolve_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Git Conflict MCP, so you can run agents against it safely.

FAQ

Questions about post_resolve

What does the post_resolve tool do? +

Execute this tool BEFORE running resolve_conflict to confirm the resolution process. This acts as a safety confirmation step. It is categorised as a Write tool in the Git Conflict MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on post_resolve? +

Register the Git Conflict MCP server in PolicyLayer and add a rule for post_resolve: 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 Git Conflict MCP. Nothing to install.

What risk level is post_resolve? +

post_resolve is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit post_resolve? +

Yes. Add a rate_limit block to the post_resolve 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 post_resolve completely? +

Set action: deny in the PolicyLayer policy for post_resolve. 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 post_resolve? +

post_resolve is provided by the Git Conflict MCP server (mattyatea/git-conflict-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.