Read the content of a conflicted file by its ID. (Rate limit: 5 calls per minute). You must use list_conflicts to get the ID first.
AI agents call read_conflict to retrieve information from Git Conflict MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays the content of a conflicted file to facilitate conflict resolution workflows. It performs no modifications, deletions, or external actions. The most severe capability is reading existing data within the repository, which falls squarely within the Read category.
From the tool's definition Tool name and description explicitly state 'Read the content of a conflicted file' - this is purely a retrieval operation with no side effects. The rate limit and requirement to use list_conflicts first further confirm it is a read-only query operation.
Attacks that exploit this kind of access
Read the content of a conflicted file by its ID. (Rate limit: 5 calls per minute). You must use list_conflicts to get the ID first. It is categorised as a Read tool in the Git Conflict MCP MCP Server, which means it retrieves data without modifying state.
Register the Git Conflict MCP server in PolicyLayer and add a rule for read_conflict: 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.
read_conflict is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_conflict 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.
Set action: deny in the PolicyLayer policy for read_conflict. 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.
read_conflict 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →