当用户需要归档、交接或查看某个分支的 Markdown 记录时调用。
AI agents call export_branch_markdown to retrieve information from GitBranchMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool exports/reads existing branch data into Markdown format for viewing or archiving purposes. It retrieves and formats data without modifying or deleting anything. Similar sibling tools (export_demo_markdown, export_main_markdown) confirm this is a read/export pattern. Severity is low as misuse only exposes branch notes.
From the tool's definition export_branch_markdown — 'export' combined with 'Markdown' and the description referencing archiving/handoff/viewing a branch's Markdown record
Attacks that exploit this kind of access
当用户需要归档、交接或查看某个分支的 Markdown 记录时调用。. It is categorised as a Read tool in the GitBranchMCP MCP Server, which means it retrieves data without modifying state.
Register the GitBranch MCP server in PolicyLayer and add a rule for export_branch_markdown: 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 GitBranchMCP. Nothing to install.
export_branch_markdown 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 export_branch_markdown 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 export_branch_markdown. 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.
export_branch_markdown is provided by the GitBranch MCP server (lianggaoyuan/gitbranchmcp). 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 →