当用户想配置 Claude Code、Cursor、Claude Desktop 项目规则或系统提示词时调用。
AI agents call get_workflow_prompt 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.
This tool retrieves workflow prompts and system prompt configurations for development tools (Claude Code, Cursor, Claude Desktop). It reads and returns existing configuration data without modifying, deleting, or executing external operations. The capability is informational only, fitting the Read category (retrieve/query with no side effects).
From the tool's definition Tool name 'get_workflow_prompt' and description indicating it retrieves or fetches workflow prompts/configurations for IDE tools. The verb 'get' and the context of 'retrieve' system prompts/project rules suggests data retrieval without modification.
Attacks that exploit this kind of access
当用户想配置 Claude Code、Cursor、Claude Desktop 项目规则或系统提示词时调用。. 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 get_workflow_prompt: 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.
get_workflow_prompt 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 get_workflow_prompt 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 get_workflow_prompt. 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.
get_workflow_prompt 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 →