This record as markdown: /tools/io-github-zereight-gitlab-mcp/list-group-projects.md
What list_group_projects does on Gitlab Mcp
AI agents call list_group_projects to retrieve information from Gitlab Mcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_group_projects is rated Low
This tool retrieves a list of projects belonging to a GitLab group. It performs no side effects, does not modify data, and does not execute code or operations. The verb 'list' is a canonical Read operation. The blast radius of misuse is limited to information disclosure of project names and metadata already accessible to users with group visibility.
From the tool's definition Tool name 'list_group_projects' and description 'List projects in a group' indicate a read-only operation that retrieves/queries existing project data without modification.
Attacks that exploit this kind of access
The rule that runs list_group_projects safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gitlab Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_group_projects, this is the rule to start with:
list_group_projects is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gitlab Mcp, apply this rule, and every list_group_projects call is checked against it from then on.
Questions about list_group_projects
List projects in a group. It is categorised as a Read tool in the Gitlab Mcp MCP Server, which means it retrieves data without modifying state.
Register the Gitlab MCP server in PolicyLayer and add a rule for list_group_projects: 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 Gitlab Mcp. Nothing to install.
list_group_projects 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 list_group_projects 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 list_group_projects. 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.
list_group_projects is provided by the Gitlab MCP server (@zereight/mcp-gitlab). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gitlab, and thousands of servers like it.
This server
Across the catalogue