glab_projects · RedisNexus MCP: Risk & Policy

WHAT IT DOES

What glab_projects does on RedisNexus

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

WHY IT NEEDS A POLICY

Why glab_projects needs a policy

The tool spans multiple risk levels: 'list' and 'view' are Read operations, but 'create' and 'fork' are Write operations that create new resources. Per the classification rules, Write takes precedence over Read. The blast radius is medium because creating or forking projects affects repository structure and access, but these actions are reversible (projects can be deleted).

From the tool's definition Tool performs actions including 'create' and 'fork', which are reversible data modifications. Description explicitly states 'Manage GitLab projects: list, view, create, fork.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

glab_projects Rate-limited

glab_projects 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": {
    "glab_projects": {
      "limits": [
        {
          "counter": "glab_projects_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 RedisNexus, so you can run agents against it safely.

FAQ

Questions about glab_projects

What does the glab_projects tool do? +

Manage GitLab projects: list, view, create, fork. It is categorised as a Write tool in the RedisNexus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on glab_projects? +

Register the RedisNexus MCP server in PolicyLayer and add a rule for glab_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 RedisNexus. Nothing to install.

What risk level is glab_projects? +

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

Can I rate-limit glab_projects? +

Yes. Add a rate_limit block to the glab_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.

How do I block glab_projects completely? +

Set action: deny in the PolicyLayer policy for glab_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.

What MCP server provides glab_projects? +

glab_projects is provided by the RedisNexus MCP server (rajkumar-madhu/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.