add_security_stages

A write tool on the Gitlab MCP server.

SERVERGitlab SOURCEdkeeno/gitlab-mcp-server

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/dkeeno-gitlab-mcp-server/add-security-stages.md

WHAT IT DOES

What add_security_stages does on Gitlab

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

RISK

Why add_security_stages is rated Medium

The tool appears to add or modify security stages within GitLab CI/CD pipelines based on context from the server's stated capabilities and naming pattern of sibling tools. This is a Write action (creates/modifies pipeline configuration reversibly) rather than Destructive since pipeline stages can be removed or modified.

From the tool's definition Tool name 'add_security_stages' combined with server description indicating ability to manage 'security scans' and CI/CD pipeline configuration.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs add_security_stages safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Gitlab, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For add_security_stages, this is the rule to start with:

add_security_stages Rate-limited

add_security_stages 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": {
    "add_security_stages": {
      "limits": [
        {
          "counter": "add_security_stages_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Gitlab, apply this rule, and every add_security_stages call is checked against it from then on.

FAQ

Questions about add_security_stages

What does the add_security_stages tool do? +

add_security_stages is a write tool on the Gitlab MCP server. It is categorised as a Write tool in the Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_security_stages? +

Register the Gitlab MCP server in PolicyLayer and add a rule for add_security_stages: 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. Nothing to install.

What risk level is add_security_stages? +

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

Can I rate-limit add_security_stages? +

Yes. Add a rate_limit block to the add_security_stages 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 add_security_stages completely? +

Set action: deny in the PolicyLayer policy for add_security_stages. 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 add_security_stages? +

add_security_stages is provided by the Gitlab MCP server (dkeeno/gitlab-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Gitlab, and thousands of servers like it.

This server

All 56 Gitlab tools →

Across the catalogue

add-tag on Kanban MCP Server →kb_add on Persistent Kb → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →