GitLab MCP Server

create_issue

Create new issues in GitLab projects to track bugs, tasks, or feature requests with titles, descriptions, assignees, labels, and milestones.

Instructions

Create a new issue in a GitLab project

Input Schema

TableJSON Schema

Name	Required	Description
`project_id`	Yes	Project ID or URL-encoded path
`title`	Yes	Issue title
`description`	No	Issue description
`assignee_ids`	No	Array of user IDs to assign
`labels`	No	Array of label names
`milestone_id`	No	Milestone ID to assign

Implementation Reference

src/api/issues.ts:79-98 (handler)

The implementation of the 'createIssue' function, which handles sending the POST request to the GitLab API to create an issue.

export async function createIssue(projectId: string, options: CreateIssueOptions): Promise<GitLabIssue> {
  if (!projectId?.trim()) {
    throw new Error("Project ID is required");
  }
  if (!options?.title?.trim()) {
    throw new Error("Issue title is required");
  }

  const endpoint = `/projects/${encodeProjectId(projectId)}/issues`;

  const issue = await gitlabPost<GitLabIssue>(endpoint, {
    title: options.title,
    description: options.description,
    assignee_ids: options.assignee_ids,
    milestone_id: options.milestone_id,
    labels: options.labels?.join(",")
  });

  return GitLabIssueSchema.parse(issue);
}

src/schemas.ts:263-271 (schema)

The schema definition for the 'create_issue' tool's input arguments.

export const CreateIssueSchema = ProjectParamsSchema.extend({
  title: z.string().describe("Issue title"),
  description: z.string().optional().describe("Issue description"),
  assignee_ids: z.array(z.number()).optional().describe("Array of user IDs to assign"),
  labels: z.array(z.string()).optional().describe("Array of label names"),
  milestone_id: z.number().optional().describe("Milestone ID to assign")
});

export const CreateMergeRequestSchema = ProjectParamsSchema.extend({

src/server.ts:89-97 (registration)

Tool registration for 'create_issue' in the server implementation.

{
  name: "create_issue",
  description: "Create a new issue in a GitLab project",
  inputSchema: zodToJsonSchema(CreateIssueSchema)
},
{
  name: "create_merge_request",
  description: "Create a new merge request in a GitLab project",
  inputSchema: zodToJsonSchema(CreateMergeRequestSchema)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.5.2Mar 22, 2026

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description bears full responsibility for disclosing behavioral traits. It only states the basic action, omitting side effects (e.g., audit trail, notifications), authorization needs, rate limits, or what occurs on success/failure. This is insufficient for an agent to use the tool safely.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with no fluff. It conveys the core purpose efficiently. However, it could be slightly expanded to include key usage hints without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 6 parameters (2 required) and no output schema, the description fails to provide enough context for complete understanding. It does not explain the relationship between parameters or common usage patterns, leaving the agent to infer from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers all 6 parameters with descriptions, achieving 100% schema coverage. The description adds no new meaning beyond the schema, so a baseline score of 3 is appropriate. No parameter information is missing from the structured data.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('create') and the resource ('a new issue in a GitLab project'). It effectively distinguishes from sibling tools like create_branch or create_merge_request, leaving no ambiguity about what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives (e.g., create_merge_request). It does not mention any prerequisites, such as required permissions or project existence, and offers no example scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.