Skip to main content
Glama
zereight

gitlab mcp

by zereight
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

list_group_merge_requests

Read-only

List merge requests across all projects in a GitLab group and its subgroups. Filter by state, author, labels, search, or pagination to review group-wide merge activity.

Instructions

List merge requests across all projects of a group and its subgroups. Use this for a collection of resources; choose the corresponding get tool when you already know the single resource to inspect. It is read-only and does not mutate GitLab data; missing resources, invalid identifiers, insufficient permission, and rate limits are returned as errors. When project_id or group_id is accepted, provide the numeric ID or complete URL-encoded path described by the schema; use required identifiers and pagination fields exactly as documented.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
wipNoFilter merge requests against their wip status
pageNoPage number for pagination (default: 1)
sortNoReturn merge requests sorted in ascending or descending order
scopeNoReturn merge requests from a specific scope
stateNoReturn merge requests with a specific state
labelsNoArray of label names
searchNoSearch for specific terms
group_idYesGroup ID or URL-encoded path
jmespathNoOptional JMESPath expression filtering the JSON result before return.
order_byNoReturn merge requests ordered by the given field
per_pageNoNumber of items per page (max: 100, default: 20)
author_idNoReturns merge requests created by the given user ID (integer). Mutually exclusive with author_username.
milestoneNoMilestone title
assignee_idNoReturn MRs assigned to the given user ID (integer), 'none', or 'any'. Mutually exclusive with assignee_username.
reviewer_idNoReturns merge requests which have the user as a reviewer. Must be an integer, 'none', or 'any'. Mutually exclusive with reviewer_username.
non_archivedNoReturn merge requests from non-archived projects only. Defaults to true.
created_afterNoReturn merge requests created after the given time
source_branchNoReturn merge requests from a specific source branch
target_branchNoReturn merge requests targeting a specific branch
updated_afterNoReturn merge requests updated after the given time
created_beforeNoReturn merge requests created before the given time
updated_beforeNoReturn merge requests updated before the given time
author_usernameNoReturns merge requests created by the given username. Mutually exclusive with author_id.
assignee_usernameNoReturns merge requests assigned to the given username. Mutually exclusive with assignee_id.
reviewer_usernameNoReturns merge requests which have the user as a reviewer by username. Mutually exclusive with reviewer_id.
source_project_idNoReturn merge requests with the given source project ID
with_labels_detailsNoReturn more details for each label
approved_by_usernamesNoReturns merge requests approved by the given usernames (array).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.66
    • addedInput schema / properties / jmespath
      Added value: +{
+  "description": "Optional JMESPath expression filtering the JSON result before return.",
+  "type": "string"
+}
  2. Addedv2.1.57

TDQS

A4.1/5.0
Behavior4/5

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

It confirms read-only behavior, which matches the readOnlyHint annotation, and adds useful error behavior: missing resources, invalid identifiers, insufficient permission, and rate limits are returned as errors. This goes beyond the annotations by telling the agent what failure modes to expect, without contradicting any annotation.

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 compact and front-loaded with the primary purpose. The third sentence is somewhat long and includes a mildly redundant instruction to use fields exactly as documented, but it still earns its place by disclosing error behavior and ID format requirements.

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

Completeness4/5

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

Given the tool's 28 parameters and no output schema, the description reasonably covers the essential call context: scope, when to use it, read-only safety, error conditions, and identifier format. The schema handles the exhaustive parameter details, so nothing critical is missing for correct invocation.

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 has 100% description coverage, so the description does not need to repeat parameter details. The note about numeric IDs versus URL-encoded paths mirrors the schema's group_id description, and the instruction to use required identifiers and pagination fields is general rather than additive. Baseline 3 is appropriate.

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 identifies a specific verb, resource, and scope: 'List merge requests across all projects of a group and its subgroups.' It clearly distinguishes this group-scoped list operation from the single-resource get tool mentioned in the second sentence, and the name itself differentiates it from project-level or global list siblings.

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

Usage Guidelines4/5

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

The description gives explicit when-to-use guidance: use it for a collection of resources, and use the corresponding get tool when a single resource is already known. It does not explicitly compare against the sibling list_merge_requests tool, but the group/subgroup scope and the get-tool contrast provide clear context for selection.

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

Deploy Server

Other Tools