Gitlab

Gitlab List Mrs

gitlab_list_mrs

Read-onlyIdempotent

List merge requests in a GitLab project by project ID. Returns MR ID, title, state, author, source/target branches, and URL. Filter by state and author.

Input Schema

TableJSON Schema

Name	Required	Description
`state`	No	Filter by state: "opened", "closed", "merged", or "all" (default: "opened")
`_apiKey`	Yes	GitLab personal access token
`per_page`	No	Number of merge requests to return (default 20, max 100)
`project_id`	Yes	Project ID (numeric) or full path "namespace/project" (e.g. "gitlab-org/gitlab") — pass the plain path, do not URL-encode it.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`merge_requests`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 18, 2026

changedInput schema / properties / project_id / description

Previous value: -"Project ID or URL-encoded path"New value: +"Project ID (numeric) or full path \"namespace/project\" (e.g. \"gitlab-org/gitlab\") — pass the plain path, do not URL-encode it."

Changed1 schema field changedMay 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "merge_requests": {
+      "items": {
+        "properties": {
+          "author": {
+            "description": "Author username",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "created_at": {
+            "description": "Creation timestamp",
+            "type": "string"
+          },
+          "iid": {
+            "description": "Merge request internal ID",
+            "type": "number"
+          },
+          "merge_status": {
+            "description": "Merge status",
+            "type": "string"
+          },
+          "source_branch": {
+            "description": "Source branch name",
+            "type": "string"
+          },
+          "state": {
+            "description": "Merge request state (opened/closed/merged)",
+            "type": "string"
+          },
+          "target_branch": {
+            "description": "Target branch name",
+            "type": "string"
+          },
+          "title": {
+            "description": "Merge request title",
+            "type": "string"
+          },
+          "updated_at": {
+            "description": "Last update timestamp",
+            "type": "string"
+          },
+          "url": {
+            "description": "Merge request web URL",
+            "type": "string"
+          }
+        },
+        "required": [
+          "iid",
+          "title",
+          "state",
+          "author",
+          "source_branch",
+          "target_branch",
+          "merge_status",
+          "url",
+          "created_at",
+          "updated_at"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "merge_requests"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "_apiKey": "your-gitlab-api-key",
+    "project_id": "123"
+  },
+  {
+    "_apiKey": "your-gitlab-api-key",
+    "per_page": 50,
+    "project_id": "123",
+    "state": "merged"
+  }
+]

First observedApr 22, 2026

TDQS

B3.2/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the read-only nature is covered. However, the description adds no further behavioral context such as authentication requirements, rate limits, pagination behavior, or what happens on missing parameters. It merely lists return fields, which is likely redundant given the output schema. The added value beyond annotations is minimal.

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

Conciseness3/5

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

The description is concise (two sentences) and front-loads the core action, but it contains a distracting inaccuracy ('Filter by state and author') that sticks out and could mislead. It is not overly verbose, but the incorrect filter reference reduces its effectiveness.

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

Completeness3/5

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

For a read-only list tool with a complete schema (100% coverage), an output schema, and good annotations, the description is mostly adequate. It clearly states what the tool does and what it returns. However, the false 'author' filter is a notable gap that could lead to misuse. Additionally, it does not mention pagination limits, though per_page is in the schema. Overall, it is functional but not fully complete.

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

Parameters2/5

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

Schema coverage is 100%, so the schema already documents all parameters. The description claims 'Filter by state and author,' but there is no 'author' parameter in the schema. This is misleading and could cause an agent to attempt a filter that does not exist. The description does not clarify any parameter semantics beyond what the schema provides, and it introduces an inconsistency.

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 (list), resource (merge requests in a GitLab project), and method (by project ID). It also enumerates the returned fields (MR ID, title, state, author, source/target branches, URL), which distinguishes it from sibling tools like gitlab_list_issues and gitlab_get_project. The purpose is specific and unambiguous.

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

Usage Guidelines3/5

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

The description implies usage for listing merge requests in a project but does not explicitly state when to use this tool versus alternatives (e.g., gitlab_list_issues for issues) or mention any exclusions. While the tool name and context make the intended use clear, there is no explicit guidance or contrast with siblings, leaving the agent to infer.

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

All Gitlab tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.