Skip to main content
Glama
ttpears

GitLab MCP Server

by ttpears

Create Broadcast Message

create_broadcast_message

Create GitLab broadcast messages as banners or notifications for announcements, with scheduling and targeting options. Requires admin privileges.

Instructions

Create a GitLab broadcast message. Requires administrator privileges on the GitLab instance.

Input Schema

NameRequiredDescriptionDefault
fontNoForeground (font) color in hex format
colorNoBackground color in hex format, e.g. "#E75E40"
themeNoTheme name (GitLab 16.9+), e.g. "indigo", "red"
ends_atNoISO 8601 timestamp when the message ends
messageYesMessage text to display
starts_atNoISO 8601 timestamp when the message starts
dismissableNoWhether users can dismiss the broadcast message
target_pathNoPath glob for pages where the message should appear
broadcast_typeNoBroadcast type: "banner" or "notification"
userCredentialsNoYour GitLab credentials (optional — falls back to the configured env token if not provided)
target_access_levelsNoAccess levels to target: 10=Guest, 20=Reporter, 30=Developer, 40=Maintainer, 50=Owner

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv4.0.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / ends_at / pattern
      Added value: +"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
    • addedInput schema / properties / starts_at / pattern
      Added value: +"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
    • addedInput schema / properties / target_access_levels / items / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / target_access_levels / items / minimum
      Added value: +-9007199254740991
    • changedInput schema / properties / userCredentials / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "accessToken": {
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "gitlabUrl": {
      -        "format": "uri",
      -        "type": "string"
      -      }
      -    },
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "properties": {
      +      "accessToken": {
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "gitlabUrl": {
      +        "format": "uri",
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. Addedv1.15.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare this is a non-readonly, non-idempotent, non-destructive write, so the mutation profile is covered structurally. The description adds the meaningful extra context that administrator privileges are required, but says nothing about what is returned on success (e.g., an ID needed for later update/delete) or any failure modes.

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

Conciseness5/5

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

Two short sentences with zero filler; the action is front-loaded and the prerequisite follows immediately. Nothing in the description is redundant or padded.

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 an 11-parameter creation tool with no output schema, the description is thin: it does not mention the scheduling window, page targeting, or credential fallback behavior, all of which materially shape a correct call. It is adequate because the schema is fully documented, but it leaves the agent to infer how the optional parameters interact.

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?

Schema description coverage is 100%, including enum values for broadcast_type and access-level meanings, so the schema carries parameter semantics fully. The description adds no parameter-level information beyond what is already documented, which is the expected baseline when coverage is complete.

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

Purpose4/5

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

States a specific verb and resource ("Create a GitLab broadcast message"), which cleanly separates it from siblings like update_broadcast_message, delete_broadcast_message, and list_broadcast_messages. It does not explicitly name those alternatives, but the create/broadcast pairing is 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 admin-privilege prerequisite is stated, which is genuinely useful before an agent attempts the call. However, there is no guidance on when to create vs. update an existing message, or on how scheduling (starts_at/ends_at) affects whether a new message is the right choice.

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