Skip to main content
Glama
Sign In
GitLab MCP Server

GitLab MCP Server

by ttpears
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

My Todos

list_my_todos
Read-onlyIdempotent

Retrieve and filter your authenticated GitLab to-do items by state, action, target type, or project/group to review pending notifications.

Instructions

List the authenticated user's GitLab to-do items (notifications about issues, MRs, mentions, reviews requested, etc.). Filter by state, action, target type, or group/project. Requires user authentication.

Input Schema

NameRequiredDescriptionDefault
sortNoSort order — e.g. CREATED_DESC (default on server), CREATED_ASC, UPDATED_DESC, UPDATED_ASC.
typeNoFilter by target type — e.g. Issue, MergeRequest, Epic, Commit, DesignManagement::Design, AlertManagement::Alert
afterNoPagination cursor. To fetch the next page, pass the previous response pageInfo.endCursor here and repeat until pageInfo.hasNextPage is false. Paginating this way is the reliable path to complete results and accurate totals.
firstNoNumber of todos to retrieve
stateNoFilter by todo state: pending (default), done, or allpending
actionNoFilter by todo action — e.g. assigned, mentioned, build_failed, marked, approval_required, unmergeable, directly_addressed, review_requested
fetchAllNoFetch multiple pages in one call, up to "first" items total (max 100) — NOT exhaustive. For complete results or accurate counts, leave this false and paginate via after (pageInfo.endCursor).
authorIdsNoFilter by todo authors. Accepts numeric user IDs or full gid://gitlab/User/N strings.
groupPathNoLimit to a group by full path (e.g. "my-org/platform"). Resolved to a node GID server-side before filtering.
isSnoozedNoFilter by snooze state: true → only snoozed, false → only non-snoozed.
projectPathNoLimit to a project by full path (e.g. "my-org/my-repo"). Resolved to a node GID server-side before filtering.
userCredentialsNoYour GitLab credentials (optional — falls back to the configured env token if not provided)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv4.0.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • 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. Changed2 schema fields changedv2.2.4
    • changedInput schema / properties / after / description
      Previous value: -"Cursor for pagination"New value: +"Pagination cursor. To fetch the next page, pass the previous response pageInfo.endCursor here and repeat until pageInfo.hasNextPage is false. Paginating this way is the reliable path to complete results and accurate totals."
    • changedInput schema / properties / fetchAll / description
      Previous value: -"Fetch all pages up to 100 results"New value: +"Fetch multiple pages in one call, up to \"first\" items total (max 100) — NOT exhaustive. For complete results or accurate counts, leave this false and paginate via after (pageInfo.endCursor)."
  3. Addedv1.19.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral detail — the authentication requirement — but does not mention pagination behavior or result shape beyond what the schema already exposes via the after/fetchAll params.

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?

Three compact, front-loaded sentences that define the resource, enumerate filters, and flag the auth prerequisite. Slight looseness from 'etc.' but no wasted sentences.

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?

For a 12-param read-only list tool with no output schema but full schema coverage and safety annotations, the description covers purpose, filter scope, and auth. It omits pagination/return expectations, but the schema's after/fetchAll descriptions handle that, so it is largely complete.

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%, so the schema already documents all 12 parameters thoroughly. The description only names the filter categories (state, action, target type, group/project), which largely restates schema content without adding format or interaction guidance, so baseline 3 applies.

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 (List) and resource (authenticated user's GitLab to-do items), and clarifies what a to-do is with concrete examples (issues, MRs, mentions, reviews requested). Clear enough to distinguish from read tools like get_issues, but it does not explicitly name the mutation siblings (mark_todo_done, restore_todo) that share the resource.

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 filter dimensions imply when to reach for this tool, and 'Requires user authentication' flags a precondition. However, there is no explicit when-not guidance or routing to alternatives (e.g., use mark_todo_done to modify, list_my_events for activity rather than to-dos), leaving selection to inference.

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