Skip to main content
Glama
launchnotes

LaunchNotes MCP Server

Official
by launchnotes

List LaunchNotes Announcements

launchnotes_list_announcements
Read-onlyIdempotent

Retrieve announcements from a LaunchNotes project with options to filter by state, sort by date fields, and control output format.

Instructions

List all announcements in a LaunchNotes project with optional filtering and ordering.

Args:

  • project_id (string): The ID of the project

  • state ('draft' | 'scheduled' | 'published' | 'archived', optional): Filter by state

  • limit (number, optional): Number to return (max 100, default: 50)

  • order_by_field ('publishedAt' | 'createdAt' | 'updatedAt', optional): Field to sort by

  • order_by_direction ('ASC' | 'DESC', optional): Sort direction (ascending or descending)

  • response_format ('json' | 'markdown'): Output format (default: 'markdown')

Returns: List of announcements with id, headline, state, dates, and slug

Use Cases:

  • "List all announcements in my LaunchNotes project"

  • "Show me all published announcements ordered by published date"

  • "List draft announcements"

  • "Show scheduled announcements sorted by creation date descending"

Note: To use ordering, both order_by_field and order_by_direction must be specified. Default ordering (when not specified) is by updatedAt descending.

Error Handling:

  • Returns "Project not found" if project ID doesn't exist

  • Returns "Authentication failed" if API token is invalid

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_idYesThe ID of the LaunchNotes project
stateNoFilter by announcement state
limitNoNumber of announcements to return (max 100)
order_by_fieldNoField to sort by
order_by_directionNoSort direction: 'ASC' for ascending, 'DESC' for descending
response_formatNoOutput format: 'json' for structured data, 'markdown' for human-readablemarkdown

Implementation Reference

  • Inline handler function that executes the launchnotes_list_announcements tool logic: fetches announcements using GraphQL, supports JSON or Markdown output formats, and handles errors.
    async (params: ListAnnouncementsInput) => {
      try {
        const result = await listAnnouncements(client, params.project_id, {
          state: params.state,
          first: params.limit,
          orderByField: params.order_by_field,
          orderByDirection: params.order_by_direction,
        });
    
        const announcements = result.project.announcements.nodes;
    
        if (params.response_format === RESPONSE_FORMAT.JSON) {
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(
                  {
                    total: announcements.length,
                    announcements,
                    hasMore: result.project.announcements.pageInfo.hasNextPage,
                  },
                  null,
                  2
                ),
              },
            ],
          };
        }
    
        // Markdown format
        return {
          content: [
            {
              type: "text",
              text: formatAnnouncementListMarkdown(announcements),
            },
          ],
        };
      } catch (error) {
        return {
          isError: true,
          content: [
            {
              type: "text",
              text: `Error listing announcements: ${error instanceof Error ? error.message : "Unknown error"}`,
            },
          ],
        };
      }
    }
  • Zod schema defining the input parameters for launchnotes_list_announcements: project_id (required), state, limit, ordering fields, and response_format.
    export const ListAnnouncementsSchema = z
      .object({
        project_id: z
          .string()
          .min(1, "Project ID is required")
          .describe("The ID of the LaunchNotes project"),
        state: announcementStateSchema,
        limit: z
          .number()
          .min(1)
          .max(100)
          .default(50)
          .optional()
          .describe("Number of announcements to return (max 100)"),
        order_by_field: orderByFieldSchema,
        order_by_direction: sortDirectionSchema,
        response_format: responseFormatSchema,
      })
      .strict();
  • MCP tool registration for launchnotes_list_announcements, including title, detailed description, input schema reference, annotations, and inline handler.
      server.registerTool(
        "launchnotes_list_announcements",
        {
          title: "List LaunchNotes Announcements",
          description: `List all announcements in a LaunchNotes project with optional filtering and ordering.
    
    Args:
      - project_id (string): The ID of the project
      - state ('draft' | 'scheduled' | 'published' | 'archived', optional): Filter by state
      - limit (number, optional): Number to return (max 100, default: 50)
      - order_by_field ('publishedAt' | 'createdAt' | 'updatedAt', optional): Field to sort by
      - order_by_direction ('ASC' | 'DESC', optional): Sort direction (ascending or descending)
      - response_format ('json' | 'markdown'): Output format (default: 'markdown')
    
    Returns:
      List of announcements with id, headline, state, dates, and slug
    
    Use Cases:
      - "List all announcements in my LaunchNotes project"
      - "Show me all published announcements ordered by published date"
      - "List draft announcements"
      - "Show scheduled announcements sorted by creation date descending"
    
    Note: To use ordering, both order_by_field and order_by_direction must be specified.
    Default ordering (when not specified) is by updatedAt descending.
    
    Error Handling:
      - Returns "Project not found" if project ID doesn't exist
      - Returns "Authentication failed" if API token is invalid`,
          inputSchema: ListAnnouncementsSchema,
          annotations: {
            readOnlyHint: true,
            destructiveHint: false,
            idempotentHint: true,
            openWorldHint: true,
          },
        },
        async (params: ListAnnouncementsInput) => {
          try {
            const result = await listAnnouncements(client, params.project_id, {
              state: params.state,
              first: params.limit,
              orderByField: params.order_by_field,
              orderByDirection: params.order_by_direction,
            });
    
            const announcements = result.project.announcements.nodes;
    
            if (params.response_format === RESPONSE_FORMAT.JSON) {
              return {
                content: [
                  {
                    type: "text",
                    text: JSON.stringify(
                      {
                        total: announcements.length,
                        announcements,
                        hasMore: result.project.announcements.pageInfo.hasNextPage,
                      },
                      null,
                      2
                    ),
                  },
                ],
              };
            }
    
            // Markdown format
            return {
              content: [
                {
                  type: "text",
                  text: formatAnnouncementListMarkdown(announcements),
                },
              ],
            };
          } catch (error) {
            return {
              isError: true,
              content: [
                {
                  type: "text",
                  text: `Error listing announcements: ${error instanceof Error ? error.message : "Unknown error"}`,
                },
              ],
            };
          }
        }
      );
  • Core helper function that constructs and executes the GraphQL query to list announcements from the LaunchNotes API, applying filters and ordering.
    export async function listAnnouncements(
      client: GraphQLClient,
      projectId: string,
      filters?: {
        state?: string;
        first?: number;
        after?: string;
        orderByField?: string;
        orderByDirection?: string;
      }
    ): Promise<{
      project: {
        announcements: {
          nodes: LaunchNotesAnnouncementList[];
          pageInfo: {
            hasNextPage: boolean;
            endCursor?: string;
          };
        };
      };
    }> {
      const variables: Record<string, unknown> = {
        projectId,
        first: filters?.first || 50,
        after: filters?.after,
      };
    
      // Add state filter if provided
      if (filters?.state) {
        variables.state = filters.state;
      }
    
      // Add orderBy if field and direction are provided
      if (filters?.orderByField && filters?.orderByDirection) {
        variables.orderBy = {
          field: filters.orderByField,
          sort: filters.orderByDirection,
        };
      }
    
      return client.execute(LIST_ANNOUNCEMENTS_QUERY, variables);
    }
  • Helper utility to format the fetched announcements list into a human-readable Markdown table/list for the tool's markdown response format.
    export function formatAnnouncementListMarkdown(
      announcements: LaunchNotesAnnouncementList[]
    ): string {
      if (announcements.length === 0) {
        return "No announcements found.";
      }
    
      const lines = [`# Announcements (${announcements.length})`, ""];
    
      announcements.forEach((ann) => {
        lines.push(`## ${ann.headline}`);
        lines.push(`- **ID:** ${ann.id}`);
        lines.push(`- **State:** ${ann.state}`);
        lines.push(`- **Slug:** ${ann.slug}`);
        if (ann.publishedAt) {
          lines.push(
            `- **Published:** ${new Date(ann.publishedAt).toLocaleString()}`
          );
        }
        if (ann.scheduledAt) {
          lines.push(
            `- **Scheduled:** ${new Date(ann.scheduledAt).toLocaleString()}`
          );
        }
        lines.push(`- **Created:** ${new Date(ann.createdAt).toLocaleString()}`);
        lines.push("");
      });
    
      return lines.join("\n");
    }
Behavior4/5

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

The description adds valuable behavioral context beyond annotations: it specifies ordering requirements ('both order_by_field and order_by_direction must be specified'), default ordering ('updatedAt descending'), and error handling ('Project not found', 'Authentication failed'). Annotations already cover safety (readOnlyHint=true, destructiveHint=false), but the description provides operational details that help the agent use the tool correctly.

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 well-structured with clear sections (Args, Returns, Use Cases, Note, Error Handling) and front-loads the core purpose. However, the 'Args' section is somewhat redundant given the comprehensive schema, and the description could be more concise by focusing only on value-added information beyond the structured fields.

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

Completeness5/5

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

For a read-only listing tool with excellent annotations (readOnlyHint, openWorldHint, idempotentHint) and 100% schema coverage, the description provides complete contextual information. It covers purpose, usage examples, behavioral constraints, error handling, and output format details, making it fully sufficient for agent understanding without an output schema.

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?

With 100% schema description coverage, the input schema already documents all parameters thoroughly. The description's 'Args' section essentially repeats what's in the schema (though it adds the 'max 100' constraint for limit, which is also in the schema). It provides minimal additional semantic value beyond the well-documented schema.

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 verb ('List') and resource ('announcements in a LaunchNotes project') with specific scope ('all announcements'). It distinguishes from siblings like 'launchnotes_get_announcement' (singular) and 'launchnotes_get_top_announcements' (curated subset) by emphasizing comprehensive listing with filtering capabilities.

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 'Use Cases' section provides clear examples of when to use this tool ('List all announcements', 'Show me all published announcements', etc.), giving practical context. However, it doesn't explicitly state when NOT to use it or mention specific alternatives among the sibling tools, though the examples imply filtering scenarios.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/launchnotes/mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server