Skip to main content
Glama

get_programs

Read-onlyIdempotent

Fetch a paginated list of programs from Eduframe. Specify results per page and cursor to navigate through large datasets efficiently.

Instructions

Get all programs

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cursorNoCursor for fetching the next page of results
per_pageNoNumber of results per page (default: 25)

Implementation Reference

  • Registration and handler for the 'get_programs' tool. The handler calls apiList('/program/programs', {cursor, per_page}) to fetch paginated programs, logs the response, and formats the result via formatList().
    export function registerProgramProgramTools(server: McpServer): void {
      server.registerTool(
        "get_programs",
        {
          description: "Get all programs",
          annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true },
          inputSchema: {
            cursor: z.string().optional().describe("Cursor for fetching the next page of results"),
            per_page: z.number().int().positive().optional().describe("Number of results per page (default: 25)"),
          },
        },
        async ({ cursor, per_page }) => {
          try {
            const result = await apiList<EduframeRecord>("/program/programs", { cursor, per_page });
            void logResponse("get_programs", { cursor, per_page }, result);
            const toolResult = formatList(result.records, "program programs");
            if (result.nextCursor) {
              toolResult.content.push({ type: "text", text: `\nNext page cursor: ${result.nextCursor}` });
            }
            return toolResult;
          } catch (error) {
            return formatError(error);
          }
        },
      );
  • Input schema for get_programs: optional cursor (string) for pagination and per_page (positive int, default 25).
    inputSchema: {
      cursor: z.string().optional().describe("Cursor for fetching the next page of results"),
      per_page: z.number().int().positive().optional().describe("Number of results per page (default: 25)"),
    },
  • Central registration: registerProgramProgramTools is called from registerAllTools(), which iterates over all tool registrations and invokes them with the McpServer instance.
    export function registerAllTools(server: McpServer): void {
      for (const register of tools) {
        register(server);
      }
    }
  • The apiList() helper function performs a GET request to a paginated list endpoint, parses the Link header for cursor-based pagination, and returns records with nextCursor.
    export async function apiList<T>(path: string, query?: Record<string, QueryValue>): Promise<ListResult<T>> {
      const { token } = getConfig();
      const url = buildUrl(path, query);
    
      const response = await fetch(url.toString(), {
        method: "GET",
        headers: buildHeaders(token),
      });
    
      await checkResponse(response);
    
      const records = (await response.json()) as T[];
      const nextCursor = parseNextCursor(response.headers.get("Link"));
    
      return { records, nextCursor };
    }
  • The formatList() helper formats a list of records into a human-readable CallToolResult, displaying the count and JSON content.
    export function formatList(records: EduframeRecord[], resourceName: string): CallToolResult {
      if (records.length === 0) {
        return {
          content: [
            {
              type: "text",
              text: `No ${resourceName} found.`,
            },
          ],
        };
      }
    
      return {
        content: [
          {
            type: "text",
            text: `Found ${records.length} ${resourceName}:\n\n${formatJSON(records)}${RESPONSE_LOG_HINT}`,
          },
        ],
      };
    }
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the agent knows this is a safe read. The description adds no further behavioral context, but does not contradict annotations.

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 extremely concise (3 words), but could include more information about pagination or structure. It is front-loaded but minimal.

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

Completeness2/5

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

Given the simplicity (2 optional params, no output schema), the description is too sparse. It does not mention pagination or that it returns a list, leaving gaps for the agent.

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 coverage is 100% with both parameters (cursor, per_page) having descriptions. The description adds no additional meaning, meeting the baseline for high coverage.

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?

The description 'Get all programs' clearly states the action and resource. It distinguishes from the sibling 'get_program' (singular) by implying a list, but lacks explicit differentiation.

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

Usage Guidelines2/5

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

No guidance on when to use this tool vs alternatives like other list tools (e.g., get_courses). The description does not mention context or exclusions.

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/martijnpieters/eduframe-mcp'

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