Skip to main content
Glama

get_course

Read-onlyIdempotent

Retrieve a course record by providing its ID. Access course details and settings.

Instructions

Get a course record

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesID of the course to retrieve

Implementation Reference

  • The 'registerCourseTools' function registers the 'get_course' tool (among others) using server.registerTool(). This is the registration point.
    import { z } from "zod";
    import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { apiGet, apiList, apiPatch, apiPost } from "../api";
    import { formatCreate, formatError, formatList, formatShow, formatUpdate, type EduframeRecord } from "../formatters";
    import { logResponse } from "../response-logger";
    
    const courseCostSchemeEnum = z.enum(["student", "order", "tbd", "free"]);
    
    export function registerCourseTools(server: McpServer): void {
      server.registerTool(
        "get_courses",
        {
          description: "Get all course records",
          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)"),
            published: z.enum(["published"]).optional().describe("Show only published courses"),
          },
        },
        async ({ cursor, per_page, published }) => {
          try {
            const result = await apiList<EduframeRecord>("/courses", { cursor, per_page, published });
            void logResponse("get_courses", { cursor, per_page, published }, result);
            const toolResult = formatList(result.records, "courses");
            if (result.nextCursor) {
              toolResult.content.push({ type: "text", text: `\nNext page cursor: ${result.nextCursor}` });
            }
            return toolResult;
          } catch (error) {
            return formatError(error);
          }
        },
      );
    
      server.registerTool(
        "get_course",
        {
          description: "Get a course record",
          annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true },
          inputSchema: { id: z.number().int().positive().describe("ID of the course to retrieve") },
        },
        async ({ id }) => {
          try {
            const record = await apiGet<EduframeRecord>(`/courses/${id}`);
            void logResponse("get_course", { id }, record);
            return formatShow(record, "course");
          } catch (error) {
            return formatError(error);
          }
        },
      );
    
      server.registerTool(
        "create_course",
        {
          description: "Create a course.",
          annotations: { readOnlyHint: false, destructiveHint: false, idempotentHint: false },
          inputSchema: {
            category_id: z.number().int().describe("Identifier of the category of the course."),
            name: z.string().describe("The name of the course."),
            code: z.string().describe("The code of the course."),
            cost_scheme: courseCostSchemeEnum.optional().describe("How should the course be paid by default."),
            cost: z
              .string()
              .optional()
              .describe(
                "The price to be paid for this course. Required if cost_scheme is student (default value) or order.",
              ),
            is_published: z.boolean().optional().describe("Boolean representing the publishable status of the course."),
            custom: z.record(z.unknown()).optional(),
            custom_associations: z.record(z.unknown()).optional(),
            course_tab_contents_attributes: z
              .array(
                z.object({
                  content: z.string().describe("The HTML content of the course tab."),
                  course_tab_id: z.number().int().describe("Unique identifier of the course tab."),
                }),
              )
              .optional(),
          },
        },
        async (body) => {
          try {
            const record = await apiPost<EduframeRecord>("/courses", body);
            void logResponse("create_course", body, record);
            return formatCreate(record, "course");
          } catch (error) {
            return formatError(error);
          }
        },
      );
    
      server.registerTool(
        "update_course",
        {
          description: "Update a course.",
          annotations: { readOnlyHint: false, destructiveHint: false, idempotentHint: true },
          inputSchema: {
            id: z.number().int().positive().describe("ID of the course to update"),
            category_id: z.number().int().optional().describe("Identifier of the category of the course."),
            name: z.string().optional().describe("The name of the course."),
            code: z.string().optional().describe("The code of the course."),
            duration: z.string().optional().describe("The duration of the course."),
            level: z.string().optional().describe("A string indicating the level of the course."),
            result: z.string().optional().describe("The result of the course"),
            cost: z.string().optional().describe("The price to be paid for this course."),
            cost_scheme: courseCostSchemeEnum.optional().describe("How should the course be paid by default."),
            is_published: z.boolean().optional().describe("Boolean representing the publishable status of the course."),
            conditions: z.string().optional().describe("The conditions of the course."),
            custom: z.record(z.unknown()).optional(),
            custom_associations: z.record(z.unknown()).optional(),
            course_tab_contents_attributes: z
              .array(
                z.object({
                  content: z.string().optional().describe("The HTML content of the course tab."),
                  course_tab_id: z.number().int().optional().describe("Unique identifier of the course tab."),
                }),
              )
              .optional(),
          },
        },
        async ({ id, ...body }) => {
          try {
            const record = await apiPatch<EduframeRecord>(`/courses/${id}`, body);
            void logResponse("update_course", { id, ...body }, record);
            return formatUpdate(record, "course");
          } catch (error) {
            return formatError(error);
          }
        },
      );
    }
  • The handler for 'get_course'. It takes an 'id' parameter, calls apiGet('/courses/{id}'), logs the response, and returns formatShow(record, 'course').
    server.registerTool(
      "get_course",
      {
        description: "Get a course record",
        annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true },
        inputSchema: { id: z.number().int().positive().describe("ID of the course to retrieve") },
      },
      async ({ id }) => {
        try {
          const record = await apiGet<EduframeRecord>(`/courses/${id}`);
          void logResponse("get_course", { id }, record);
          return formatShow(record, "course");
        } catch (error) {
          return formatError(error);
        }
      },
    );
  • The input schema for the 'get_course' tool: requires a single 'id' parameter of type z.number().int().positive().
    {
      description: "Get a course record",
      annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true },
      inputSchema: { id: z.number().int().positive().describe("ID of the course to retrieve") },
    },
  • The 'apiGet' helper function used by the handler to perform the GET request to the Eduframe API endpoint.
    export async function apiGet<T>(path: string, query?: Record<string, QueryValue>): Promise<T> {
      const { token } = getConfig();
      const url = buildUrl(path, query);
    
      const response = await fetch(url.toString(), {
        method: "GET",
        headers: buildHeaders(token),
      });
    
      return handleResponse<T>(response);
    }
  • The 'formatShow' helper function that formats the retrieved record for display.
    export function formatShow(record: EduframeRecord, resourceName: string): CallToolResult {
      return {
        content: [
          {
            type: "text",
            text: `${resourceName}:\n\n${formatJSON(record)}${RESPONSE_LOG_HINT}`,
          },
        ],
      };
    }
Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description need not repeat these. It adds no further behavioral context (e.g., auth requirements, rate limits), making it adequate but not enriched.

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?

The description is a single, minimal sentence with no wasted words. For a simple retrieval tool, this level of conciseness is appropriate.

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?

Given the simplicity of the tool (one required parameter, clear schema, and annotations covering safety), the description is nearly complete. However, it omits any mention of the return value, which could be inferred but not explicit.

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 a clear description for the 'id' parameter. The description does not add any additional meaning beyond what the schema already provides.

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 a course record' clearly states the action (get) and the resource (course record). It implicitly distinguishes from plural 'get_courses' but does not explicitly differentiate from other get tools like 'get_course_variant' or 'get_course_location'.

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 is provided on when to use this tool versus alternatives like 'get_courses' for listing or 'get_course_variant' for variants. Usage context is implied but not explicit.

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