Skip to main content
Glama
TylerIlunga

Procore MCP Server

Discover Procore API Categories

procore_discover_categories
Read-onlyIdempotent

Retrieve a hierarchical map of Procore API categories, modules, and endpoint counts. Start here to understand what Procore can do and narrow subsequent searches.

Instructions

List every Procore API category with its modules and endpoint counts. Use this as the first step when exploring what Procore can do — it returns a hierarchical map (Category > Module > endpoint count) that scopes any follow-up discovery or search call. Returns a JSON object; takes no inputs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Tool 'procore_discover_categories' is registered via server.registerTool with metadata (title, description, inputSchema) and a callback that delegates to handleDiscoverCategories.
    server.registerTool(
      "procore_discover_categories",
      {
        title: "Discover Procore API Categories",
        description:
          "List every Procore API category with its modules and endpoint counts. " +
          "Use this as the first step when exploring what Procore can do — it returns " +
          "a hierarchical map (Category > Module > endpoint count) that scopes any " +
          "follow-up discovery or search call. Returns a JSON object; takes no inputs.",
        inputSchema: {},
        annotations: { title: "Discover API Categories", ...READ_ONLY },
      },
      async () => {
        const text = await handleDiscoverCategories();
        return { content: [{ type: "text" as const, text }] };
      }
    );
  • Main handler: fetches category index from the catalog service and formats it into a human-readable hierarchical string (Category > Module > endpoint count).
    export async function handleDiscoverCategories(): Promise<string> {
      const index = getCategories();
    
      const lines: string[] = [
        `Procore API — ${index.totalEndpoints} total endpoints across ${Object.keys(index.categories).length} categories\n`,
      ];
    
      for (const [name, data] of Object.entries(index.categories).sort(
        (a, b) => b[1].totalEndpoints - a[1].totalEndpoints
      )) {
        lines.push(`## ${name} (${data.totalEndpoints} endpoints)`);
        const modules = Object.entries(data.modules)
          .sort((a, b) => b[1].endpointCount - a[1].endpointCount)
          .map(([mod, info]) => `  - ${mod}: ${info.endpointCount} endpoints`)
          .join("\n");
        lines.push(modules);
        lines.push("");
      }
    
      lines.push(
        "Use procore_discover_endpoints with a category and optional module to see specific endpoints."
      );
    
      return lines.join("\n");
    }
  • Helper function that delegates to repository to load the category index from a JSON file.
    export function getCategories(): CategoryIndex {
      return loadCategories();
    }
  • Loads cached categories.json data from disk with in-memory caching.
    export function loadCategories(): CategoryIndex {
      if (categoriesCache) return categoriesCache;
      const raw = readFileSync(join(DATA_DIR, "categories.json"), "utf8");
      categoriesCache = JSON.parse(raw) as CategoryIndex;
      return categoriesCache;
    }
  • Type definition for the CategoryIndex returned by the handler — defines the shape of categories, modules, and endpoint counts.
    export interface CategoryIndex {
      categories: Record<
        string,
        {
          modules: Record<string, { endpointCount: number; tags: string[] }>;
          totalEndpoints: number;
        }
      >;
      totalEndpoints: number;
      generatedAt: string;
    }
Behavior4/5

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, indicating safe read operation. Description adds value by stating return type ('JSON object') and structure ('hierarchical map'), and confirms no inputs. No contradictions.

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 sentences: first states purpose, second adds usage guidance and return format. Front-loaded with key information. No unnecessary words.

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?

No output schema, but description outlines structure (Category > Module > endpoint count) and return type (JSON object). Sufficient for a discovery tool. No missing behavioral cues beyond annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has no properties, so schema_description_coverage is trivially 100%. Description explicitly states 'takes no inputs', which is sufficient. Baseline for zero parameters is 4.

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 tool lists every Procore API category with modules and endpoint counts. It uses specific verb 'list' and resource 'Procore API categories'. The hierarchical map detail differentiates it from sibling tools like procore_discover_endpoints and procore_search_endpoints.

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?

Explicitly says 'Use this as the first step when exploring what Procore can do', providing clear context for when to use. It also implies scoping follow-up calls, but doesn't explicitly state when not to use it or list alternatives.

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/TylerIlunga/procore-mcp-server'

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