mcp-tool

A development guide for building monday.com API tools in the Agent Toolkit package. monday.com is a work-management platform, and its API lets software read or change boards and other account data.

In plain words
What is it for?
Use it when creating, changing, or debugging platform API tools, defining their inputs and outputs, or adding MCP tools under the toolkit’s platform-api-tools directory.
Why use it?
It gives developers the required structure and conventions for adding or debugging tools that communicate with monday.com through GraphQL, a way to query APIs.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/mondaycom/mcp/mcp-tool
Clone the repo
git clone --depth 1 https://github.com/mondaycom/mcp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,808 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01808
Opus 5 $0.00000 $0.00904
Sonnet 5 $0.00000 $0.00362
Haiku 4.5 $0.00000 $0.00181

Measured yesterday against content hash dee7aaf1feab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-tool scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/mcp-tool.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developing monday.com API Tools (Agent Toolkit)

Guide for developing monday.com platform API tools in the agent-toolkit package. Use when creating, modifying, or debugging tools in packages/agent-toolkit/src/core/tools/platform-api-tools/, working with GraphQL queries, or adding new MCP tools to the toolkit.

Package Location

packages/agent-toolkit — published as @mondaydotcomorg/agent-toolkit.

Architecture Overview

All platform API tools live under src/core/tools/platform-api-tools/. Each tool extends BaseMondayApiTool<InputSchema, Output> from base-monday-api-tool.ts, which itself implements the Tool interface from src/core/tool.ts.

Tool interface

// From src/core/tool.ts
interface Tool<Input, Output> {
  name: string;             // snake_case identifier (e.g. "create_update")
  type: ToolType;           // READ, WRITE, or ALL_API
  annotations: ToolAnnotations; // MCP annotations
  enabledByDefault?: boolean;
  getDescription(): string;
  getInputSchema(): Input;
}

BaseMondayApiTool

abstract class BaseMondayApiTool<Input, Output> {
  constructor(mondayApi: ApiClient, apiToken?: string, context?: MondayApiToolContext);
  abstract name: string;
  abstract type: ToolType;
  abstract annotations: ToolAnnotations;
  abstract getDescription(): string;
  abstract getInputSchema(): Input;
  protected abstract executeInternal(input): Promise<ToolOutputType<Output>>;
}

The public execute() method wraps executeInternal() with tracking. Always implement executeInternal(), never override execute().

Creating a New Tool

1. File structure

Simple tools can be a single file. Tools with GraphQL operations, tests, or helpers should use a folder:

tool-name/
├── tool-name.ts              # Tool class
├── tool-name.graphql.ts      # GraphQL query/mutation
├── tool-name.test.ts         # Tests
└── tool-name.utils.ts        # Helpers

2. Define GraphQL operations

Create a .graphql.ts file using gql from graphql-request:

Read the full file on GitHub · 224 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 224 lines · 0 tokens per session scan A dee7aaf1feab

Subscribe to this mod's changes

mcp-tool is a command published in the GitHub repository mondaycom/mcp (421 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,808 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.