Mondaycom APIBLOCK
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Enable AI agents to operate reliably within real workflows. This MCP is monday.com's open framework for connecting agents into your work OS - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.
🌟 Overview
This repository, maintained by the monday.com AI team, provides a comprehensive set of tools for AI agent developers who want to integrate with monday.com. Whether you're building AI assistants, automations, or custom integrations, our tools make it easy to connect to the monday.com platform.
👉 New to monday MCP? Start here: [monday.com/w/mcp](https://monday.com/w/mcp)
🔑 What is monday.com?
monday.com is a work operating system that powers teams to run processes, projects, and everyday work. Teams use monday.com to plan, track, and manage their work in one centralized platform. It provides a visual, intuitive interface where t
bc1e742f98a2OBSERVED · 2026-10-01Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add monday-api-mcp -- npx -y @mondaydotcomorg/[email protected]
{
"mcpServers": {
"monday-api-mcp": {
"command": "npx",
"args": [
"-y",
"@mondaydotcomorg/[email protected]"
]
}
}
}Exposed tools (6)
6 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Builders | read | |
Development | read | Dev workspace |
Engineering | read | Engineering workspace |
child | read | desc |
my_schema | read | A test schema |
schema_a | read | First |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (7 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (17)
1. A monday.com developer account with developer mode enabled
- `create_item` — was `[IMPORTANT] use create_items instead...`; now leads with what the tool creates
- `change_item_column_values` — was `[IMPORTANT] use update_items instead...`; now leads with what it changes
.eslintignore
.graphqlrc.yml
.prettierignore
.prettierrc.json
import { ToolInputType, ToolOutputType, ToolType } from '../../../tool';import { MondayApiResponse } from '../../base-tool/base-monday-apps-tool';import { ToolInputType, ToolOutputType, ToolType } from '../../../tool';import { ToolInputType, ToolOutputType, ToolType } from '../../../tool';import { ToolInputType, ToolOutputType, ToolType } from '../../../tool';@typescript-eslint/eslint-plugin, @typescript-eslint/parser, eslint, prettier, ts-node, turbo, typescript
@mondaydotcomorg/api, axios, exceljs, jsonwebtoken, mammoth, unpdf, zod, zod-to-json-schema
@modelcontextprotocol/sdk, @mondaydotcomorg/agent-toolkit, @mondaydotcomorg/atp-client, @mondaydotcomorg/atp-mcp-adapter, @mondaydotcomorg/atp-server, dotenv, zod, @types/jest
packages/agent-toolkit/src/monday-graphql/generated/graphql.dev/graphql.ts
packages/agent-toolkit/src/monday-graphql/generated/graphql/graphql.ts
Gates applied: instruction_override, no_behavioural_pass.
bc1e742f98a2full audit observations/trust-audit/mcp-server/mondaycom__mondaycom-api.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-01 | bc1e742f98a2 | BLOCK | D | 69 | first audit |
Questions
What is the Mondaycom API MCP server?
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.
What tools does Mondaycom API expose?
6 in total: 6 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Mondaycom API safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Mondaycom API need?
No credential environment variables were found in its source, so it appears to need none.
How does Mondaycom API run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @mondaydotcomorg/monday-api-mcp at 3.3.1.
How current is this page?
The grade is for one exact copy of the source (bc1e742f98a2), read on 2026-10-01. The repository is watched and re-audited when it changes.