Skip to main content
Glama
mondaycom

monday MCP Server

Official
by mondaycom

Manage monday Platform Agent

manage_agent
Destructive

Manage the full lifecycle of monday.com agents: create via AI or manually, read, update, delete, activate, deactivate, and run agents.

Instructions

Full lifecycle management for monday platform agents — create, read, update, delete, change state, and run.

monday platform agents are user-built work orchestrators on monday.com — each has a profile (name, role, avatar), a goal, and a markdown execution plan. Agents in state ACTIVE can be triggered automatically. They are NOT local LangChain or MCP agents.

ACTIONS (only pass fields that apply to the chosen action):

  • create: { action:"create", prompt, agent_model? } — AI-generated agent. Platform creates profile, goal, and plan from the prompt.

  • create_blank: { action:"create_blank", name?, role?, role_description?, avatar_url?, gender?, background_color?, user_prompt? } — manually defined agent.

  • get one: { action:"get", agent_id }

  • list owned: { action:"get" }

  • update: { action:"update", agent_id, name?, role?, role_description?, plan?, agent_model? }

  • delete: { action:"delete", agent_id }

  • activate: { action:"activate", agent_id }

  • deactivate: { action:"deactivate", agent_id }

  • run: { action:"run", agent_id }

RULES:

  • "create_blank" with no fields creates a nameless blank agent — only do this intentionally.

  • "update" requires at least one of name/role/role_description/plan/agent_model.

  • "update", "delete", "activate", "deactivate", "run" all require "agent_id".

  • Created agents start INACTIVE. Follow with action:"activate" using the returned agent_id before they can be triggered.

  • ⚠️ DESTRUCTIVE — "delete" is permanent and irreversible. When the user refers to an agent by name, ALWAYS call action:"get" first to confirm the correct agent_id before deleting.

  • "run" is fire-and-forget. Returns trigger_uuid — no run-status query exists, treat successful enqueue as the only signal.

  • Agent state is one of ACTIVE, INACTIVE, ARCHIVED, or FAILED. DELETED only appears as the return value of action:"delete".

USAGE EXAMPLES:

  • AI create: { "action": "create", "prompt": "Run my daily standup every weekday at 9am." }

  • Manual create:{ "action": "create_blank", "name": "Standup Bot", "role": "Project Manager", "gender": "female" }

  • Fetch one: { "action": "get", "agent_id": "42" }

  • List mine: { "action": "get" }

  • Rename: { "action": "update", "agent_id": "7", "name": "New Name" }

  • Activate: { "action": "activate", "agent_id": "7" }

  • Deactivate: { "action": "deactivate", "agent_id": "7" }

  • Run: { "action": "run", "agent_id": "7" }

  • Delete: { "action": "delete", "agent_id": "7" }

RELATED TOOLS:

  • agent_catalog — browse available trigger types and skills before wiring them to an agent

  • manage_agent_triggers — manage which triggers fire this agent automatically

  • manage_agent_skills — manage which skills this agent can perform

  • manage_agent_knowledge — manage which boards/docs this agent has access to

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes"create" — create a new agent via AI (pass prompt). "create_blank" — create a new agent manually (pass name/role/etc). "get" — fetch one agent by agent_id or list owned agents. "update" — modify mutable fields on an existing agent. "delete" — permanently delete an agent (irreversible). "activate" — transition agent to ACTIVE. "deactivate" — transition agent to INACTIVE. "run" — manually enqueue an agent run (fire-and-forget).
agent_idNoUsed with action:"get" to fetch a specific agent. Required for action:"update", "delete", "activate", "deactivate", "run". Omit for action:"create", "create_blank", or action:"get" (to list owned agents).
promptNoRequired for action:"create". Plain-language description of what the agent should do. Platform generates profile, goal, and plan via AI.
agent_modelNoUsed with action:"create" or action:"update". Omit unless the user explicitly names a valid monday-supported model.
nameNoUsed with action:"create_blank" or action:"update". Display name of the agent.
roleNoUsed with action:"create_blank" or action:"update". Short role title (e.g. "Customer Success Bot").
role_descriptionNoUsed with action:"create_blank" or action:"update". Detailed description of the agent role.
avatar_urlNoUsed with action:"create_blank". HTTPS URL of the avatar. Prefer dapulse-res.cloudinary.com or cdn.monday.com.
genderNoUsed with action:"create_blank". Hint for generated avatar/name when profile fields are omitted.
background_colorNoUsed with action:"create_blank". Lowercase hex, e.g. "#9450fd".
user_promptNoUsed with action:"create_blank". Stored as metadata. Not used for AI generation.
planNoUsed with action:"update". New step-by-step execution plan in markdown.
Behavior5/5

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

Annotations declare destructiveHint=true and readOnlyHint=false. The description reinforces that delete is permanent and irreversible, notes that 'run' is fire-and-forget with no run-status query, and states that created agents start inactive. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is relatively long due to the tool's complexity, but it is well-structured with clear sections (ACTIONS, RULES, USAGE EXAMPLES, RELATED TOOLS). It is front-loaded with a summary sentence. Every sentence adds necessary value, though some redundancy exists (e.g., rules repeated in examples). Slightly verbose but appropriate.

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

Completeness5/5

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

Given 12 parameters, 1 required, high complexity with conditional actions, and no output schema, the description covers all necessary aspects: action-specific parameter requirements, behavioral notes (fire-and-forget, agent states), safety warnings, and related tools. Examples for every action provide complete guidance.

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?

Schema description coverage is 100%, so baseline is 3. The description adds significant value by grouping parameters by action, providing examples, and clarifying conditional requirements (e.g., agent_id required for update/delete but omitted for create). It does not just repeat schema but offers cohesive action-specific guidance.

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 'Full lifecycle management for monday platform agents' and enumerates all actions (create, read, update, delete, change state, run). It identifies the resource as user-built work orchestrators on monday.com, distinguishing from local LangChain or MCP agents, and from sibling tools like agent_catalog.

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

Usage Guidelines5/5

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

The description provides explicit when-to-use guidance for each action, lists rules and common pitfalls (e.g., agents start inactive, delete is irreversible), includes usage examples for every action, and references related tools (agent_catalog, manage_agent_triggers, etc.) to direct the agent to 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/mondaycom/mcp'

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