Skip to main content
Glama
mondaycom

monday MCP Server

Official

Configure AI Column

configure_ai_column

Configure AI on an existing column of a monday.com board to automate tasks like categorization, summarization, translation, extraction, text generation, writing improvement, or person assignment.

Instructions

Add AI to a column or set up an AI column on a monday.com board. Use this tool when the user wants to automatically categorize, summarize, translate, extract, generate text, improve writing, or assign people using AI on a column. This is the right tool for requests like "add AI to a column", "set up automatic extraction/categorization/summarization", "make a column use AI", "configure AI on a column", or "use AI to automatically fill a column".

The column must already exist on the board with a compatible type for the chosen block. To create a new AI column, first use create_column to create the column, then use this tool to add AI behavior.

BLOCK TYPES (only pass fields that apply to the chosen block_type):

  • categorize: { block_type, source_type, source_column_id?, additional_instructions? } — assigns labels from target column's existing status/dropdown options

  • summarize: { block_type, source_type, source_column_id?, additional_instructions? } — generates concise summaries

  • translate: { block_type, source_type, source_column_id?, target_language } — translates to target language

  • improve_text: { block_type, source_type, source_column_id?, tone?, improver_length?, refinement_type? } — rewrites/fixes text

  • extract: { block_type, source_type, source_column_id?, entity_type, custom_instructions?, additional_instructions? } — extracts structured info

  • open_block: { block_type, ai_query } — flexible custom prompt, reference columns via {pulse.column_id}

  • write_me: { block_type, ai_query, tone, output_length } — generates new text from prompt

  • person_assignment: { block_type, source_type, source_column_id?, groups } — assigns people based on context

SOURCE TYPES (required for all blocks except open_block and write_me):

  • item_name: uses the item's name as input

  • thread: uses the item's updates/comments as input

  • column: uses another column's value (requires source_column_id)

  • emails_and_activities: uses emails & activities (categorize only)

COLUMN REFERENCE SYNTAX (for open_block and write_me ai_query):

  • {pulse.column_id} — regular board column

  • {pulse.name} — the item name

  • {pulse.subitem.column_id} — subitem column

RELATED TOOLS:

  • create_column — create the target column first if it doesn't exist

  • get_board_schema — discover existing columns and their types/IDs

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
board_idYesThe ID of the board containing the column
column_idYesThe ID of the column to configure with AI
block_typeYesThe AI block type to configure. See tool description for which fields apply to each block.
source_typeNoWhere the AI reads input. Required for all blocks except open_block and write_me. Values: item_name (item name), thread (updates/comments), column (another column — requires source_column_id), emails_and_activities (categorize only).
source_column_idNoThe ID of the source column. Required when source_type is "column".
additional_instructionsNoCustom instructions for categorize/summarize/extract blocks (max 3000 chars).
target_languageNoRequired for translate block. The target language to translate text into.
toneNoWriting tone. Required for write_me, optional for improve_text.
output_lengthNoRequired for write_me block. Approximate desired output length.
improver_lengthNoFor improve_text only. Desired length relative to input text.
refinement_typeNoFor improve_text only. Level of text refinement to apply.
entity_typeNoRequired for extract block. Type of entity to extract from text.
custom_instructionsNoRequired for extract when entity_type is "custom". Describes what to extract (max 3000 chars).
ai_queryNoRequired for open_block and write_me. Natural-language prompt. Reference columns via {pulse.column_id}, item name via {pulse.name}, subitems via {pulse.subitem.column_id}. Max 3000 chars.
groupsNoRequired for person_assignment. Array of groups, each with user_ids and a description.
run_backfillNoWhether to immediately apply AI to existing items (up to 200). Defaults to true.
Behavior5/5

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

Annotations show readOnlyHint=false, destructiveHint=false, idempotentHint=false, which are consistent with the description's focus on configuring AI (non-read, non-destructive). The description discloses prerequisites (column must exist with compatible type) and behavior per block type, adding context beyond 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 well-structured with sections for block types, source types, column reference syntax, and related tools. It is slightly verbose but every section adds necessary information. Front-loaded with purpose and usage.

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?

With 16 parameters and no output schema, the description covers all necessary context: prerequisites, block-specific parameter requirements, source type explanations, column reference syntax, and related tools. It is complete for a complex configuration tool.

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 coverage is 100%, but the description adds value by listing which parameters apply to each block type, explaining source types and column reference syntax. This helps the AI agent correctly fill parameters beyond the schema's descriptions.

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's purpose: 'Add AI to a column or set up an AI column on a monday.com board'. It lists specific use cases (categorize, summarize, translate, etc.) and distinguishes from sibling tools like create_column.

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 explicitly tells when to use this tool (e.g., 'add AI to a column', 'set up automatic extraction/categorization/summarization') and provides alternative tools (create_column for creating a column first). It also details block types, source types, and column reference syntax.

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