Skip to main content
Glama
TylerIlunga

Procore MCP Server

Create Custom Field

create_custom_field

Create a custom field in Procore to store extra information for projects or people. Supply company ID, field name, and type to generate it.

Instructions

Creates a new Custom Field for a given company ID. Custom Fields are used to store additional information about Projects or People. company_id defaults to the value set by procore_set_config when omitted. Creates the custom field and returns it with its new id (HTTP 201); calling it again creates another record. Failures come back as an error payload carrying the HTTP status — commonly 401 when the token has expired, 403 without tool permission, and 404 when an id does not resolve. Required parameters: company_id, name, type. Procore API: Company Admin > Custom - Configurable Tools. Endpoint: POST /rest/v1.0/workforce-planning/v2/companies/{company_id}/custom-fields

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesJSON request body field — the name of the Custom Field that appears in the UI.
typeYesJSON request body field — the type of Custom Field. Determines the kind of data it will store. The type cannot be changed once created.
valuesNoJSON request body field — only applicable for `select` or `multi-select` fields. List of values that will be options in the field's dropdown.
sort_byNoJSON request body field — only applicable for `select` or `multi-select` fields. Controls sorting of dropdown values. `alpha` sorts alphabetically, while `listed` maintains the provided order.
on_peopleNoJSON request body field — if true, the field is available on People.
can_filterNoJSON request body field — if true, allows this field to be used as a filter.
company_idYesURL path parameter — unique identifier for the company. This parameter accepts both formats: - **Recommended**: Procore company ID (integer) - Use this for new integrations - Legacy: LaborChart UUID format (uuid string...
descriptionNoJSON request body field — a description to help Admin users understand the field’s purpose.
on_projectsNoJSON request body field — if true, the field is available on Projects.
integration_onlyNoJSON request body field — if true, only integrations can update this field.
Behavior4/5

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

The description adds behavior beyond annotations: 'calling it again creates another record' (non-idempotent), common error codes (401, 403, 404), company_id defaulting to procore_set_config value, and the HTTP 201 response with new id. These are consistent with annotations (readOnlyHint=false, idempotentHint=false), so no contradiction.

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 dense but front-loaded with the purpose in the first sentence, and each subsequent sentence adds value (default behavior, non-idempotency, error payloads, endpoint). It is somewhat long but not wasteful.

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?

Given 10 fully documented parameters, annotations, and no output schema, the description adequately covers the creation behavior, defaulting, non-idempotency, common errors, and endpoint. It does not detail the return structure beyond the new id, which is acceptable for a create tool.

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

Parameters2/5

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

Schema coverage is 100% with detailed parameter descriptions, so baseline is 3. However, the description says 'company_id defaults to the value set by procore_set_config when omitted' while the schema marks company_id as required, creating a direct contradiction. It also lists required parameters as company_id, name, type, further confusing whether company_id can be omitted. This inconsistency undermines reliable parameter handling.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource+scope: 'Creates a new Custom Field for a given company ID.' It also clarifies the domain by explaining custom fields store info about Projects or People and includes the endpoint. However, it does not explicitly distinguish from the similar sibling create_custom_field_definitions, so purpose is clear but sibling differentiation is implicit.

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

Usage Guidelines3/5

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

Usage is implied: the tool clearly creates a custom field, and the description notes custom fields are used for Projects or People. It does not explicitly state when not to use this tool or name alternatives such as update_custom_field or delete_custom_field, so guidance is implied rather than explicit.

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