Lightfield MCP integration for AI agents.

Connect AI agents to Lightfield through 10 structured actions, including get account, get api key metadata, and get contact. Review authentication, inputs, w…

ACTION CONTRACTS
10
AUTHENTICATION
API key
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the Lightfield integration exposes

The Lightfield Agent App exposes 10 provider-backed actions for productivity and ai work. Its current contract lets an authorized agent get one lightfield account by id, validate the current lightfield api key and return its subject and scopes, and get one lightfield contact by id. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.

For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Lightfield account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real Lightfield capabilities.

Showing 10 of 10 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

get_accountREAD

Get one Lightfield account by ID.

INPUTS: id

get_api_key_metadataREAD

Validate the current Lightfield API key and return its subject and scopes.

get_contactREAD

Get one Lightfield contact by ID.

INPUTS: id

get_custom_object_recordREAD

Get one Lightfield custom object record by object type and record ID.

INPUTS: entitySlug / id

get_opportunityREAD

Get one Lightfield opportunity by ID.

INPUTS: id

list_accountsREAD

List Lightfield accounts with optional pagination and filters.

INPUTS: limit / offset / filters

list_contactsREAD

List Lightfield contacts with optional pagination and filters.

INPUTS: limit / offset / filters

list_custom_object_recordsREAD

List records for a Lightfield custom object type with optional filters.

INPUTS: entitySlug / limit / offset / filters

list_object_definitionsREAD

List custom object types available to the current Lightfield API key.

list_opportunitiesREAD

List Lightfield opportunities with optional pagination and filters.

INPUTS: limit / offset / filters

INPUT CONTRACTS

Know what the action needs before it runs.

get_account

idREQUIRED
The Lightfield record ID to retrieve.

get_contact

idREQUIRED
The Lightfield record ID to retrieve.

get_custom_object_record

entitySlugREQUIRED
The custom object type slug.
idREQUIRED
The Lightfield record ID to retrieve.

get_opportunity

idREQUIRED
The Lightfield record ID to retrieve.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Get Account

Get one Lightfield account by ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

get_account

Verify with Get Api Key Metadata

Validate the current Lightfield API key and return its subject and scopes. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

get_api_key_metadata

SAFETY BOUNDARY

Operate Lightfield with explicit limits

  • Authorize Lightfield with API key and grant only the provider access required by the selected actions.
  • The current action names appear read-oriented, but returned Lightfield data may still be sensitive and should be minimized before it enters model context.
  • Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
  • The sampled contract declares provider scopes including `accounts:read`, `contacts:read`, and `opportunities:read`; verify the complete action contract before execution.
  • After a call, inspect the structured result and execution record before reporting that the Lightfield task completed successfully.

CONNECTION MODEL

API key

Lightfield API key sent as a Bearer token. Admins can create and revoke keys from the Lightfield API keys settings page: https://crm.lightfield.app/crm/settings/api-keys.

Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.

READ SIGNALS
10
WRITE SIGNALS
0
HIGH IMPACT
0
REVIEW SIGNALS
0

EVIDENCE AND AVAILABILITY

Provider reference

Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Lightfield.

Official Lightfield website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS