# Agents API

> You're reading the Mindset v3 documentation. v3 is no longer sold; this is reference for existing customers. Mindset 4 docs are at /docs.

Parameters full description

- [Note](https://docs4.mindset.ai/v3/deploy/api/agent-management-deprecated/retrieve-agents): You can find below the full description of Parameters for each POST/PATCH/GET/DELETE methods and also what parameters you can expect from the API responses.

  If you want to test the API, please see the Agents API playground.

#### POST - Create a new agent

## Parameters:

#### **agentName** *String*

Name of the agent

#### **agentPurpose** *String*

Purpose of the agent

Please read [Agent creation - Provide clear purpose](https://docs4.mindset.ai/v3/deploy/sdk2/sdk2-best-practices#1-provide-clear-purpose)

#### **formatting** *String*

Output formatting instructions

Please read [Agent creation - Specify clear formatting rules](https://docs4.mindset.ai/v3/deploy/sdk2/sdk2-best-practices#3-specify-clear-formatting-rules)

#### **agentPersonality** *String*

Personality of the agent

Please read [Agent creation - Define personality traits](https://docs4.mindset.ai/v3/deploy/sdk2/sdk2-best-practices#2-define-personality-traits)

#### **agentPolicyRules** *String*

Policy rules for the agent

Please read [Agent creation - Set appropriate policies](https://docs4.mindset.ai/v3/deploy/sdk2/sdk2-best-practices#4-set-appropriate-policies)

#### **contextUids** *String\[]*

Array of existing context Uids (max 30)

#### **mcpserverUids** *String\[]*

Array of existing mcpserver Uids (max 5)

#### **planUids** *String\[]*

Array of existing plan UIDs (max 20)

#### **skillUids** *String\[]*

Array of existing skill UIDs (max 20)

#### **tags** *String\[]*

Array of tags (max 10). You will be able to view reports based grouping or filtering of activity according to the tags applied when creating the agent.

#### **access** *String*

default : `restrictedAccess` Access control mode for this agent. Use Agent Sessions with restrictedAccess agents.

Possible values: \[`restrictedAccess`, `openAccess`]

#### **externalTenantId** *String*

External tenant identifier. Valid characters are A-Za-z0-9\_-.

#### **iceBreakerMessage** *String*

Invisible instruction to prompt the agent to greet users in a specific way or style (max 1000)

#### PATCH - Update an existing agent

## Parameters:

#### **agentName** *String*

Name of the agent

#### **agentPurpose** *String*

Purpose of the agent

#### **formatting** *String*

Output formatting instructions

#### **agentPersonality** *String*

Personality of the agent

#### **agentPolicyRules** *String*

Policy rules for the agent

#### **live** *Boolean*

Set the agent status: live or not live

#### **contextUids** *String\[]*

Array of existing context Uids (max 30)

#### **mcpserverUids** *String\[]*

Array of existing mcpserver Uids (max 5)

#### **planUids** *String\[]*

Array of existing plan UIDs (max 20)

#### **skillUids** *String\[]*

Array of existing skill UIDs (max 20)

#### **tags** *String\[]*

Array of tags (max 10). You will be able to view reports based grouping or filtering of activity according to the tags applied when creating the agent.

#### **access** *String*

default : `restrictedAccess` Access control mode for this agent. Use Agent Sessions with restrictedAccess agents.

Possible values: \[`restrictedAccess`, `openAccess`]

#### **externalTenantId** *String*

External tenant identifier. Valid characters are A-Za-z0-9\_-.

#### **iceBreakerMessage** *String*

Invisible instruction to prompt the agent to greet users in a specific way or style (max 1000)

#### GET - Query the list of agents

## Parameters:

#### **startAfter - Querying for “the next page”** *String*

Use the `startAfter` parameter and provide the `createdAt` string of the last agent in the current results set When there are no more results you will receive an empty array in the response and a 404 status code

#### **contextUid** *String*

Filter results to a specific contextUid (cannot be used with mcpserverUid)

#### **mcpserverUid** *String*

Filter results to a specific mcpserverUid (cannot be used with contextUid)

#### **externalTenantId** *String*

Filter results to a specific externalTenantId

#### DELETE - Delete an agent by providing its uid

#### RESPONSE DATA

You will get the same response data when calling POST, PATCH or GET.

**_Note_**: When retrieving a collection of agents, the response will be an array of objects.

#### **uid** *String*

Mindset internal agent uid

#### **agentName** *String*

Name of the agent

#### **agentPurpose** *String*

Purpose of the agent

#### **formatting** *String*

Output formatting instructions

#### **agentPersonality** *String*

Personality of the agent

#### **agentPolicyRules** *String*

Policy rules for the agent

#### **live** *Boolean*

Agent status: live or not live

#### **createdAt** *ISO timestamp*

Agent creation date

#### **contextUids** *String\[]*

Array of existing context Uids (max 30)

#### **mcpserverUids** *String\[]*

Array of existing mcpserver Uids (max 5)

#### **planUids** *String\[]*

Array of plan UIDs (max 20)

#### **skillUids** *String\[]*

Array of skill UIDs (max 20)

#### **tags** *String\[]*

Array of tags (max 10).

#### **access** *String*

Access control mode for this agent. Possible values: \[`restrictedAccess`, `openAccess`]

#### **externalTenantId** *String*

#### **iceBreakerMessage** *String*