Skip to main content
Metatextai logo
  • Category: artificial intelligence
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 13
  • Triggers: 0
  • Slug: METATEXTAI
  • Version: 20261101_00

Tools

Slug: METATEXTAI_CHAT_COMPLETIONSGenerate OpenAI-compatible chat completions for a chosen model from a prompt or conversation messages. Control generation with temperature, a stop sequence, and a maximum token count.

Input Parameters

string
Optional stop sequence to end generation when encountered.
string
required
Model to use for chat completion.
string
Optional prompt text; alternative to using ‘messages’.
string
Optional project identifier for billing or project-specific settings.
array
List of message objects for conversation; alternative to ‘prompt’.
integer
Maximum number of tokens to generate.
number
Sampling temperature to use, between 0.0 and 2.0.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_CLASSIFYClassify text using a project model and return labels with confidence scores. Missing confidence is reported as 0.0; an empty prediction list can also result from access, availability, rate-limit, or network failures.

Input Parameters

string
required
Text to classify.
string
Model identifier to use. Defaults to the project’s primary model if omitted.
object
Optional settings to refine classification behavior.
string
required
Identifier of the project to use for classification.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_CREATE_POLICY_GUARDRAILSCreate a policy guardrail for a specific application to define automated content rules. Specify the policy’s rules and targets, with an optional description and custom violation response.

Input Parameters

string
required
Unique identifier for the new policy
array
required
List of policy rules to enforce
string
required
Where the policy applies. Allowed values: ‘user’, ‘assistant’, ‘context’, ‘system’. Aliases: ‘output’=assistant, ‘input’=[‘user’,‘context’]
string
Optional short description of the policy
string
required
Identifier of the application in which to create the policy
string
Optional custom message returned when a policy violation occurs

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_DELETE_POLICY_GUARDRAILSDelete a guardrail policy by application and policy ID. A success result can also reflect a 404 or 410 response and does not necessarily confirm that a policy was deleted.

Input Parameters

string
required
The ID of the policy to delete.
string
required
The ID of the application.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_EVALUATETool to evaluate LLM messages against policies/guardrails. Use after generating model output to get violation details or corrections.

Input Parameters

array
required
Conversation messages to evaluate. Must include ‘user’ and ‘assistant’ messages; ‘system’ optional.
array
Inline policies to evaluate; overrides console defaults when provided.
boolean
If true, stops evaluation on first violation.
array
List of policy IDs to override default console policies.
string
Application identifier; defaults to your configured application ID.
string
Top-level override response message on violation. Overrides correction.
boolean
If true, returns corrected output when violations occur (unless override_response is set).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_EXTRACTExtract structured data from text using a project model. Empty predictions can also result from access, endpoint availability, or rate-limit failures.

Input Parameters

string
required
Text to perform information extraction on
string
Optional model identifier to use for extraction
object
Additional options for extraction
string
required
Identifier of the project to run extraction on

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_GENERATEGenerate text for a project model using either a prompt or chat messages. Set temperature, a stop sequence, and a maximum token count to control generation.

Input Parameters

string
Sequence at which to stop generating further tokens.
string
required
Model to use for generation (e.g., ‘gpt-3.5’).
string
Prompt text for completion. Provide this OR messages, not both.
array
List of chat messages for chat-based models. Provide this OR prompt, not both.
integer
Maximum number of tokens to generate.
string
required
Identifier of the project to use for generation.
number
Sampling temperature between 0 and 2.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_LIST_APPLICATIONSList MetaTextAI applications to discover their available IDs, names, and descriptions.

Input Parameters

string
Filter by tag or label (if supported)
integer
Maximum number of applications to return (if supported)
integer
Number of items to skip (if supported)
Filter applications by name/description (if supported)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_LIST_MODELSList available models and their supported tasks to help choose a model for chat completions. An empty list can also indicate an authorization or endpoint failure, or an unrecognized response shape.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_LIST_POLICIES_GUARDRAILSList guardrail policies for a specific application using its application ID, to inspect its configured policies.

Input Parameters

string
required
Identifier of the application to list policies for

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_LIST_RED_TEAM_TEST_PROBESList available red-team test probe identifiers to discover probes for red teaming. No parameters are required.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_RUN_RED_TEAM_TEST_SCANTool to run a vulnerability red-team test scan. Use when you need to execute probes against an application.

Input Parameters

array
List of probe identifiers to run. If not provided, default probes will be used.
string
required
The application ID to scan.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: METATEXTAI_UPDATE_POLICY_GUARDRAILSUpdate an existing application’s policy guardrails and rules. The returned policy may echo the request even when all endpoints fail and one returned 403 or 404, so it does not by itself confirm the update.

Input Parameters

string
required
Unique policy ID. Must be identical to the path policy_id.
array
required
List of rule objects that define the guardrails.
string
required
Where rules apply. Allowed values: ‘user’, ‘assistant’, ‘context’, ‘system’. Alias ‘input’ maps to [‘user’,‘context’], ‘output’ maps to ‘assistant’.
string
required
The policy ID to update. Must match id in the body.
string
Short description of the policy (optional).
string
required
The application ID that scopes the policy.
string
Custom message returned when violations occur (optional).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not