PromptArmor

PromptArmor Analyze API

Analyze LLM input and output through the detector engine.

GitHub OpenAPI
Business capability
Threat Detection & Response Management BC-620.30

Operations 2

POST /v1/analyze/input Analyze LLM input #
POST /v1/analyze/output Analyze LLM output #

Documentation

📖
Documentation
https://promptarmor.readme.io/reference/basics-of-promptarmor-architecture
📖
APIReference
https://promptarmor.readme.io/reference/post_v1-check-content

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/prompt-armor/refs/heads/main/openapi/prompt-armor-analyze-api-openapi.yml

Other Resources

🔗
PostmanCollection
https://raw.githubusercontent.com/api-evangelist/prompt-armor/refs/heads/main/collections/prompt-armor.postman_collection.json
🔗
OpenCollection
https://raw.githubusercontent.com/api-evangelist/prompt-armor/refs/heads/main/collections/prompt-armor.opencollection.json
🔗
APIsJSON
https://raw.githubusercontent.com/api-evangelist/prompt-armor/refs/heads/main/apis.yml

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/prompt-armor-analyze-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

prompt-armor-analyze-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: PromptArmor Analyze API
  description: PromptArmor is an LLM application security platform that detects and blocks indirect prompt injection, data exfiltration, phishing, and system manipulation in production AI applications.
  termsOfService: https://www.promptarmor.com/
  contact:
    name: PromptArmor
    url: https://www.promptarmor.com/
  version: '1.0'
servers:
- url: https://api.promptarmor.com
  description: PromptArmor production API
security:
- ApiKeyAuth: []
tags:
- name: Analyze
  description: Analyze LLM input and output through the detector engine.
paths:
  /v1/analyze/input:
    post:
      operationId: analyzeInput
      tags:
      - Analyze
      summary: Analyze LLM input
      description: Analyzes LLM input (for example an email your LLM is about to summarize) and runs the detectors - including adversarial input detection - returning a verdict. When a session_id is supplied, session-based anomaly detection is also run.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AnalyzeRequest'
      responses:
        '200':
          description: Detection verdict.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AnalyzeResponse'
        '401':
          description: Missing or invalid Api-Key.
        '429':
          description: Rate limited.
  /v1/analyze/output:
    post:
      operationId: analyzeOutput
      tags:
      - Analyze
      summary: Analyze LLM output
      description: Analyzes LLM output (for example the summary your LLM produced) and runs the detectors - including data exfiltration detection - returning a verdict. When a session_id is supplied, session-based anomaly detection is also run.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AnalyzeRequest'
      responses:
        '200':
          description: Detection verdict.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AnalyzeResponse'
        '401':
          description: Missing or invalid Api-Key.
        '429':
          description: Rate limited.
components:
  schemas:
    AnalyzeResponse:
      type: object
      properties:
        containsInjection:
          type: boolean
          description: True when the analyzed text matches a known injection / threat class.
        detectors:
          type: object
          description: Per-detector results. A detector value of true indicates an issue was found for that detection type (for example data exfiltration, phishing, system manipulation, adversarial instructions).
          additionalProperties:
            type: boolean
    AnalyzeRequest:
      type: object
      required:
      - text
      properties:
        text:
          type: string
          description: The LLM input or output text to analyze (for example an email being summarized, or the generated summary).
        session_id:
          type: string
          description: Optional session identifier enabling session-based anomaly detection across multiple analyze calls.
        detectors:
          type: array
          description: Optional list of detectors to apply for this request.
          items:
            type: string
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: Api-Key
      description: PromptArmor API key passed in the Api-Key request header.