ModelMarket Firewall API

The firewall API from ModelMarket — 1 operation(s) for firewall.

GitHub OpenAPI

Operations 1

POST /x402/warden-scan WARDEN verdict on an MCP server's tools/list: allow or block, a 0-1 score and… #

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/modelmarket-dev:modelmarket-dev-firewall-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

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. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

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

OpenAPI Specification

modelmarket-dev-firewall-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: modelmarket.dev — AIMarket Hub v3 Firewall API
  description: Lean federation hub for AI capability discovery and routing. Plugins extend functionality.
  version: 3.21.0
tags:
- name: Firewall
paths:
  /x402/warden-scan:
    post:
      operationId: wardenScan
      summary: 'WARDEN verdict on an MCP server''s tools/list: allow or block, a 0-1 score and…'
      description: 'WARDEN verdict on an MCP server''s tools/list: allow or block, a 0-1 score and every finding with the matched text (prompt injection, secret requests, exfiltration, hidden Unicode). Deterministic published rules, no network.'
      tags:
      - Firewall
      x-payment-info:
        price:
          mode: fixed
          currency: USD
          amount: '0.001'
        protocols:
        - x402:
            scheme: exact
            network: eip155:8453
            asset: USDC
            payTo: '0x1218ff36C5d2e3B6A565CdB1A8B1AcCFc606Ad0a'
      security: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                tools:
                  type: array
                  description: the server's tools/list result, up to 500 definitions
                  items:
                    type: object
                    properties:
                      name:
                        type: string
                      description:
                        type: string
                      inputSchema:
                        type: object
                    required:
                    - name
                server:
                  type: object
                  description: optional {name, url}, used only as a label
              required:
              - tools
            example:
              tools:
              - name: get_weather
                description: Returns the forecast for a city.
                inputSchema:
                  type: object
      responses:
        '200':
          description: The result (paid).
          content:
            application/json:
              schema:
                type: object
                properties:
                  status:
                    type: string
                    const: ok
                  service:
                    type: string
                    const: warden-scan
                  engine:
                    type: object
                    properties:
                      package:
                        type: string
                      ruleset:
                        type: object
                        properties:
                          version:
                            type: string
                          digest:
                            type: string
                    required:
                    - package
                  verdict:
                    type: object
                    properties:
                      allow:
                        type: boolean
                      score:
                        type: number
                        minimum: 0
                        maximum: 1
                      decidedBy:
                        type:
                        - string
                        - 'null'
                      blockedTools:
                        type: array
                        items:
                          type: string
                      allowedTools:
                        type: array
                        items:
                          type: string
                      findings:
                        type: array
                        items:
                          type: object
                          properties:
                            gate:
                              type: string
                            code:
                              type: string
                            severity:
                              type: string
                            tool:
                              type:
                              - string
                              - 'null'
                            advisory:
                              type: boolean
                            message:
                              type: string
                          required:
                          - gate
                          - code
                          - severity
                          - message
                    required:
                    - allow
                    - score
                    - findings
                  scope:
                    type: string
                required:
                - status
                - service
                - engine
                - verdict
              example:
                status: ok
                service: warden-scan
                engine:
                  package: '@aimarket/warden@0.31.0'
                  ruleset:
                    version: '23'
                verdict:
                  allow: true
                  score: 1
                  findings: []
        '400':
          description: 'Missing or invalid input. Not settled: the buyer pays nothing.'
        '402':
          description: 'Payment required: the x402 V2 terms are in the PAYMENT-REQUIRED header.'
          headers:
            PAYMENT-REQUIRED:
              schema:
                type: string
              description: base64 JSON x402 payment terms
        '429':
          description: Per-caller rate limit.
        '502':
          description: The upstream service failed. Not settled.