Public Commons Media Search

Available ActionsEach successful request consumes credits as outlined below.

search_titles^5crlist_page_media^5crget_file^5crsearch_commons_media^5cr

Details

Let AI agents search Wikipedia and Wikimedia Commons to discover and download free images, audio, video, and other public media assets. The tool provides simple actions for page title search, listing media on a page, fetching file URLs (thumbnail, preferred, original), and direct Commons media search with pagination, enabling agentic content sourcing and research workflows with clear file description and licensing context.

Use Cases

Agentic media discovery, Search Wikimedia Commons files by keyword, Find free images for articles, Retrieve media download URLs, Check file description and license pages, Collect public media assets for presentations, Build datasets of public images, Source audio or video clips for projects

Connect Your Agent In 5 Min

Watch the setup guide for your platform

Or Install Locally

STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections. This lightweight connector routes requests to https://api.agentpmt.com/mcp. All tool execution happens in the cloud and the server cannot edit any files on your computer.

npm install -g @agentpmt/mcp-routeragentpmt-setup

curl -X POST "https://api.agentpmt.com/products/purchase" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ********" \
  -d '{
    "product_id": "696ef640fb2f7d26fd1ef7ab",
    "parameters": {
      "action": "search_titles",
      "q": "example_q",
      "project": "wikipedia",
      "language": "en",
      "limit": 50
    }
  }'

import requests
import json

url = "https://api.agentpmt.com/products/purchase"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer ********"
}

data = {
    "product_id": "696ef640fb2f7d26fd1ef7ab",
    "parameters": {
        "action": "search_titles",
        "q": "example_q",
        "project": "wikipedia",
        "language": "en",
        "limit": 50
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.status_code)
print(response.json())

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "696ef640fb2f7d26fd1ef7ab",
  parameters: {
    "action": "search_titles",
    "q": "example_q",
    "project": "wikipedia",
    "language": "en",
    "limit": 50
  }
};

fetch(url, {
  method: "POST",
  headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error("Error:", error));

const axios = require('axios');

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "696ef640fb2f7d26fd1ef7ab",
  parameters: {
    "action": "search_titles",
    "q": "example_q",
    "project": "wikipedia",
    "language": "en",
    "limit": 50
  }
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error("Error:", error.message);
  });

Login to view your API and budget keys. The example above uses placeholder values. Sign in to see personalized code with your bearer token.

This tool supports credit-based access for external agents using AgentAddress identities or standard crypto wallets. External agents should use the External Agent API to buy credits with x402 and invoke this tool.

1. Buy Credits

Purchase credits via x402 payment (500 credit minimum, 100 credits = $1).

# Request payment requirements (returns 402 + PAYMENT-REQUIRED header)
curl -i -s -X POST "https://www.agentpmt.com/api/external/credits/purchase" \
  -H "Content-Type: application/json" \
  -d '{ "wallet_address":"0xYOUR_WALLET", "credits": 500, "payment_method":"x402" }'

# Sign the EIP-3009 authorization, then retry with signature header
curl -s -X POST "https://www.agentpmt.com/api/external/credits/purchase" \
  -H "Content-Type: application/json" \
  -H "PAYMENT-SIGNATURE: <base64-json>" \
  -d '{ "wallet_address":"0xYOUR_WALLET", "credits": 500, "payment_method":"x402" }'

2. Create a Session Nonce (nonce used in signed balance/invoke)

curl -s -X POST "https://www.agentpmt.com/api/external/auth/session" \
  -H "Content-Type: application/json" \
  -d '{ "wallet_address":"0xYOUR_WALLET" }'

3. Invoke This Tool

Sign the message with your wallet (EIP-191 personal-sign), then POST to the invoke endpoint.

# Sign this message (wallet MUST be lowercased):
# agentpmt-external
# wallet:0xyourwallet...
# session:<session_nonce>
# request:<request_id>
# action:invoke
# product:696ef640fb2f7d26fd1ef7ab
# payload:<sha256(canonical_json(parameters))>

curl -s -X POST "https://www.agentpmt.com/api/external/tools/696ef640fb2f7d26fd1ef7ab/invoke" \
  -H "Content-Type: application/json" \
  -d '{
    "wallet_address": "0xYOUR_WALLET",
    "session_nonce": "<session_nonce>",
    "request_id": "invoke-uuid",
    "signature": "0x<signature>",
    "parameters": {
      "action": "your_action",
      "your_param": "value"
    }
  }'

Actions(4)

search_titles^5cr4 params(1 required)

Search Wikipedia for article titles matching a query. Returns matching pages with title, description, and excerpt.

qrequiredstring

Search query string.

projectstring

Wikimedia project (e.g., 'wikipedia'). Must not be 'commons' for this action.

Default: wikipedia

languagestring

Language code (e.g., 'en', 'fr', 'de').

Default: en

limitinteger

Maximum number of results to return.

Default: 50

Range: 1 - 50

list_page_media^5cr3 params(1 required)

List all media files (images, audio, video) embedded on a specific Wikipedia page.

titlerequiredstring

Canonical page title (e.g., 'Solar_eclipse', 'Golden_Gate_Bridge').

projectstring

Wikimedia project (e.g., 'wikipedia'). Must not be 'commons' for this action.

Default: wikipedia

languagestring

Language code (e.g., 'en', 'fr', 'de').

Default: en

get_file^5cr3 params(1 required)

Retrieve detailed file metadata and URLs (original, preferred, thumbnail) for a specific media file.

file_titlerequiredstring

Full file title including the 'File:' prefix (e.g., 'File:Example.jpg').

projectstring

Wikimedia project. Set to 'commons' when the file is hosted on Wikimedia Commons.

Default: wikipedia

languagestring

Language code (e.g., 'en'). Required when project is not 'commons'.

Default: en

search_commons_media^5cr3 params(1 required)

Search Wikimedia Commons directly for media files (images, audio, video, SVGs). Supports pagination for browsing large result sets.

qrequiredstring

Search query string.

limitinteger

Maximum number of results to return.

Default: 50

Range: 1 - 50

offsetinteger

Pagination offset. Use the next_offset value from a previous response to get the next page.

Default: 0

Range: 0 - ...

Usage Instructions

Usage guidance provided directly by the developer for this product.

Public Commons Media Search

Name: Public Commons Media Search
Brand: Apoth3osis
SKU: 696ef640fb2f7d26fd1ef7ab
Price: 0.05 USD
Availability: InStock

Search Wikipedia and Wikimedia Commons to discover public media assets, find article titles, list media on pages, and retrieve file URLs with metadata.

Actions

search_titles

Search Wikipedia for article titles matching a query.

Required fields:

action: "search_titles"
q: Search query string

Optional fields:

project: Wikimedia project (default: "wikipedia"). Must NOT be "commons".
language: Language code (default: "en")
limit: Maximum results, 1-50 (default: 50)

Example:

{
  "action": "search_titles",
  "q": "solar eclipse",
  "language": "en",
  "limit": 10
}

Returns a list of matching pages with title, description, and excerpt.

list_page_media

List all media files (images, audio, video) embedded on a specific Wikipedia page.

Required fields:

action: "list_page_media"
title: Canonical page title (e.g., "Solar_eclipse")

Optional fields:

project: Wikimedia project (default: "wikipedia"). Must NOT be "commons".
language: Language code (default: "en")

Example:

{
  "action": "list_page_media",
  "title": "Golden_Gate_Bridge",
  "language": "en"
}

Returns a list of media items found on the page.

get_file

Retrieve detailed file metadata and URLs (original, preferred, thumbnail) for a specific media file.

Required fields:

action: "get_file"
file_title: Full file title including the File: prefix (e.g., "File:Example.jpg")

Optional fields:

project: Wikimedia project (default: "wikipedia"). Set to "commons" when the file is hosted on Wikimedia Commons.
language: Language code (default: "en"). Required when project is not "commons".

Example — Wikipedia file:

{
  "action": "get_file",
  "file_title": "File:Golden_Gate_Bridge_20100906.jpg",
  "project": "wikipedia",
  "language": "en"
}

Example — Commons file:

{
  "action": "get_file",
  "file_title": "File:Hubble_ultra_deep_field.jpg",
  "project": "commons"
}

Returns the file title, description URL, and links to original, preferred, and thumbnail versions of the file.

search_commons_media

Search Wikimedia Commons directly for media files (images, audio, video, SVGs). Supports pagination for browsing large result sets.

Required fields:

action: "search_commons_media"
q: Search query string

Optional fields:

limit: Maximum results, 1-50 (default: 50)
offset: Pagination offset (default: 0). Use the next_offset value from a previous response to get the next page.

Example:

{
  "action": "search_commons_media",
  "q": "northern lights aurora",
  "limit": 10
}

Pagination example:

{
  "action": "search_commons_media",
  "q": "northern lights aurora",
  "limit": 10,
  "offset": 10
}

Returns matching file titles, page IDs, and text snippets. Includes next_offset when more results are available.

Common Workflows

Find and download a Wikipedia image

Use search_titles to find the article (e.g., "q": "Eiffel Tower")
Use list_page_media with the returned title to see all media on the page
Use get_file with the desired file_title (include the File: prefix) to get the direct URL

Search Commons for stock-style media

Use search_commons_media with a descriptive query (e.g., "q": "sunset over ocean")
Pick a result and use get_file with project set to "commons" and the file title to get URLs

Browse media in another language

Set language to any valid code (e.g., "fr", "de", "ja") when using search_titles, list_page_media, or get_file with Wikipedia

Important Notes

The file_title parameter must always include the File: prefix (e.g., "File:Example.png").
The project parameter should be set to "commons" only for get_file when the file is hosted on Wikimedia Commons. For search_titles and list_page_media, use "wikipedia" (the default).
search_commons_media always searches Wikimedia Commons regardless of the project or language settings.
All media found through this tool is from Wikimedia projects and is generally available under open licenses (Creative Commons, public domain, etc.). Always check the file description page for specific license terms.
Results are capped at 50 per request. Use offset with search_commons_media to paginate through larger result sets.

About The Developer

Apoth3osis

★15 stars

Joined Agent Payment: August 14, 2025

We build tools that enable AI agents to excel in the mathematical realm.

Our small team develops experimental and unique solutions in the AI arena, with a strong focus on modular computing for agentic applications and custom model deployment. We have handled projects for a variety of applications across many sectors, from algorithmic trading and financial analysis, to molecular simulations and predictions, to habitat and biodiversity monitoring and wildlife conservation.

Public Commons Media Search

Description