BroFindAI APIbrofindai.com ↗
Query 560+ curated AI tools and 320+ MCP servers from BroFindAI. Filter by category, pricing, platform, and tags via two clean endpoints.
What is the BroFindAI API?
The BroFindAI API provides two endpoints — search_tools and search_mcp_servers — that expose a directory of 560+ AI tools and 320+ Model Context Protocol servers. Each tool record includes category, pricing model, platform availability, vote count, and flags for API availability and open-source status. MCP server records include category, tags, and a direct URL sourced from the punkpeye/awesome-mcp-servers curated list.
curl -X GET 'https://api.parse.bot/scraper/f8a80747-1cc4-48d5-9a97-bdd9f8617759/search_tools?limit=5&query=writing&offset=0&category=Audio+%26+Voice' \ -H 'X-API-Key: $PARSE_API_KEY'
Typed, relational, agent-ready
A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.
- Fully typed · autocompletes
- Objects link to objects
- Typed errors & pagination
Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:
uv add parse-sdk uv run parse init uv run parse add --marketplace brofindai-com-api
uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.
"""Walkthrough: BroFindAI SDK — bounded, re-runnable; every call capped."""
from parse_apis.brofindai_com_api import BroFindAI, ToolCategory, InputFormatInvalid
client = BroFindAI()
# Search AI tools by keyword
for tool in client.tools.search(query="writing", limit=3):
print(tool.name, tool.category, tool.pricing)
# Filter tools by category
item = client.tools.search(category=ToolCategory.CODING_AND_DEV_TOOLS, limit=1).first()
if item:
print(item.name, item.url, item.tags)
# Search MCP servers
for server in client.mcp_servers.search(query="database", limit=3):
print(server.name, server.category, server.tags)
# Filter MCP servers by category
for server in client.mcp_servers.search(category="Browser Automation", limit=2):
print(server.name, server.description[:60])
# Typed error handling
try:
for t in client.tools.search(query="code", limit=3):
print(t.name, t.tagline)
except InputFormatInvalid as e:
print("invalid input:", e)
print("exercised: tools.search, mcp_servers.search")
Full-text search across 560+ curated AI tools. Matches against name, tagline, description, category, and tags. Results are ordered by votes descending. Each tool includes its category, pricing model, platform availability, and tags. Use offset and limit for manual pagination.
| Param | Type | Description |
|---|---|---|
| limit | integer | Maximum number of tools to return per page, between 1 and 100. |
| query | string | Search term matched against tool name, tagline, description, category, and tags. Omitting returns all tools. |
| offset | integer | Number of items to skip for pagination. |
| category | string | Filter by AI tool category. Omitting returns tools from all categories. |
{
"type": "object",
"fields": {
"count": "number of tools returned in this response",
"tools": "array of AI tool records with id, slug, name, tagline, description, url, category, pricing, votes, platform, has_api, opensource, and tags",
"total": "total number of matching tools across all pages"
},
"sample": {
"data": {
"count": 1,
"tools": [
{
"id": "61c4b3df-c8d9-4af1-8bb1-984c74cc1469",
"url": "https://copilot.microsoft.com/",
"name": "Copilot",
"slug": "copilot",
"tags": [
"coding",
"developer",
"llm",
"automation"
],
"votes": 0,
"has_api": null,
"pricing": "Paid",
"tagline": "Microsoft's AI companion powered by GPT-4 across all products",
"category": "Coding & Dev Tools",
"platform": [
"Windows"
],
"opensource": null,
"description": "Microsoft Copilot is an AI assistant integrated across Microsoft's ecosystem..."
}
],
"total": 88
},
"status": "success"
}
}About the BroFindAI API
AI Tool Search
The search_tools endpoint accepts a free-text query matched against tool name, tagline, description, category, and tags. You can also pass a category filter to narrow results to a specific segment. Results are ordered by votes descending and support manual pagination via offset and limit (1–100 per page). Each record in the tools array returns: id, slug, name, tagline, description, url, category, pricing, votes, platform, has_api, and opensource. The total field tells you how many tools match across all pages so you can calculate pagination yourself.
MCP Server Search
The search_mcp_servers endpoint covers 320+ open-source MCP servers. The query parameter matches against server name, description, category, and tags. The category filter accepts values like Databases, Browser Automation, or Coding Agents and is case-insensitive. Each record in the servers array returns name, description, url, category, and tags. There is no offset parameter on this endpoint — pagination is not supported here.
Data Coverage Notes
The search_tools endpoint exposes structured metadata that lets you distinguish free vs. paid tools (pricing), whether a tool exposes its own API (has_api), and whether it is open-source (opensource). These boolean flags make the endpoint useful for programmatic filtering beyond what the BroFindAI site UI surfaces. The MCP server dataset is explicitly sourced from a named public list (punkpeye/awesome-mcp-servers), so coverage reflects that curation.
The BroFindAI API is a managed, monitored endpoint for brofindai.com — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when brofindai.com changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official brofindai.com API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Build a tool recommendation widget that surfaces AI tools by category and filters out non-API tools using the
has_apiflag - Aggregate vote counts across categories to identify which AI tool segments are trending on BroFindAI
- Populate a developer resource page with MCP servers filtered to the
DatabasesorBrowser Automationcategory - Compare open-source vs. proprietary tool distribution within a specific AI category using the
opensourceandpricingfields - Search for MCP servers by tag or description keyword to find integration points for a given workflow
- Generate a curated newsletter section of top-voted AI tools by querying
search_toolswith no query and sorting by the defaultvotesorder - Build a filtering UI for LLM tooling choices by combining category, pricing, and platform fields from
search_tools
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 200 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
| Team | $300/mo | 20,000 | 300 req/min |
| Company | $1,000/mo | 100,000 | 500 req/min |
Each endpoint has a fixed posted price per successful call — most fall between 1 and 10 credits — shown on this API's page before you run it. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does BroFindAI have an official developer API?+
What does the `search_tools` endpoint return beyond a tool's name and description?+
pricing (the pricing model), platform (platform availability), votes (community upvote count), has_api (boolean indicating whether the tool itself exposes an API), opensource (boolean), category, url, slug, and tagline. Results default to descending vote order.Does `search_mcp_servers` support pagination?+
search_tools, the search_mcp_servers endpoint does not accept an offset parameter, so you cannot page through results in chunks. Use limit to cap response size, but you cannot retrieve subsequent pages. You can fork this API on Parse and revise it to add offset-based pagination if your use case requires it.Can I retrieve detailed changelogs, screenshots, or user reviews for individual tools?+
How do I filter AI tools to only those that are free and open-source?+
category parameter to narrow by domain, then filter the returned tools array client-side on the pricing and opensource fields. Both fields are present on every tool record returned by search_tools.