MakerPerks MCP-AQL Adapter
Enables AI agents to browse and apply for builder perks (free credits, discounts, etc.) via a single semantic endpoint, with optional user-controlled autonomy for signups.
README
MakerPerks MCP-AQL Adapter
A native MCP-AQL server over MakerPerks — the browseable, agent-friendly directory of builder perks (free credits, discounts, and programs for startups, students, OSS maintainers, indie devs, and non-profits).
It exposes the whole directory (200+ programs) to an AI agent through one
token-cheap semantic tool (mcp_aql_read, ~120 tokens) instead of a wall of
discrete MCP tools — the operations are discovered at runtime via introspection.
That's ~95%+ fewer tool-registration tokens than a conventional "a tool per query"
server.
Connect
- Hosted (zero install): add
https://makerperks.mcpaql.comas a remote MCP connector (claude.ai, Claude Code, Cursor, …). OAuth registers automatically. - Local (stdio):
npm install && npm run build, then point your MCP client atnode dist/index.js.
Then call mcp_aql_read with { "operation": "introspect" } to discover the
operations: list_programs, get_program, search_programs.
How it works
- Native MCP-AQL READ surface over MakerPerks' published
perks.json— decoupled from MakerPerks (no fork divergence; updates flow on refresh). - stdio + Streamable HTTP transports over one transport-agnostic core.
- Hosted on Cloudflare Workers (web-standard Streamable HTTP), fronted by OAuth 2.1 + dynamic client registration so OAuth-mandatory clients connect. The endpoint is public and read-only.
Status
- Live: read adapter + dual transport + Cloudflare hosting + OAuth — done and
archived (
openspec/specs/). - Next — Stage 1: an application pipeline that drives the actual perk signups under a user-controlled autonomy switch. Tracked as GitHub issues (epic #22).
Documentation
CLAUDE.md— project configuration & conventionsdocs/ROADMAP.md— the staged plandocs/ARCHITECTURE.md— system model & MCP-AQL primitivesopenspec/specs/— the spec baseline (capabilities)
License
Code & schemas: AGPL-3.0 (commercial tiers available, like the rest of the MCP-AQL org). Docs: CC BY 4.0.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.