Intelligent API routing for AI agents. Best service, best price, free alternatives.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Inspect callable tools, capabilities, and parameters exposed to AI agents by Mcp Server.
executeRoute to the best service and make the API call. Returns result + metadata (service, cost, latency).
compareShow all available services for a capability with scores. See what's available before committing.
categoriesList all supported capabilities and their services.
Your agents overpay for every API call. We fix that.
Hebline routes every API call β including LLM calls β to the best service at the right price. Free when it's enough. Paid when it matters. It knows the difference.
Every other router earns a margin on your paid calls. Routing you to free alternatives kills their revenue. No margin on your API calls. Ever.
Your agents are bleeding money. One task triggers 5β10 paid API calls across different providers. No transparency, no cost control. Hebline fixes that:
Your agent connects to Hebline as an MCP server. Instead of calling APIs directly, it uses Hebline's tools β execute, compare, or categories. Hebline scores all available services, picks the best one, makes the call, and returns the result with full metadata.
| Tool | Description |
|---|---|
execute | Route to the best service and make the API call. Returns result + metadata (service, cost, latency). |
compare | Show all available services for a capability with scores. See what's available before committing. |
categories | List all supported capabilities and their services. |
Add to claude_desktop_config.json:
Add to .mcp.json:
Add to .cursor/mcp.json:
Add to ~/.codeium/windsurf/mcp_config.json:
Add to .vscode/mcp.json:
Set environment variables for any paid providers you want to use:
No keys? No problem β Hebline routes to free alternatives automatically.
| Category | Free | Paid (BYOK) |
|---|---|---|
| LLMs | Groq (Llama 3.3 70B), Google Gemini Flash | OpenAI GPT-4o-mini (OPENAI_API_KEY) |
| Geocoding | Nominatim (OpenStreetMap) | Google Maps (GOOGLE_MAPS_API_KEY) |
| Translation | MyMemory | DeepL (DEEPL_API_KEY), LibreTranslate (LIBRETRANSLATE_API_KEY) |
| Web Scraping | Fetch Scraper | Firecrawl (FIRECRAWL_API_KEY) |
| Currency | ExchangeRate-API | Fixer.io (FIXER_API_KEY) |
| OCR | OCR.space | Google Vision (GOOGLE_VISION_API_KEY) |
| Weather | Open-Meteo | OpenWeatherMap (OPENWEATHERMAP_API_KEY) |
| Web Search | DuckDuckGo | Brave Search (BRAVE_API_KEY) |
| News | HackerNews | NewsAPI.org (NEWSAPI_KEY) |
9 categories, 20 services. Free services work instantly β no API key needed. LLMs route through the Hebline proxy when no local key is set (50 free calls/day).
An agent asks: "Geocode the Brandenburg Gate in Berlin"
Hebline receives:
Hebline responds:
The agent got coordinates, knows it was free, and Hebline logged the call for future analysis.
Every API call is logged to ~/.hebline/calls.jsonl:
No content is logged β only metadata. This data will power Hebbian Learning in future versions.
Contributions are welcome! Adding a new adapter is straightforward β implement the ServiceAdapter interface and register it.
Built by Hebline β Route free first. Only pay when necessary.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/mcp-server-69)<a href="https://allmcps.com/mcp/mcp-server-69"><img src="https://allmcps.com/api/badge/mcp-server-69?style=directory" alt="Mcp Server on AllMCPs" /></a>