Skip to main content

6 posts tagged with "AI-Agent"

View all tags

Save 70% of Your AI Coding Plan Quota by Replacing ZhiPu Search with Tavily MCP

· 3 min read

When using ZhiPu GLM Coding Plan with Claude Code, I noticed my monthly quota draining faster than expected. The culprit? Built-in MCP tools — web-search-prime and web-reader — were consuming coding conversation quota for every web search and page fetch.

TL;DR

Replace ZhiPu's built-in web-search-prime and web-reader MCP services with Tavily MCP. Result: free 1000 searches/month with zero impact on coding quota.

Build a Custom MCP Toolkit with Python FastMCP to Connect Any AI Model

· 8 min read

While building AI Agent systems for clients, we found that different tasks require vastly different model capabilities and costs: vision models for image analysis, lightweight models for text completion, and local models for internal data queries. MCP (Model Context Protocol) turns each capability into an independent tool that AI clients invoke on demand.

TL;DR

Build a custom MCP Server in 30 minutes with Python FastMCP, connecting any OpenAI-compatible API based on scenario and cost. This article demonstrates the full workflow using the Doubao vision model, with extension templates for text generation, image generation, TTS, and more.

Unify Multiple Search APIs with Abstract Class, Return Errors Instead of Raising

· 4 min read

Encountered this issue while building an AI Agent platform for a client: needed to support multiple search providers (Tavily, Serper, Brave, Bing) while ensuring tool call failures don't interrupt the Agent's conversation flow.

TL;DR

  1. Define SearchProvider abstract base class + SearchResult data model for unified interface and output
  2. Each provider inherits the base class, implements search() method with field mapping
  3. Key design: Return SearchResult with error info on failure, never raise exceptions

Bypass Supabase Auth for Playwright E2E Testing Without Login

· 4 min read

Encountered this issue while building an AI Agent SaaS platform for a client. Here's the root cause and solution.

TL;DR

E2E tests shouldn't depend on real OAuth login flows. By detecting localStorage test markers in the useAuth hook, you can inject mock auth state directly and skip Supabase initialization. Also change the Zustand store's loading default to false to prevent AuthGuard from showing an infinite spinner.