MCP App StoreMCP App StoreBaidu Search adds real-time web and image search capability for Chinese-language content. It wraps the Baidu Qianfan API so an agent can query the Chinese web, retrieve web pages or images, apply time-based filters, and surface relevance and authority ratings alongside results.
Use this skill when an agent needs up-to-date information from Chinese-language sources, wants to perform image-based similarity searches, or must limit results by publish date. Ideal for news lookups, researching China-specific documentation, or collecting localized media.
Agents that can run shell commands and HTTP-backed tools (generic CLI agents, Python-based assistants, or any agent with network access).
Baidu Search skill provides Chinese web and image search via Baidu Qianfan API. The script is well-structured with proper argparse CLI, error handling for HTTP errors, and uses only stdlib (no external deps). It failed to run in test because BAIDU_QIANFAN_AK/SK env vars are required and not set, but the script gracefully exits with a clear error message. SKILL.md is written entirely in Chinese which limits accessibility. Architecture is basic — monolithic script with no references/ directory or progressive disclosure.
Clean skill — no security concerns. Uses stdlib only, no hardcoded creds, no destructive commands, no exfiltration. Network calls are only to Baidu's official API endpoints (aip.baidubce.com). The skill is niche (Chinese-language search) but legitimately useful for that audience. Architecture is flat — single script, no references/ or separation of concerns. SKILL.md lacks English documentation.
Gmail Automation via Rube MCP
Automate Gmail actions (send, reply, search, labels, drafts, attachments) through a Rube MCP Gmail toolkit with best-practice tool sequences and pitfalls noted.
Nano Banana 2 — Gemini 3.1 Flash Image Preview
Run Google Gemini 3.1 Flash Image Preview via inference.sh CLI: text-to-image, image editing, multi-image input, and Google Search grounding.
PDF Processing (OpenAkita)
Process PDFs: extract text and tables, merge/split/rotate pages, OCR scanned PDFs, manipulate metadata, protect or watermark files, and generate new PDFs progra
XLSX / Spreadsheet Skill
Handle creation, editing, cleaning, and conversion of spreadsheet files (.xlsx, .xlsm, .csv, .tsv) with robust formulas, formatting, and recalculation workflows
PPTX — Presentation (.pptx) Skill
Create, read, edit, and QA .pptx presentations: extract text, generate thumbnails, edit templates, and convert slides for visual QA and exports.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
FastAPI Project Templates
Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.
ClawPod / Massive Unblocker
Bypass anti-bot restrictions and fetch rendered HTML or structured search results via Massive's Unblocker API (handles CAPTCHAs, JS rendering, geo-restrictions)
Retriever (Membrane) Integration
Integrate with Retriever via the Membrane CLI to search, query, and proxy Retriever data (documents, snippets, queries) with built-in auth and pagination.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Integrated Finance (Membrane) Connector
Interact with Integrated Finance via the Membrane CLI to manage accounts, transactions, budgets, and reports; handles auth and proxy requests.
Scite Database (Smart Citations)
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.
