The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
How I reduced our AI agent's input context by ~90%.
Before optimizing MCP in Webito, our agent received all 96 tools and their schemas upfront — around 13–14K input tokens before it could even start working.
I changed the MCP architecture so the agent first discovers available tools, then fetches the full schema only when it actually needs one.
Result: roughly 14K → 1.5K input tokens per iteration.
The interesting question is: what happens when you have 5,000 tools?
At that scale, semantic search starts making much more sense for tool discovery.
I wrote more about the architecture and trade-offs in my Medium article.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
AI Assistant Using Your Business Knowledge Base — RAG on Your Documents
THE PROBLEM
Q&A bots break down when knowledge lives in documents: a 100-page manual has no "questions" to match, it can't fit into a prompt, and generic chatbots hallucinate instead of admitting what they don't know.
THE SOLUTION
A RAG (Retrieval-Augmented Generation) knowledge base: documents are split into meaningful chunks, embedded into a vector index, and the assistant answers from the right sections — by meaning, not keywords.
Any format as-is: PDF, DOCX, TXT, Markdown — 100+ pages is fine
Answers grounded in YOUR documents — it says "I don't have that information" rather than inventing
Source references — every answer shows which document and section it came from
Runs on your infrastructure — documents never leave your control
One command to re-index after updating documents — documented, no programmer needed
LIVE DEMO
Ask it about my products, pricing, deployment and support — it answers from 6 real documents with sources:
https://kb-assistant-demo.dvc-ai.workers.dev
The 'I don't have that information' line is the part most RAG builds skip, and it's the one that matters. How do you set the cutoff? On mine, a fixed similarity threshold broke once I filtered results by user role. Scores shifted and it refused questions it could answer.
Every MCP server you connect costs tokens before it does anything.
We measured five browser MCP servers reading the same page (one URL, 18 Sep):
• chrome-devtools-mcp: 12,321 tokens
• Playwright MCP: 11,119
• read-website-fast: 4,938
• server-puppeteer: 2,871
• mcp-server-fetch: 1,298
The tool list alone costs 5,760 tokens for DevTools and 4,366 for Playwright the moment you connect, before a single call.
Why it matters: those tool definitions sit in context on every turn. Connect three heavy servers "just in case" and you pay for all of them on every message, in cost and in the model's attention.
The rule we now use:
• Reading a page: fetch.
• Driving a page (clicks, forms, flows): Playwright.
• Debugging runtime (console, network): DevTools, connected only for that task.
If you're building agents for clients, this is an easy win to check first: list what's connected, and cut what the task doesn't need.
The full pipeline in one view. Discover: AI-search gap scanning, opportunity discovery, cluster planning, 16 formats. Write: brand voice memory, citation architecture, FAQ blocks, image generation. Publish: native Webflow, WordPress and Shopify publishing, internal link weaving, SEO metadata and schema — plus multi-site support for agencies.
