Skip to main content

4 posts tagged with "mcp"

View all tags

MCP's Fix for Bloated Tool Catalogues Has a Bill Attached — And It's in the Docs, Not the Roadmap

· 8 min read
Rafael Fernandes
NLP Engineer & Tech Writer at WiLine
Share:
Protocols · AI NewsProgressive tool discovery and the provider prompt cache

The MCP maintainers' current roadmap names a problem most people building agents have felt without measuring: a server's tool catalogue is charged to the model before anyone asks a question. Under Improved primitives, the post is blunt about it — "Connecting to a server with a hundred tools means the model pays for that entire surface before the user has asked a single question, and tool selection tends to get worse as the list grows."

What makes this worth reading is not the roadmap. It's that the fix is already written down, in the client documentation, alongside a warning that it can cost more than the problem it solves — and that warning gets far less attention than the fix it qualifies.

LangChain Just Made MCP First-Class — We Ran It the Same Day, and Three Things Don't Work Yet

· 10 min read
Rafael Fernandes
NLP Engineer & Tech Writer at WiLine
Share:
Agent Frameworks · AI NewsMCP support lands in the main LangChain package

In July the MCP specification ripped out sessions. We wrote at the time that the change was infrastructure, not changelog — that a stateless core would let servers sit behind ordinary load balancers and survive redeploys, and that clients would need to catch up.

Today LangChain caught up. MCP support moved out of the separate langchain-mcp-adapters package and into langchain itself, rebuilt on FastMCP, with two features the old spec made impossible: elicitation as a LangGraph interrupt, and a cacheable tool catalog.

We installed it the same afternoon and pointed it at a server we wrote against the new spec. The announcement is accurate. The ecosystem around it is not ready — and one of the gaps quietly converts a human-approval gate into a sentence the model invents.

An agent can narrow its own web search, but never widen it

· 4 min read
Rafael Fernandes
NLP Engineer & Tech Writer at WiLine
Share:
Agents · AI News

Narrow only, never wider

Please use trusted sourcesTrusted sources are all there are

Your agent can search the web. You write in the prompt: only use sec.gov and the big financial wires. It usually listens. The times it does not are the times you learn that a line in a prompt is a request, not a rule.

On 19 August AWS added site filters to the web search tool in Bedrock AgentCore. Small feature. But the way it handles a disagreement is worth knowing, because that is what makes it a guardrail instead of a note.

MCP Just Shipped Its Biggest Update Ever — Here's What Actually Changes for AI Agent Engineers

· 5 min read
Rafael Fernandes
NLP Engineer & Tech Writer at WiLine
Share:
Protocols · AI NewsModel Context Protocol — the 2026-07-28 specification

The Model Context Protocol just had its biggest revision since launch. The 2026-07-28 specification doesn't add a feature — it rewrites how every MCP server talks to every client. If you've deployed an MCP server anywhere past "runs on my laptop," this one touches your infrastructure, not just your changelog.