MCP lets AI assistants query publishers directly, no central index needed
Is MCP becoming the common foundation of smart, decentralised search?
Instead of copying the web into one index, MCP lets each publisher keep its data at home and expose it through its own server, which assistants query on demand at the moment of a question. The protocol, launched by Anthropic in November 2024 and now under the Linux Foundation's Agentic AI Foundation, returns answers with source, licence, author and update date attached. Contexte Tech demonstrates this with an open MCP server for its catalogue of European public datasets, prompts and tools.
MCP does not replace the web: it gives assistants a way in.
- randomblock1
No, because HTTP already is. You can't have every MCP added. Every harness has a search tool, so just fetch data as needed. MCP isn't for search, it's for interacting. Sometimes that's search but mostly not.
- brap
For web services, what is the point of MCP or even a skill when modern agents can just find API docs on their own and use it?
I think in this day and age agents no longer need official 3P integrations, they can just use whatever API is already available (and in some cases even the UI).
- hobofan
> Three things still have to be built, server by server
> citation
Nope, as long as the MCP server exposes enough metadata to be cited (mostly trivial), citation is a job of the client/LLM.
> trust
Also just a function of the client. The server can't aid here at all as it's inherently untrustworthy in the system.
> measurement
Maybe. Though it's debatable how much measurement _each_ server needs, and whether that actually gives meaningful insight to optimize. This might as well be measured outside of the servers, in the client/a centralized logging system that also sees surrounding context.