(magpie) branch main updated: docs(education): add MCP server to glossary (#1189)

[po...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

potiuk pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/magpie.git


The following commit(s) were added to refs/heads/main by this push:
     new 54a4627c docs(education): add MCP server to glossary (#1189)
54a4627c is described below

commit 54a4627cbce2af5fc81787521e06b9a5b3b1659f
Author: Pratiksha Badheka <pr...@gmail.com>
AuthorDate: Thu Sep 10 05:39:47 2026 +0530

    docs(education): add MCP server to glossary (#1189)
    
    * docs(education): add MCP server to glossary
    
    Why: the glossary defines Agent and Skill but never MCP server, even
    though skills rely on MCP servers to reach external tools like
    GitHub, Slack, and Gmail. Adds a plain-English definition consistent
    with the existing glossary style, placed after "Skill" since MCP is
    what a skill uses to act on the outside world.
    
    * docs(education):add 2 space in doc paraghraph
    
    why:make it proper style
    
    * chore(markdownlint.json):revert accidenlty markdown lintfile edit
    
    why: the file was accidently commited so revert it and commit with no functional change
---
 docs/education/README.md | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/docs/education/README.md b/docs/education/README.md
index 443a5617..596f90ba 100644
--- a/docs/education/README.md
+++ b/docs/education/README.md
@@ -59,6 +59,13 @@ New to AI, or to these words? Here is what they mean in Magpie:
 - **Prompt**: the written instructions you give the model.
 - **Skill**: a text file that tells the agent how to do one job, with
   instructions and examples. In Magpie, writing skills is the main work.
+- **MCP server**: a small running program that connects an agent to one
+  external service — like GitHub, Slack, or Gmail — using a shared set of
+  rules (the Model Context Protocol, or MCP) instead of custom one-off code
+  for each service. The agent acts as a *client*: it sends the MCP server
+  requests like "list open issues" or "post this message," and the server
+  carries that action out against the real service. Agents find the right
+  MCP server through a config file the runtime reads at startup.
 - **Deterministic and probabilistic**: normal code is *deterministic*, so the
   same input always gives the same result. An agent is *probabilistic*, so the
   same input can give slightly different results each time.