Plexara
Learning / Plexara MCP
What is an MCP?
201 - Anatomy of a Plexara MCP
201 shows what is actually in the box on a Plexara server: the tools, resources, prompts, memory, and knowledge the agent sees. This lesson is the map.
202 - Your first day with Plexara
A new Plexara user gets connected, sends a first question, and platform_info takes over. Walks through day one and how subsequent turns inherit context.
203 - DataHub Search: describing the domain
Plexara enriches every query with semantic context, but a short prompt asking the agent to describe the domain first brings world knowledge to the session.
204 - Trino Query: analytics and insights
Plexara reaches customer data through Trino. What Trino is, how it maps to DataHub metadata, why OLAP queries finish fast, and how to export large results.
205 - Assets: dashboards, reports, and data
Plexara's asset system persists dashboards, reports, and exports outside chat. Naming asset tools in a prompt saves tokens and keeps outputs shareable.
206 - Knowledge: from memory to insights
Plexara ships session-coupled memory and a distinct insights pipeline that, once admin-reviewed, promotes observations into org-wide catalog documentation.
207 - Governance: personas, access, and audit
Governance in Plexara is enforced when a tool is invoked, not described in a policy. Personas, default-deny, layered safeguards, and a single audit log.
208 - MCP Prompts: reusable prompts
MCP prompts are reusable instructions for agents. Plexara ships a default library and adds user-, persona-, or org-scoped prompts through the Portal.
209 - MCP Resources: templates and examples
An MCP resource is reference material the server makes addressable by URI. Admins add them via the Portal or API so the agent can pull them into a session.
210 - Putting it all together: a worked end-to-end example
A capstone that walks a single real-world question through every Plexara subsystem covered in the 200 series, with a tool-by-tool reference at the end.