A platform lead connects the company's first agent to the semantic layer over MCP. The demo works. The agent lists the metrics, picks net revenue, and returns a number by region. Then someone asks which definition it used, who approved it, and whether the caller was allowed to see the refund detail. The semantic layer and MCP question starts there. The protocol carried the request perfectly. What came back is the subject of this article.
MCP, the Model Context Protocol, is the open standard for connecting an AI model to tools and data. A semantic layer MCP server exposes the layer's definitions as tools an agent can call. Every vendor on this query now ships one. They differ in what a tool call returns, and that difference decides what the agent can defend.
MCP standardizes the ask. The server decides the answer. A metrics-layer server returns a metric name, a description, compiled SQL, and rows. A governed-meaning server returns the definition, its owner, its version, the permitted joins, and the entitlement applied, with the number.
The MCP specification (revision 2025-06-18) defines a tool as a name, a description, an input schema, and an optional output schema. A call returns a content array and, optionally, a structured JSON object. That is the whole envelope. The protocol says nothing about what a metric is, who owns it, or whether it is current. Our post What Is a Semantic Layer? lists what a layer has to hold for an agent. MCP is how the agent asks for it.
| Part of the protocol | What the specification defines | What it leaves open |
|---|---|---|
| Tool definition | name, description, inputSchema, and an optional outputSchema | Whether the description is a typed sentence or a governed definition |
| Tool result | A content array, plus optional structuredContent that "MUST" match the output schema | Which fields are in it |
| Resource annotations | audience, priority, and lastModified, all optional | Who approved the content and whether it is still in force |
| Trust | Clients "MUST consider tool annotations to be untrusted unless they come from trusted servers" | Where the trust comes from |
Source: the specification's tools and resources pages. One catalog vendor's page on this query (published 2026-10-12) reads it the same way: "MCP standardizes how an agent asks a semantic layer for a metric. It leaves open which definition the agent should receive." That is correct. The page's remedy is a second MCP server, from that vendor, which picks the definition while the semantic layer's own server calculates it. In its words, "Neither server takes over the other's job." The open question is whether the definition and the calculation should have been two objects at all.
The four servers people search for with this term all document their tools. They describe one shape: a discovery tool that lists what exists, and a query tool that runs it.
| Server | Discovery tool | Query tool | What comes back |
|---|---|---|---|
| dbt MCP server (docs updated 2026-11-20) | list_metrics, which "Retrieves all defined metrics"; get_dimensions; get_entities | query_metrics, which "Executes metric queries with filtering and grouping options"; get_metrics_compiled_sql | Per dbt's launch post, "metric names, types, labels, and descriptions", then compiled SQL and results |
| Cube MCP server (read 2026-11-22) | searchDataModel, which returns "compact records (name, title, description, type)" | runQuery, which returns "a schema, a page of rows, and hasMore / totalRows" | Names, descriptions, rows. "Every tool runs as the authenticated user" |
| Snowflake-managed MCP server (read 2026-11-22) | One tool declared per semantic view; the server "only supports using semantic views" | A semantic view tool that "generates SQL from natural language text" | The SQL statement. Access needs "SELECT on Semantic View" |
| Databricks Genie Agent MCP server (Public Preview, 2026-10-23) | A Genie Agent of "up to 50 Unity Catalog tables, views, or metric views" | A plain-language question; "Genie writes and runs the SQL against that agent's tables and returns the result" | The result, "with Unity Catalog permissions enforced on every request" |
The open-source Boring Semantic Layer (version 0.3.19, released 2026-11-11) does the same inside a Python package, with tools for "Listing available models", "Getting model metadata", and "Querying models with dimensions, measures, and filters". Every one of these pages is accurate about what it ships. dbt adds that its MCP tools "can change without notice or a deprecation period. Don't treat them as a contract."
So the agent receives a name, a description somebody typed, a type, and either compiled SQL or rows. Our post Metrics Layer vs Semantic Layer: The Difference Is a Noun explains why that is the natural output of a layer built from metrics. A metrics layer can define a calculation. It cannot define a concept.
Picture the agent after the two tools return. It holds a metric named net_revenue, a description, and a table of numbers. Five things it needs are missing. The catalog vendor's page agrees on most of them: "MCP carries no field for staleness or certification."
meta key or a group setting, and changes to meta "don't trigger state:modified". The GraphQL Metric type carries a description and no owner field.lastModified is an optional annotation on a resource.The agent's side of this is our post A Semantic Layer for AI Agents: What the Agent Needs Before It Asks for Revenue. This article stays on the wire.
Here is the same request against a semantic layer built on an ontology, a formal model of the business's concepts and how they relate. The left column is assembled from the vendor tool docs above. The right column is what TopQuadrant's live agent-ready page says is served.
| Field | Metrics-layer server | Governed-meaning server |
|---|---|---|
| Name | net_revenue | Net revenue, a measure of the Order concept |
| Description | A free-text field | The agreed definition, the one its owner approved |
| Owner | A meta tag or group setting, if someone set it | A named person, on the record |
| Version and date | Git history, outside the payload | Version, status, and the date it last changed |
| Calculation | Compiled SQL | The same logic, held on the same governed asset as the definition |
| Mapping | Implicit in the SQL | Concept to table to column, "held as data you can query" |
| Permitted joins | Entities as join keys | Only modelled relationships; "the join paths available to them come from the ontology" |
| Entitlement | The warehouse grant of the signed-in user | Evaluated per request on the concept, for the identity the agent acts for |
| Record of the answer | Server logs, if kept | "the definitions resolved, their versions, the entitlements applied, and the data returned" |
The live page's own example: Active account, version 3, current: an account with at least one posted transaction in the trailing 90 days, excluding fee reversals and internal transfers. Owner, Retail Finance. Changed 2026-05-14. A BI pack, a dbt model, and an assistant over MCP all read it. Change it once and all three move.
That is the sentence the two-server architecture cannot write. Where the definition and the calculation are one asset, there is nothing left for a second server to choose. What the approval adds is covered in our post Ground Truth: SME-Approved vs Inferred Metadata. The MCP answer carries it.
dbt's own benchmark (dbt Developer Blog, 2026-04-07) makes the best case for a metrics-layer server: "the Semantic Layer tells you it can't answer. It never returns invalid data." The same page states the limit: the layer "can only answer questions that fall within the scope of what's been modeled" (dbt Developer Blog). A refusal is safe when the definition it refused on was the agreed one. Inside scope, the payload above is still what the agent gets. Our post Semantic Layer vs Text-to-SQL: What a Refusal Is Worth takes that question in full.
Connect a client, call the discovery tool, call the query tool, and read the raw result. Then ask five questions of the payload.
A server that passes all five is serving authoritative context: meaning that named people agreed to, in a form a machine can act on. The discipline behind that is our post Context Management: The Complete Guide. A server that passes none is a metrics layer with an MCP endpoint, which is fine for a dashboard.
TopQuadrant ships the governed record and serves it over MCP. Our agent-ready semantic layer page says what the agent receives: concepts, permitted relationships, and metric logic. The agent resolves what a term means before composing a query. Every metric and entity carries its business definition, its owner, its calculation, and its mapping to physical columns. Access rules attach to governed concepts and are evaluated per request against the identity the agent is acting for. Every served answer records the definitions resolved, their versions, the entitlements applied, and the data returned. It is also served over API and SPARQL.
AI proposes definitions and mappings, and your experts confirm them. Each definition is validated with SHACL, on open standards TopQuadrant helped author, so the whole record is yours to export. Your catalog stays, and it syncs.
MCP carries the request. TQ Data Foundation carries the record back with the number. That is what the agent actually receives.