Analytics Legends — SAP AI & Analytics MCP Server

Traverse the learning knowledge graph

query_knowledge_graph

Read-onlyIdempotent

The RELATIONS between the platform's teaching objects — which Academy module teaches which concept, which study covers which module, what a concept relates to. THIS IS THE ONLY TOOL ON THIS SERVER THAT SERVES EDGES; the others serve rows. Ask it what connects to what, not what exists. SCOPE, AND IT IS NARROWER THAN 'the knowledge graph': it carries four node types — concept, module, study, vendor — and every edge whose BOTH endpoints are one of them. The whole graph holds twelve node types; the eight it does not carry are each either served by their own tool or named as not served at all, and _meta.excluded_node_types says which per type (consultant data is served at NO tier), so a missing type is a documented boundary and never a silent gap. Call it with node_id (e.g. module:M178, concept:C001, study:ai-impact-2026-EN) to walk one node's neighbourhood; with node_type and/or query to find a node id first. edge_type and direction narrow a walk. Read _meta.available_edge_types — computed from the served projection on every call — before assuming an edge type exists.

Input Schema

TableJSON Schema

Name	Required	Description
`lang`	No	ISO-639-1 language for the LABELS — en, fr or de. Defaults to en. The fallback is declared and never silent: the language asked for, then English, then French, and `_meta.label_language_coverage` says on how many nodes each language is actually filled. Concept and module titles carry French; German arrives as the corpus is translated, and an untranslated node falls back rather than being hidden.
`limit`	No	Max rows (hard cap 50).
`query`	No	Case-insensitive substring of a node's label. Applies to the NODE listing, not to a walk. Matched against the label SERVED, so it follows `lang`.
`cursor`	No	Opaque token from a previous response's `_meta.next_cursor`. Pass it back with the SAME filter arguments; `null` means the last page. Changing a filter refuses the cursor.
`node_id`	No	Fully-qualified node id, `<type>:<id>` — `module:M178`, `concept:C001`, `study:ai-impact-2026-EN`, `vendor:alteryx`. With it, rows are that node's EDGES (one row per neighbour). Without it, rows are NODES.
`direction`	No	Which side of the edge `node_id` must sit on. Default `both`. Ignored without `node_id`, and the response says so rather than pretending it applied.
`edge_type`	No	Restrict a walk to one relation. The authority is `_meta.available_edge_types`, computed on every call — no list is kept here: a four-name list once stood here while the projection served five, then a five-name list while it served six (`broader`).
`node_type`	No	Restrict to one carried node type: concept · module · study · vendor. Read `_meta.available_node_types`.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`rows`	Yes
`tool`	Yes
`_meta`	No
`_attribution`	Yes
`result_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 1, 2026

changedInput schema / properties / edge_type / description

Previous value: -"Restrict a walk to one relation. The served projection carries FIVE — teaches · taught_by · covers · related · mentions — and this list is a HINT, not the authority: read `_meta.available_edge_types`, computed on every call. A four-name list stood here while the projection served five, so `mentions` was reachable and undocumented."New value: +"Restrict a walk to one relation. The authority is `_meta.available_edge_types`, computed on every call — no list is kept here: a four-name list once stood here while the projection served five, then a five-name list while it served six (`broader`)."

Changed1 schema field changedSep 24, 2026

changedOutput schema / properties / rows / items / properties / direction / description

Previous value: -"`out` = node_id → neighbour, `in` = neighbour → node_id. Walk rows only."New value: +"`out` = node_id → neighbour, `in` = neighbour → node_id, `both` = the relation is stored in both directions (served once — see `_meta.symmetric_edges_folded`). Walk rows only."

Changed4 schema fields changedSep 3, 2026

addedInput schema / properties / lang

Added value: +{
+  "description": "ISO-639-1 language for the LABELS — en, fr or de. Defaults to en. The fallback is declared and never silent: the language asked for, then English, then French, and `_meta.label_language_coverage` says on how many nodes each language is actually filled. Concept and module titles carry French; German arrives as the corpus is translated, and an untranslated node falls back rather than being hidden.",
+  "pattern": "^[A-Za-z]{2}$",
+  "type": "string"
+}

changedInput schema / properties / query / description

Previous value: -"Case-insensitive substring of a node's label. Applies to the NODE listing, not to a walk."New value: +"Case-insensitive substring of a node's label. Applies to the NODE listing, not to a walk. Matched against the label SERVED, so it follows `lang`."

addedOutput schema / properties / rows / items / properties / label / description

Added value: +"In the language asked for when the node carries it, else the declared fallback — see `label_lang`."

addedOutput schema / properties / rows / items / properties / label_lang

Added value: +{
+  "description": "The language the served `label` is actually written in. It differs from the requested `lang` exactly when that translation does not exist.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

Changed1 schema field changedAug 27, 2026

changedInput schema / properties / edge_type / description

Previous value: -"Restrict a walk to one relation (teaches · taught_by · covers · related). Read `_meta.available_edge_types` — it is computed, never written here."New value: +"Restrict a walk to one relation. The served projection carries FIVE — teaches · taught_by · covers · related · mentions — and this list is a HINT, not the authority: read `_meta.available_edge_types`, computed on every call. A four-name list stood here while the projection served five, so `mentions` was reachable and undocumented."

Changed1 schema field changedAug 23, 2026

changedInput schema / properties / cursor / description

Previous value: -"Opaque token from a previous response's `_meta.next_cursor`. Pass it back with the SAME filter arguments to read the next page; a null `next_cursor` means you have reached the end. It is bound to those filters and refused if they change — a cursor names a POSITION in one ordering, and applying it to another query would start the page in the wrong place."New value: +"Opaque token from a previous response's `_meta.next_cursor`. Pass it back with the SAME filter arguments; `null` means the last page. Changing a filter refuses the cursor."

AddedAug 14, 2026

TDQS

A5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the read-only annotations, it discloses important boundaries: the four carried node types, eight excluded node types documented in `_meta.excluded_node_types`, consultant data served at no tier, and `_meta.available_edge_types` as the runtime authority. It also explains language fallback behavior and cursor reuse constraints, which are behavioral context not present in annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but appropriately so for a complex, multi-parameter traversal tool, and it is front-loaded with the core edge-vs-row distinction. Every major sentence appears to carry operational information, including scope boundaries, invocation modes, and dynamic meta fields.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, 8 parameters, full schema descriptions, annotations, and an output schema, the description is complete enough for correct invocation. It covers purpose, scope, alternatives, edge/node distinction, parameter intent, pagination, language fallback, and dynamic metadata without needing to describe return values already covered by the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds substantial meaning: node_id examples and its role in switching rows from nodes to edges, direction being ignored without node_id, query applying to node listings rather than walks, and lang affecting served labels with declared fallback. These details go well beyond the schema's field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

It states a specific verb and resource — traversing the learning knowledge graph for relations — and explicitly distinguishes this as the only tool on the server that serves edges rather than rows. The scope is narrowed to four node types and the contrast with 'what exists' tools makes the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells the agent exactly when to use it: 'Ask it what connects to what, not what exists,' and contrasts it with sibling node-serving tools. It also explains the two invocation modes clearly — walk via node_id or discover a node id first via node_type and/or query — and notes how edge_type and direction narrow a walk.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Analytics Legends — SAP AI & Analytics MCP Server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.