Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | -61% | 0% |
| case-02 | ✗→✗ | ＝ Same ✗ | -11% | 0% |
| case-03 | ✗→✗ | ＝ Same ✗ | -36% | 0% |
| case-04 | ✗→✗ | ＝ Same ✗ | -11% | 0% |
A thin reference for the Atlas knowledge-graph MCP tool surface so any agent (including sub-agents) can query the graph without re-deriving conventions. The server URL is wired natively by the atlas plugin and is overridable via ATLAS_MCP_URL. Never invent node ids — only use ids returned by these tools.
> Position: this is the SECONDARY / enrichment layer. The atlas plugin is > scan-first — it inventories your REAL systems by scanning your actual sources > (Azure via read-only az, git repos, local directories) and process/data > mining them. The graph queries below are used ONLY to add best-practice / > comparison context to those already-discovered real systems. Do NOT use the > graph as the primary content, and never pad a real inventory with generic > catalog nodes. Tie every graph lookup back to a real scanned system.
mcp__atlas__atlas_public_searchFull-text/semantic search over the graph. Key params: q (query), optional kind filter, limit. Prefer it to find seed/anchor nodes from need terms.
mcp__atlas__atlas_public_recordFetch one node's full record by id (fields + edges). Use expandNeighbors to pull immediate relations in one call. Prefer it to read detail once you have ids.
mcp__atlas__atlas_public_neighborsTraverse the graph from a node. Key params: id, depth, edges (edge-kind filter), kinds (node-kind filter). Prefer it to expand a subsystem from anchors.
mcp__atlas__atlas_public_kindsList all node kinds in the graph. Use to scope a domain to relevant kinds.
mcp__atlas__atlas_public_kindDescribe a single node kind (schema/fields). Use before relying on a kind's shape.
mcp__atlas__atlas_public_edge_kindsList all edge kinds. Use to understand how nodes relate.
mcp__atlas__atlas_public_edge_kindDescribe a single edge kind. Use to interpret a specific relation type.
mcp__atlas__atlas_public_clustersList graph clusters (thematic groupings). Use to scope a domain to cluster(s).
mcp__atlas__atlas_public_statsGraph-level counts/metrics. Use for sizing and sanity checks.
mcp__atlas__atlas_public_wiki_pageFetch a narrative wiki page for context. Use to capture human-readable nuance.
atlas_public_search(q=<need terms>) → take top ids.atlas_public_neighbors(id, depth=2, kinds=[...]).atlas_public_record(id, expandNeighbors=true).atlas_public_clusters → pick cluster → search/neighbors scoped to it.
Other measured skills in the registry, with their headline benchmark lift.