nebula-mcp

Overview Schema Source Related Servers Discussions Admin

nebula_execute_query

Read-onlyIdempotent

Execute one approved read-only GQL statement to produce configurable graph, chart, and analysis results with a human-readable explanation.

Instructions

Execute one approved read-only GQL statement. Graph, analysis, and charts are independently configurable and default to enabled. Present all enabled results together: render a non-empty cytoscape-elements-v1 graph, render every non-empty vega-lite-v5 chart, and write a human-readable explanation from explanation_context. A table does not replace charts or the explanation.

Input Schema

TableJSON Schema

Name	Required	Default
`graph`	No
`max_rows`	No
`statement`	Yes
`render_mode`	No	spec
`include_graph`	No
`include_charts`	No
`include_analysis`	No

Output Schema

TableJSON Schema

Name	Required	Description
`graph`	No	Render this Cytoscape graph when enabled and its elements contain nodes or edges.
`query`	Yes
`table`	Yes
`charts`	No	Render every Vega-Lite chart in this list when charts are enabled and the list is non-empty; a table is not a chart replacement.
`status`	Yes
`profile`	No
`analysis`	No	Deterministic facts about the bounded returned rows when enabled.
`truncation`	Yes
`explanation_context`	Yes	Use this evidence to write a human-readable explanation for every successful query.

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedv0.1.4Sep 30, 2026

addedOutput schema / $defs / ProfileOutput

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "latency_us": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Latency Us"
+    },
+    "operators": {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "title": "Operators",
+      "type": "array"
+    },
+    "truncated": {
+      "default": false,
+      "title": "Truncated",
+      "type": "boolean"
+    }
+  },
+  "title": "ProfileOutput",
+  "type": "object"
+}

addedOutput schema / $defs / QueryMetadata / properties / connection_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Connection Id"
+}

addedOutput schema / $defs / QueryMetadata / properties / display_statement

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Display Statement"
+}

addedOutput schema / $defs / QueryMetadata / properties / environment

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Environment"
+}

addedOutput schema / $defs / QueryMetadata / properties / executed_statement
```
Added value: +{
+  "title": "Executed Statement",
+  "type": "string"
+}
```

changedOutput schema / $defs / QueryMetadata / required

Previous value: -[
-  "statement",
-  "graph",
-  "validation"
-]New value: +[
+  "statement",
+  "executed_statement",
+  "graph",
+  "validation"
+]

addedOutput schema / properties / analysis / description

Added value: +"Deterministic facts about the bounded returned rows when enabled."

addedOutput schema / properties / charts / description

Added value: +"Render every Vega-Lite chart in this list when charts are enabled and the list is non-empty; a table is not a chart replacement."

addedOutput schema / properties / explanation_context / description

Added value: +"Use this evidence to write a human-readable explanation for every successful query."

addedOutput schema / properties / graph / description

Added value: +"Render this Cytoscape graph when enabled and its elements contain nodes or edges."

addedOutput schema / properties / profile

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/ProfileOutput"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

First observedv0.1.3Aug 31, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuine behavioral context beyond them: that graph, analysis and charts toggle independently, default enabled, and that a table must not be treated as a substitute for charts or the explanation. It does not mention pagination or row limits behavior.

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

Conciseness4/5

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

Front-loaded with the core action, then the configuration semantics. The third sentence about presentation is longer than strictly needed, but the instruction is actionable rather than filler.

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

Completeness4/5

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

An output schema exists so return values need no explanation, and the description covers the toggle defaults and expected output composition. Remaining gaps are the semantics of statement, max_rows, and render_mode, which are minor for this query tool.

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

Parameters3/5

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

Schema coverage is 0% across 7 parameters, so the description has to compensate. It clarifies the include_graph/include_charts/include_analysis toggles and their defaults, but leaves statement syntax, max_rows semantics, render_mode, and the purpose of the 'graph' string parameter unexplained.

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?

States a specific verb and resource (execute a read-only GQL statement) and implicitly routes away from the mutation sibling by emphasizing 'read-only' and 'approved'. An agent can distinguish this from nebula_execute_mutation without opening either schema.

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

Usage Guidelines4/5

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

The word 'approved' signals a workflow prerequisite (statements must be validated/approved first), and the description specifies how to present results once the query runs. It does not explicitly say when to prefer this over nebula_validate_gql or nebula_render_result, but the context is clear enough.

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

Deploy Server