RCA-MCP Connector

Overview Schema Source Related Servers Score Discussions Admin

rca_analysis_run

Run a synchronous root cause analysis using a registered model and return ranked root causes with confidence scores.

Instructions

Execute an RCA analysis using a registered model and return ranked root causes. This is the primary, synchronous analysis entry point -- it blocks until the model finishes. For a model that might take a while, use rca_analysis_run_async + rca_analysis_poll_task instead (Pro+); for multiple incidents through the same model in one call, use rca_analysis_batch instead (Starter+).

Args: params (RunAnalysisInput): - model_id: an existing model from rca_model_create - payload: family-specific dict -- shape depends on the model's family (see the payload field's own description for the exact keys each family expects) - save: persist the result for later retrieval via rca_analysis_get_result (default true; set false for a throwaway check you don't want cluttering your result list) - tags: optional labels for filtering later with rca_analysis_query_results - ai_summary: also generate a short NL executive summary (Starter+, quota-limited -- see field description)

Returns: str: JSON RCAResult with root_causes, confidence_overall, explanation, raw model output, _saved_as (the result_id) if save=true, and ai_summary/ai_summary_error if ai_summary=true was requested

Input Schema

TableJSON Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv4.1.17Sep 10, 2026

addedInput schema / $defs / RunAnalysisInput / properties / ai_summary

Added value: +{
+  "default": false,
+  "description": "Also generate a short plain-English executive summary via Claude Haiku (platform-provided key). Starter+ only, subject to a monthly quota (Starter 100, Pro 1000, Enterprise unlimited) -- see ai_summary/ai_summary_error in the response. Free plan or a used-up quota returns ai_summary_error instead of failing the analysis itself.",
+  "title": "Ai Summary",
+  "type": "boolean"
+}

Changed2 schema fields changedv4.1.15Sep 8, 2026
- addedInput schema / $defs / RunAnalysisInput / properties / client_id / description
```
Added value: +"Client namespace ID"
```
- addedInput schema / $defs / RunAnalysisInput / properties / token / description
```
Added value: +"API key to authenticate this request"
```
First observedv4.1.13Jul 27, 2026

TDQS

A4.7/5.0

Behavior4/5

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

The description adds behavioral context beyond the annotations: it blocks until the model finishes (synchronous), saves results by default, and explains that ai_summary is quota-limited with a graceful fallback. This is valuable since annotations only indicate it's not read-only and not destructive. No contradictions with the 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 well-structured with an Args section and a Returns section. The primary purpose and alternative routing are front-loaded, and every sentence adds information without redundancy or fluff.

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?

The description covers the essential aspects: the synchronous blocking behavior, alternative tools, parameter usage, and return format (including _saved_as and ai_summary fields). With an output schema available, this is complete for an agent to call the tool correctly.

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

Parameters4/5

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

The description adds meaningful context for parameters: 'save' is explained with a practical use case ('throwaway check'), 'ai_summary' gets quota and error-handling details, and the payload shape is deferred to the schema with a family-specific breakdown. This goes beyond the schema's descriptions and helps the agent decide how to use the tool.

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?

The description clearly states the action ('Execute an RCA analysis'), the resource ('using a registered model'), and the outcome ('return ranked root causes'). It explicitly labels itself as the primary synchronous entry point and contrasts with async and batch alternatives, making it easy to distinguish from siblings.

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?

Provides explicit guidance on when to use this tool vs. alternatives: 'For a model that might take a while, use rca_analysis_run_async + rca_analysis_poll_task instead (Pro+); for multiple incidents through the same model in one call, use rca_analysis_batch instead (Starter+).' This is clear, specific, and leaves no ambiguity.

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

Install Server