Skip to main content
Glama
doitintl

DoiT MCP Server

Official
by doitintl

get_cloudflow_flow_run

Read-only

Retrieve a CloudFlow run's status and per-node input/output JSON to diagnose why a run failed or produced wrong data.

Instructions

Manage CloudFlow. Returns a run's status and, for each node, the JSON it consumed and produced. This is how you find out why a run failed, or that it "succeeded" while producing the wrong data.

input is null for most node types, and that is not an error. Only action nodes — the AWS, GCP, Azure, Oracle, DoiT and admin operations — record their inputs. Transform, code, branch, switch, datastore, subflow and trigger nodes record none, so their input is always null. output is recorded by every node that finishes, so read a transform's behaviour from its output.

Payloads appear as soon as a node reports a terminal status, so a poll loop can read results while later nodes are still running.

Any value the node's schema marks sensitive is replaced with a redaction marker; credentials and connection configuration never appear.

Each input and output is capped at 64KB. When a payload exceeds that, whole entries are dropped from the end, truncated is true, and totalBytes reports the untruncated size — nothing is silently cut, and what you receive is always valid JSON.

Runs belonging to another tenant, or to a different flow, return 404. Nodes inside a fan-out currently report only the last path to finish.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
runIdYes
flowIdYes
customerContextNoScope the request to a specific customer by ID. Required for DoiT employees (whose token isn't tied to a single customer); omit for direct customer users.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Addedv0.22.0

TDQS

A4.4/5.0
Behavior5/5

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

The description richly discloses behaviors beyond the readOnly/openWorld/destructive annotations: null input semantics for non-action nodes, payload visibility timing during polling, sensitive-value redaction, 64KB truncation behavior with `truncated`/`totalBytes`, 404 semantics for cross-tenant/cross-flow access, and the fan-out limitation. This is exemplary behavioral disclosure.

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?

Although long, every paragraph earns its place by covering a distinct behavioral concern: purpose, input/output semantics, timing, redaction, truncation, and error behavior. The description is front-loaded with the main purpose and uses bold formatting to highlight a critical non-error condition.

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 there is no output schema, the description thoroughly covers what the tool returns, how to interpret node input/output, pagination-like truncation behavior, redaction, and failure/error cases. It is sufficiently complete for an agent to invoke the tool and interpret its response correctly.

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

Parameters2/5

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

The schema only documents `customerContext`, leaving `runId` and `flowId` with no description and 33% schema coverage. The description does not compensate by explaining where these IDs come from, how they should be formatted, or how they relate to list_cloudflow_flow_runs. The parameter names are self-evident, but the description adds no parameter-level guidance.

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 quickly moves past the generic opener 'Manage CloudFlow' to a precise statement: it 'returns a run's status and, for each node, the JSON it consumed and produced.' It also establishes the tool's diagnostic role ('why a run failed'), which clearly distinguishes it from sibling list/detail tools like list_cloudflow_flow_runs.

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 phrase 'This is how you find out *why* a run failed, or that it succeeded while producing the wrong data' gives a clear, strong usage signal. It does not explicitly name alternatives or state when not to use it, but the context is clear enough for selection.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/doitintl/doit-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server