Skip to main content
Glama
compiuta-origin

Connhex MCP Server

Official

Read Thing Messages

read_thing_messages
Read-only

Retrieve telemetry, settings, or metadata from a Connhex device using its unique thing ID. Supports time-range filtering, decimation, and multiple data formats.

Instructions

Read messages for a Connhex thing (device/edge), identified by its thing ID. Resolves the thing's event_channel_id from its metadata and reads messages from it.

Resolving a user-facing identifier: If you only have a serial number or another business identifier, first use list_resources / list_manufacturing_resources to find the record, then look for a field named connhexId (or similar) — that value is the thing_id to pass here, not the record's own id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dsNoDecimation granularity, format "<number><s|m|h|d|w|M|y>" (e.g. "5m", "1h", "1d"). When set, the upstream service buckets messages and aggregates them with dsf. Only applies to SenML-based formats ("messages", "params", "metrics").
dsfNoAggregation function for decimation: max, min, avg, sum, stddev, variance. Defaults to "avg" upstream.
dsvNoDecimation value type: "v" for numeric SenML values, "vb" for boolean. Defaults to "v" upstream.
nameNoSenML name (metric URN) filter. Only applies to SenML-based formats ("messages", "params", "metrics"). Ignored for "infos".
to_sNoEnd time in Unix epoch seconds. Always provide from_s and to_s together when the requested time range is known; this drastically speeds up database queries. The integer part represents whole seconds; the fractional part provides sub-second precision (e.g. 1744243200.183767).
limitNoMax messages to return (upstream max is 1500).
formatNoWhich Connhex Message Policy (CMP) component to read. "messages" (default): time-series sensor data collected during operation (e.g. temperature, pressure). SenML format. Most common format — use for actual measurements or telemetry. "params": runtime-editable configuration parameters of the device (e.g. operating mode, thresholds). SenML format. Use to inspect or verify device settings. "infos": static or rarely-changing device metadata sent at boot or after firmware updates (e.g. serial number, firmware version, hardware revision). JSON format (not SenML). Use to identify or describe the device. name, ds, dsf, and dsv do not apply to this format. "metrics": internal device performance indicators (e.g. CPU usage, RAM consumption, uptime). SenML format. Use for device health monitoring and diagnostics.messages
from_sNoStart time in Unix epoch seconds. Always provide from_s and to_s together when the requested time range is known; this drastically speeds up database queries. The integer part represents whole seconds; the fractional part provides sub-second precision (e.g. 1744243200.183767).
offsetNoPagination offset.
thing_idYesThing ID (UUID). This is the value of the Connhex ID field on the resource or manufacturing record — not the resource's own id.
publisherNoPublisher UUID filter.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitYes
totalYes
offsetYes
messagesNo
Behavior4/5

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds behavioral context: it resolves event_channel_id internally, reads messages, and notes performance implications of combining from_s and to_s. No contradictions.

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?

Description is well-structured with two paragraphs: main purpose followed by identifier resolution guidance. Parameter descriptions are thorough but within the schema. No fluff, though slightly long.

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 (11 parameters, output schema, annotations), the description is comprehensive. It covers main use case, parameter details, performance tips, and identifier troubleshooting. No gaps.

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?

Schema coverage is 100%, and the description adds significant value: format parameter has detailed explanations of each enum option, thing_id clarifies it's the connhexId, and from_s/to_s include performance advice. Exceeds baseline.

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

Purpose4/5

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

The description clearly states the tool reads messages for a Connhex thing by thing ID. It explains the resolution of event_channel_id from metadata. However, it does not explicitly differentiate from sibling tools like read_channel_messages, but the internal resolution step provides implied distinction.

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?

Provides explicit guidance on resolving user-facing identifiers before using the tool, and advises providing from_s and to_s together for performance. Does not mention alternatives or when not to use, but the context is clear.

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/compiuta-origin/connhex-tools'

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