Skip to main content
Glama
Sign In
Constructor Research MCP

Constructor Research MCP

by NRGGIT
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

get_logs

Read-onlyIdempotent

Fetch up to 50 recent build or service log lines to diagnose failed starts, track build progress, and identify restart loops.

Instructions

Last lines (default 20, up to 50) of a build or service log: why a build or start failed, how far a long build got, what a starting service prints. Constructor serves logs only live: a build log while the build runs, a service log for its current container while it runs (both replayed from the start, then streamed). The MCP follows the builds and services it starts or shows and keeps their last 50 lines, so they stay readable after the build ends or the container restarts; anything else can be read only while it runs. When a new container starts, the lines of the one before stay, above a '--- new container' marker, and restarts_seen counts them: that answers whether a service keeps restarting and why. An empty service log on a running service usually means a crash loop.

Input Schema

NameRequiredDescriptionDefault
linesNoHow many of the last log lines to return.
image_idNoImage (build) ID: failure.image_id, or an image from get_deployment/list_images.
service_idNoService ID from get_deployment (services[].id).
deployment_idNoAll builds and services this deployment started.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare a safe, idempotent read; the description adds substantial operational context beyond them: live-only serving outside MCP-tracked builds/services, retention of the last 50 lines, replay-then-stream behavior, new-container markers with restarts_seen, and crash-loop interpretation. Nothing contradicts 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.

Conciseness4/5

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

Purpose and line limits are front-loaded, and nearly every sentence carries behavioral detail that cannot be inferred from annotations. The single dense paragraph is longer than ideal and would be easier to scan with structure, but there is no 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?

Covers live/retained behavior, container restarts, and the empty-log crash-loop edge case, which is impressive for a tool with no output schema. The one gap is deployment_id: the description never explains that passing it returns logs for all builds/services in a deployment, leaving that parameter's full effect to the schema.

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 100%, so the baseline is 3. The description reinforces default/max lines and speaks of build vs service logs, but it does not clarify how image_id, service_id, and deployment_id relate or whether they are mutually exclusive, so it adds little beyond the schema.

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 (last lines of a build or service log) and gives three concrete diagnostic use cases, which is enough to distinguish it from all deploy/start/stop/file-management siblings. An agent knows exactly what it retrieves without opening the 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?

Provides clear contexts for use—diagnosing failed builds/starts, measuring long-build progress, inspecting startup output—and explains live-only vs retained availability. It never names an alternative tool or an explicit when-not-to-use condition, so it is clear context without exclusion guidance.

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

Deploy Server

Other Tools