Log10x MCP Server

Official

by log-10x

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Retriever e2e probe

log10x_retriever_probe

Read-only

Probes the deployed retrieval pipeline end to end, checking offload, indexer, queues, pod readiness, query scans, S3 output, and event flow; returns a green/broken/unknown verdict with remedies.

Instructions

End-to-end probe of the deployed Retriever chain. Fires a synthetic query at the picked top-volume tenx_hash (or an explicit target_hash) and asserts every stage in order: offload bucket has recent data, indexer pipeline is running (kubectl logs grep for 'starting pipeline - Tenx: @/apps/retriever/index'), SQS subquery + stream queues drained (depth ≤ 10), retriever pod containers all ready, then submits the query and asserts CloudWatch scan complete events have matched>0, CloudWatch stream worker complete events exist, S3 qr//*.jsonl files were written, and the MCP returned events_matched>0 AND events_returned>0. Returns a structured verdict (green / broken / unknown) with per-assert observed + remedy. Call this as the post-install verify step (chained from log10x_advise_retriever step_verify) OR as a deep doctor diagnostic when log10x_retriever_query returns 0 events and the cause is unclear. Catches the silent-failure shapes that take hours to debug manually: indexer not booted, chart 1.0.20 / runtime-name stream pipeline launch failures, IRSA s3:PutObject misconfigured, MCP input_bucket misaligned with engine write location.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`namespace`	No	Kubernetes namespace where the retriever pod runs. Default: "log10x".	log10x
`target_hash`	No	Pre-picked tenx_hash to query for. When omitted, the probe queries the metric backend for the top-volume hash over the last 5 min.
`input_bucket`	No	S3 bucket where the retriever WRITES qr/<id>/*.jsonl result objects. Default: read from the resolved env-config's `retriever.input_bucket` (walking K8s ConfigMap → AWS SSM → GCP Secret Manager → Azure App Config → local file in that order). Falls back to LOG10X_RETRIEVER_INPUT_BUCKET / __SAVE_LOG10X_RETRIEVER_BUCKET__ env vars and the helm-release probe when no env-config is reachable.
`offload_bucket`	No	S3 bucket the receiver offloads data to (the bucket the retriever indexer reads from). Default: pick the `status="active"` entry from the resolved env-config's `offload_destinations[]` (walking K8s ConfigMap → AWS SSM → GCP Secret Manager → Azure App Config → local file in that order). Falls back to the LOG10X_STREAMER_BUCKET / LOG10X_OFFLOAD_BUCKET env var when no env-config is reachable. When the env var disagrees with the resolved value, the env var is ignored AND a stale-env-var warning is emitted on `envelope.warnings`.
`window_minutes`	No	Query window size in minutes. Default: 5.
`query_log_group`	No	CloudWatch log group the retriever writes per-query execution events to.	log10x-retriever-query-events

Output Schema

TableJSON Schema

Name	Required	Default
`data`	No
`tool`	Yes
`view`	No	summary
`images`	No
`actions`	No
`summary`	Yes
`warnings`	No
`truncated`	No
`next_cursor`	No
`render_hint`	No
`generated_at`	Yes
`schema_epoch`	Yes
`schema_version`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.30.7Sep 11, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly/openWorld/non-idempotent, but the description goes far beyond them: it enumerates each ordered assertion (bucket freshness, indexer pipeline, SQS queue depth ≤ 10, pod readiness, CloudWatch events, S3 files, MCP counts) and the verdict shape (green/broken/unknown with per-assert observed + remedy). It also discloses the failure classes it catches, rich behavioral context an agent cannot get from annotations alone.

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 purpose, then the assertion chain, then usage routing — logical order. It is dense and long for a single paragraph, but nearly every clause (the assertion sequence, the named failure shapes) carries selection or diagnostic value, with only mild redundancy between the assertion list and the 'catches silent-failure shapes' sentence.

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?

An output schema exists, so return-value detail is not required, yet the description still signals the structured verdict form. Combined with the explicit trigger conditions and full assertion coverage, an agent has everything needed to invoke and interpret this diagnostic correctly.

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 description coverage is 100% and the six parameter descriptions are already exhaustive (env-config resolution order, env-var fallback, stale-warning behavior), so the schema carries the load. The body adds only the conceptual note that target_hash defaults to top-volume and that bucket misalignment is a failure shape, which is marginal beyond the schema; baseline 3 applies.

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 (end-to-end probe) and resource (the deployed Retriever chain) with explicit scope, and it distinguishes itself from siblings by naming the exact stages it asserts. An agent can tell this apart from log10x_retriever_query, log10x_advise_retriever, and log10x_doctor without opening any schema.

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?

Explicit when-to-use: 'post-install verify step (chained from log10x_advise_retriever step_verify)' OR 'deep doctor diagnostic when log10x_retriever_query returns 0 events and the cause is unclear.' It names the triggering alternatives and the exact conditions that select each, leaving nothing to inference.

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

Deploy Server