F
licenseA
qualityD
maintenanceEnables searching and analyzing AWS CloudWatch logs with support for configurable log groups, time-based searches, and service-specific log stream filtering.
5
-
mcp-syslog
by crunchtools
mcp-syslog-crunchtools
Servidor MCP para los logs recopilados por crunchtools/syslog.
Construido para RT #1460, para cerrar una brecha concreta: Nagios avisa a Hermes y Hermes puede reiniciar un servicio, pero no puede leer los logs del servicio — así que toda corrección es un reinicio a ciegas. Esto la convierte en una corrección informada.
Capacidades
Herramienta | Qué responde |
| ¿Qué puedo consultar? |
| Muéstrame los ERR de este servicio en los últimos 15 minutos |
| ¿Dónde aparece esta cadena en toda la flota? |
| ¿Cuáles son las líneas más recientes de este servicio? |
| ¿Qué decía todo alrededor de las 03:14? |
| ¿Qué servicio es el más ruidoso y cuál está realmente en mal estado? |
Related MCP server: Log Analyzer MCP Server
El bucle de triaje
nagios_current_problems_tool → what is broken
syslog_search_tool(source=…, → why it broke
severity="ERR",
since="15m")
syslog_context_tool(timestamp=…) → what else was happening at that moment
nagios_schedule_check_tool → confirm the fixsyslog_context_tool sin un source es el que justifica su valor. Abarca todas las fuentes
a la vez, que es como se conecta "la aplicación se ha caído" con "el contenedor de la
base de datos se quedó sin memoria (OOM) cuatro segundos antes".
Notas de diseño
Cada resultado está limitado y avisa cuando lo está. Los logs no tienen límite y esta salida va a parar a la ventana de contexto de un modelo. Cada herramienta limita sus resultados, limita cuántas líneas escaneará y anota la respuesta cuando se alcanza cualquiera de los límites:
[!] Stopped after the 2,000,000-line scan limit, so this result is INCOMPLETE
and an empty or short result does not mean nothing happened.Esa anotación es esencial. Quien realiza la llamada no sepa distinguir entre "no ha habido errores" y "he dejado de buscar" sacará una conclusión equivocada de un resultado vacío — y este servidor existe para fundamentar las decisiones de corrección.
El filtrado por tiempo es barato. El colector pone la fecha en el nombre del archivo, así que una consulta de diez minutos abre un solo archivo en lugar de leer noventa días de historial.
Los nombres de las fuentes no son fiables. Vienen de un modelo y se usan para
construir una ruta del sistema de archivos. Cada una se resuelve y luego se confirma
que sigue dentro de la raíz de los logs, lo que detecta el traversal de rutas, las rutas
absolutas y los enlaces simbólicos que apuntan fuera del árbol — ver
tests/test_security.py.
La severidad es "al menos este nivel". severity="ERR" devuelve ERR, CRIT, ALERT
y EMERG. Una severidad no reconocida se mantiene en lugar de descartarse, porque ocultar
una línea que no entiendes es peor que mostrarla — pero no se cuenta como error en
syslog_stats_tool, o un servicio sano reportaría una tasa de error del 57%.
La severidad no es maldad. Podman registra cualquier cosa que un contenedor escribe
en stderr con prioridad err, y no son pocos los servicios que registran ahí un INFO
rutinario. En lotor, mcp-trentina ronda el 65% de "ERR" mientras está completamente
sano:
PRIORITY=3 | 2026-08-23 15:55:24 INFO httpx: HTTP Request: GET https://... "200 OK"El colector es fiel al registro del journal; el journal está informando del descriptor de archivo. Lee el mensaje y prefiere un cambio en la tasa de errores a su valor absoluto. Esta misma advertencia está en las instrucciones MCP del servidor, para que un agente que lo consulte reciba exactamente esa indicación.
Se procesan dos formatos de línea. El colector emitía cinco campos antes de 2026-08-23 y seis después, y las líneas antiguas permanecen en retención durante 90 días. La disposición que usa una línea se decide según dónde se encuentre una severidad real, no contando campos.
Formato de logs
El colector escribe seis campos separados por espacios:
2026-08-23T15:41:52+00:00 crunchtools.com crunchtools.com httpd ERR AH00169: caught SIGTERM
└─ timestamp ───────────┘ └─ host ──────┘ └─ source ────┘ └prog┘ └sev┘ └─ message ────────┘source es el flujo de logs — normalmente un nombre de contenedor. program es
el proceso dentro de él, algo relevante para los contenedores systemd donde httpd,
php-fpm y mariadb se archivan bajo un mismo nombre de servicio.
Configuración
Variable | Predeterminado | Propósito |
|
| Raíz de logs, montada en solo lectura |
|
| Límite de entradas devueltas por llamada |
|
| Límite de líneas examinadas por llamada |
No hay credenciales: el servidor lee archivos de un bind mount de solo lectura.
Ejecución
podman run -d --name mcp-syslog \
--network crunchtools \
-p 127.0.0.1:8027:8027 \
-v /srv/syslog.crunchtools.com/data/logs:/logs:ro \
quay.io/crunchtools/mcp-syslog:latest \
--transport streamable-http --host 0.0.0.0 --port 8027Monta :ro. Este servidor nunca necesita escribir, y un montaje de solo lectura hace que
un error aquí no pueda destruir el registro forense que existe para proteger.
Desarrollo
uv sync
uv run ruff check src tests
uv run mypy src
uv run pytest -vAvailable Tools
6 toolssyslog_context_toolSyslog Context ToolA
Return log entries surrounding a specific moment.
Use this after an alert names a time. Omitting source spans the whole fleet, which is how a failure gets correlated with whatever else was happening.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum entries to return. | |
| source | No | Restrict to one source. Omit to span all sources. | |
| severity | No | Optional minimum severity. | |
| timestamp | Yes | The moment of interest — ISO-8601, or relative like '30m' ago. | |
| after_seconds | No | How far forward from the timestamp to include. | |
| before_seconds | No | How far back from the timestamp to include. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A3.8/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It does add real behavioral context — omitting 'source' spans the whole fleet, which is how correlation happens — but says nothing about ordering, whether the ±60s window is a hard bound, result caps, or that this is a pure read operation.
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?
Two sentences, zero filler, and the purpose is front-loaded before the usage cue. Every clause earns its place.
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?
An output schema exists and parameter coverage is complete, so return values and inputs need no explanation here. The description covers purpose and the key triggering context; the main remaining gap is the lack of any routing guidance relative to the five sibling syslog tools.
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%, so every parameter including the relative-timestamp format ('30m') and the before/after window defaults is already documented in the schema. The description only reinforces the 'source' omission behavior, adding no new parameter semantics.
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?
States a specific verb and resource ('Return log entries surrounding a specific moment'), which is a distinct capability from siblings like syslog_search_tool, syslog_grep_tool, and syslog_tail_tool. However, it never names or contrasts with those siblings, so the agent must infer the boundary itself.
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?
'Use this after an alert names a time' gives a concrete triggering condition, which is genuinely useful routing guidance. It stops short of stating when-not to use it or naming alternatives such as syslog_search_tool for non-time-anchored queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
syslog_grep_toolSyslog Grep ToolC
Regex search across all sources, or within one named source.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum entries to return. | |
| since | No | How far back to search — relative ('15m', '2h', '3d') or ISO-8601. | 24h |
| source | No | Restrict to one source. Omit to search the whole fleet. | |
| pattern | Yes | Case-insensitive regular expression matched against the message. | |
| severity | No | Optional minimum severity. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It implies a read-only regex search but discloses nothing about auth requirements, rate limits, result ordering, or the case-insensitive matching behavior, all of which the agent must infer or read from the schema.
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?
It is a single, front-loaded sentence with no wasted words. The brevity is appropriate for the core action, though for a five-parameter tool with no annotations it borders on under-specification.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The output schema covers return values and the input schema fully documents parameters, so those needs are met. The remaining gap is behavioral and sibling-routing context, which the one-sentence description does not supply for an unannotated search tool.
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%, so the baseline is 3. The description reinforces the source parameter by mentioning 'one named source', but adds no syntax, format, or default-value detail beyond what the schema already documents.
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 states a specific verb ('Regex search') and resource ('sources' / 'named source'), which is clear enough. However, it does not distinguish this tool from the sibling syslog_search_tool, leaving an agent to guess which search tool applies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'across all sources, or within one named source' implies a scope choice, but there is no explicit when-to-use, when-not-to-use, or named alternative. With a sibling search tool present, the lack of routing guidance is a clear gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
syslog_search_toolSyslog Search ToolC
Search collected logs by source, time window, severity and pattern.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum entries to return. | |
| since | No | Start of the window — relative ('15m', '2h', '3d') or ISO-8601. | 1h |
| until | No | End of the window. Omit for "up to now". | |
| source | No | Container or service name. Omit to search every source. | |
| pattern | No | Optional case-insensitive regular expression matched against the message. | |
| program | No | Restrict to one program within the source (e.g. 'httpd' inside a web container). | |
| severity | No | Minimum severity: EMERG, ALERT, CRIT, ERR, WARNING, NOTICE, INFO, DEBUG. 'ERR' returns ERR and anything more severe. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden of behavioral disclosure, yet it says nothing about read-only nature, result limits, ordering, or truncation behavior. It is implied to be a read/search operation but nothing confirms the safety profile or output behavior.
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?
A single efficient sentence with the key filter dimensions front-loaded and no filler. It is appropriately short for a broad search tool, though it is arguably too sparse to earn a 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists so return values needn't be explained, and the schema fully documents all seven parameters. The remaining gap is routing guidance among the many sibling log tools, which the description does not address.
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%, so both the description and schema document the parameters; the schema in fact adds far more (relative/ISO-8601 time formats, severity ordering, regex matching, program scoping). The description only names the filter dimensions already covered by the schema, so baseline 3 is appropriate.
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?
States a specific verb (search) and resource (collected logs) plus the filterable dimensions, so the purpose is unambiguous. However, it offers no differentiation from the many similar siblings (syslog_grep_tool, syslog_tail_tool, syslog_context_tool), leaving the agent to guess which search variant applies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use guidance and no mention of alternatives, despite a crowded sibling set of overlapping log-query tools. The agent gets no signal about when this broad search is preferable to grep, tail, or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
syslog_sources_toolSyslog Sources ToolA
List log sources available to query, with size and last-write time.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| pattern | No | Optional case-insensitive substring to filter source names. | |
| include_internal | No | Include the collector's own '_collector' statistics. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A3.5/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It implies a read-only enumeration and discloses returned metadata, but says nothing about permissions, cost, pagination, or whether hidden sources are omitted.
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?
A single front-loaded sentence with no filler; the action and the returned fields are stated immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists so return values need not be re-explained, and the two optional params are schema-documented. However, for a discovery tool in a six-tool family, the absence of any routing guidance to sibling tools leaves a real gap.
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%, so both parameters (pattern, include_internal) are already documented in the schema. The description adds no filtering or formatting detail beyond that 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?
States a specific verb (List) and resource (log sources), plus the metadata returned (size, last-write time), which distinguishes it from the search/grep/tail/stats siblings by resource type. It stops short of explicitly contrasting itself with any named sibling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
"available to query" implies this is a discovery step before using syslog_search_tool or syslog_grep_tool, but no alternative is named and no when-not-to-use condition is given. Usage must be inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
syslog_stats_toolSyslog Stats ToolA
Summarise log volume and error rate per source.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| top | No | How many sources to list, ranked by volume. | |
| since | No | Window to summarise — relative ('1h', '24h') or ISO-8601. | 1h |
| source | No | Restrict to one source. Omit to cover every source. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A3.6/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose the core behavior — aggregated volume and error-rate metrics keyed by source — which tells the agent this is a read/aggregate operation, but it says nothing about cost, permissions, or whether it scans the whole window, and there is no note that it does not return raw log lines.
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?
A single front-loaded sentence with no filler or repetition. It is efficient, though for a tool in a six-member family it is arguably thinner than ideal, which keeps it out of 5 territory.
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 values need not be explained, and the input schema is fully described at 100% coverage. The description supplies the aggregation semantics the structured fields cannot express, which is sufficient for an agent to call this low-complexity stats tool 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%, so 'top', 'since', and 'source' are already fully documented with defaults and formats. The description's 'per source' phrase loosely connects to the 'source' and 'top' parameters but adds no syntax, ordering, or edge-case meaning beyond the schema; baseline 3 applies.
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 names a specific verb (summarise) and resource (log volume and error rate), plus the grouping key (per source), so an agent can tell this is an aggregation tool rather than a content-retrieval one. It stops short of naming or contrasting any of the five syslog siblings (search, grep, tail, context, sources), so differentiation is inferred rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: the aggregation framing suggests using this for metrics overviews and the siblings for log content. There is no explicit when-to-use, when-not-to-use, or named alternative, so the agent must infer routing from the verb alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
syslog_tail_toolSyslog Tail ToolC
Return the most recent entries for one source.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of entries to return. | |
| source | Yes | Container or service name. | |
| severity | No | Optional minimum severity. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, yet it discloses almost nothing: it does not say whether it reads live/streams, the ordering of results, how 'minimum severity' is interpreted, or that limit defaults to 50. Only the read-like nature and recency scope are conveyed.
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?
A single short sentence with the resource and scope front-loaded and zero filler. It is efficient, though its brevity borders on under-specification rather than optimal conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values need not be explained, and the schema covers all parameters. However, for a no-annotation tool, key behavioral facts (live tail vs snapshot, ordering, severity semantics) remain undisclosed, leaving real gaps.
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%, so all three parameters (limit, source, severity) are already documented in the schema. The description adds no syntax or semantic detail beyond the schema, which is the baseline case.
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?
States a specific verb and resource ('Return the most recent entries') with a clear scope ('for one source'), which distinguishes it from search/grep/stats siblings by implication. It does not explicitly name an alternative, so it stops short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use guidance, no mention of when not to use it, and no reference to siblings like syslog_search_tool or syslog_context_tool. Only the phrase 'most recent' hints at its purpose, so usage must be inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
v0.1.0- First observed
syslog_context_tool - First observed
syslog_grep_tool - First observed
syslog_search_tool - First observed
syslog_sources_tool - First observed
syslog_stats_tool - First observed
syslog_tail_tool
TDQS
A3.5/5.0
Scored across 6 tools
Disambiguation4/5
Most tools target distinct operations: listing sources, tailing, stats, and context retrieval are clearly separated. However, syslog_search_tool (pattern search) and syslog_grep_tool (regex search across/within sources) overlap substantially and an agent could easily pick the wrong one for a pattern-matching query.
Naming Consistency5/5
All six tools use the identical syslog_<action>_tool convention, making the pattern predictable and easy to scan. The redundant '_tool' suffix is uniform, so it does not hinder consistency.
Tool Count5/5
Six tools is well-scoped for a log-query server, each covering a distinct access pattern (discovery, search, grep, tail, aggregate, context). No filler or redundancy beyond the search/grep overlap.
Completeness4/5
The surface covers the core log-investigation lifecycle: discovering sources, filtering, tailing, aggregating, and contextual surrounding entries. Minor gaps exist, such as no explicit pagination/offset control or config/retention management, but agents can work around these.
Maintenance
ActivityActive
ResponsivenessUnresponsive
Related MCP Connectors
Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Search log events, investigate anomalies, and manage cases in your Knowledge Grid tenant.
- SuperlogOAuthsh.superlog
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
Read-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables querying and analyzing logs from multiple remote Unix hosts via the Log Collector API, with tools for search, error detection, and summary generation.-
- FlicenseNot gradedqualityBmaintenanceProvides telemetry tools for retrieving recent logs and system metrics to support root-cause analysis of infrastructure incidents. Enables autonomous incident triage with grounded verification and human-in-the-loop remediation.1-
- FlicenseAqualityCmaintenanceEnables debugging of distributed transactions by continuously ingesting Docker container logs, indexing them by trace/request ID, and exposing MCP tools to search, tail, and correlate logs across services.7-