mcp-syslog
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SYSLOG_LOG_ROOT | No | Collector log root, mounted read-only | /logs |
| SYSLOG_SCAN_LIMIT | No | Cap on lines examined per call | 2000000 |
| SYSLOG_MAX_RESULTS | No | Cap on entries returned per call | 200 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
MCP server for logs collected centrally from crunchtools infrastructure. Use this to find out WHY a service failed before deciding how to fix it.
A source is normally a container name. If you are unsure of the exact name, call syslog_sources_tool first — querying a name that does not exist returns an empty result that looks identical to a healthy service.
Typical triage: nagios_current_problems_tool to see what is broken, then syslog_search_tool(source=..., severity='ERR', since='15m') to see why, then syslog_context_tool around the failure time to see what else was happening.
IMPORTANT — severity is not the same as badness. Podman records anything a container writes to stderr at syslog priority 'err', and many services log routine INFO to stderr. So a source can sit at a 60% ERR rate while being perfectly healthy. Read the message text before concluding something is wrong, and prefer a change in the error rate over its absolute value.
Every tool bounds its own output and says so when a result is truncated or the scan limit was hit. Treat those notices as meaningful: an empty result from an incomplete scan is not evidence that nothing happened.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| syslog_sources_toolA | List log sources available to query, with size and last-write time. |
| syslog_search_toolC | Search collected logs by source, time window, severity and pattern. |
| syslog_grep_toolA | Regex search across all sources, or within one named source. |
| syslog_tail_toolB | Return the most recent entries for one source. |
| syslog_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. |
| syslog_stats_toolB | Summarise log volume and error rate per source. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct query mode: listing sources, filtered search, regex grep, tailing, contextual windows, and stats. The main overlap is between syslog_search_tool (severity/pattern) and syslog_grep_tool (regex), which an agent could confuse, but the descriptions draw a reasonable line between structured filtering and regex matching.
All tools follow a clear syslog_<action>_tool pattern, which is highly predictable. The action terms mix nouns (sources, stats) and verbs (search, grep, tail), a minor inconsistency within an otherwise uniform convention.
Six tools is well-scoped for a log query server, with each tool covering a genuinely distinct access pattern (discovery, search, grep, tail, context, stats). No tool feels redundant or vestigial.
The read-only query lifecycle is well covered: discovery, filtering, regex, recency, surrounding context, and aggregate stats. Minor gaps exist around schema/field discovery or export, but core investigative workflows are fully supported without dead ends.