mcp-scalyr-dataset
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-scalyr-dataset count severity>=5 events for api hosts in the last hour"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-scalyr-dataset
Read-only MCP server for SentinelOne DataSet (formerly Scalyr) log search.
Agents can search_logs, count_logs, list_log_facets, and power_query without dumping raw API JSON, auto-paginating, or requiring Config/Write keys.
Requirements
Node.js
>= 20A Log Read Access token (the only required key / scope — Config Read and Write are never required)
Operator-set HTTPS region base URL
Related MCP server: Read-only Analytics MCP Server
Environment (mcp.json env)
Put secrets in your agent mcp.json — do not create a project .env for runtime secrets.
Variable | Required | Notes |
| yes | Log Read Access Bearer token |
| yes |
|
.env.example documents names/placeholders only.
Tools
Tool | Job | Annotations (R/D/I/O) |
| Small page of matching events (fenced pipe table) | T/F/T/T |
| Volume check ( | T/F/T/T |
| Top values for one field | T/F/T/T |
| PowerQuery table (requires an allowed | T/F/T/T |
Recommended workflow: count_logs or list_log_facets first, then a tight search_logs field clause (for example severity >= 5 or serverHost contains "api"). Do not treat a lone * as match-all. Use power_query with | group, | sort, | count(, | filter, | let, | join, or | timebucket — not | columns dumps.
Defaults: start_time=15m, end_time=0h, priority=low, max_count=25 (hard max 50). First-page relative windows are snapshotted to epoch-ms so page 2 can reuse them. search_logs prints more: yes and continuation_token only when the page is full; never auto-followed. cpu_ms is milliseconds from DataSet.
Install / run (local)
npm ci
npm run build
npm test
npm run test:connections # needs DATASET_* exported in the shellBinary after build: mcp-scalyr-dataset → dist/index.js (stdio).
mcp.json snippet (post-qc only)
Only wire this into Cursor after mcp-maker qc is not FAIL:
{
"mcpServers": {
"mcp-scalyr-dataset": {
"command": "node",
"args": ["/absolute/path/to/mcp-scalyr-dataset/dist/index.js"],
"env": {
"DATASET_BASE_URL": "https://app.scalyr.com",
"DATASET_READ_TOKEN": "your-log-read-token"
}
}
}
}Architecture
Hexagonal single package (ADR-001/002):
src/tools— inbound MCP adapterssrc/clients— outbound HTTP DataSet adaptersrc/adapters/outbound/memory+src/adapters/inbound/test— Cockburn pairsrc/application/src/domain— no MCP SDK or fetch imports
Security / residual risks
Log bodies are untrusted: allowlist → truncate → redact → untrusted fence
Secrets never in tool args, request bodies, stdout, or README examples that are real
HTTPS-only
DATASET_BASE_URL; no userinfo; tools cannot override itNo write/config/generic-HTTP tools
Residual lethal trifecta: private logs + untrusted text + agent tools — this server must not grow an exfil channel
Scripts
Script | Purpose |
| Compile TypeScript to |
| Compile tests + run node:test |
| Live smoke count (shell-exported env) |
| Hexagonal import boundaries |
Available Tools
4 toolscount_logsARead-onlyIdempotent
Volume check before search_logs. Returns count/filter/window/cpu_ms only — no event bodies.
Inputs: filter (required), end_time, priority, start_time.
list_log_facetsARead-onlyIdempotent
Top values for one field (hosts, files, severity). Use before narrowing search_logs filters.
Inputs: field (required), filter (required), end_time, priority, +2 more.
power_queryARead-onlyIdempotent
Run a DataSet PowerQuery (group, sort, count, filter, let, join, timebucket). Not for dumping raw messages — use search_logs for that. | columns alone is rejected.
Inputs: query (required), end_time, priority, start_time.
search_logsARead-onlyIdempotent
Return a small page of matching DataSet/Scalyr log events as a compact fenced pipe table. Prefer count_logs or list_log_facets first, then a tight filter. One page per call; use continuation_token for the next page (never auto-paginated).
Inputs: filter (required), columns, end_time, priority, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The four tools map to reasonably distinct jobs: facet discovery, volume counting, raw event retrieval, and aggregation. There is mild overlap — count_logs and power_query can both produce counts, and power_query can filter the same data search_logs filters — but the descriptions explicitly steer callers (e.g. 'not for dumping raw messages — use search_logs').
Three of four names follow a clean verb_noun pattern (search_logs, count_logs, list_log_facets) with a shared 'logs'/'facet' vocabulary. power_query deviates by naming a product feature rather than an action, but it is still readable and unambiguous.
Four tools is a lean but defensible surface for a log-query server covering discovery, counting, search, and aggregation. It sits slightly on the thin side — there is no schema/field-listing tool to support exploration — but no tool feels redundant.
Search, count, facet discovery, and aggregation with a continuation_token cover the core query workflow. However, list_log_facets requires already knowing a field name, and there is no way to enumerate fields/datasets or to fetch a specific event or surrounding context, which will cause dead ends for an agent exploring an unfamiliar dataset.
Maintenance
Related MCP Connectors
Query Honeycomb observability data: traces, events, metrics, SLOs, triggers, and boards.
Query Klaaro datasets, documents, and extracted records from any agent.
Query your own databases and Data Sets with read-only SQL, and build hosted dashboards.
Run SOQL queries to explore and retrieve Salesforce data. Inspect records, fields, and relationshi…
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables governed, read-only investigations of Amazon Athena access logs by searching exact user, IP, or correlation indicators and summarizing activity by correlation ID, with parameterized queries, validation, and result limits.MIT
- AlicenseNot gradedqualityCmaintenanceEnables analytics agents to run validated read-only SQL against a warehouse API with enforced row limits, required JSON responses, and secret-safe audit metadata.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to ask Purple AI hunting questions, run PowerQueries over the Singularity Data Lake, and read alerts, vulnerabilities, misconfigurations and asset inventory from a SentinelOne console, plus VirusTotal and public CVE lookups. It is read-only and accepts per-request console credentials, making it stateless and multi-tenant.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables read-only querying and server-side reduction of VMware Aria Operations for Logs (vRealize Log Insight) 8.18.x data, including event aggregation with spike detection, message signature grouping, and capped raw log search.MIT