# Better Stack (slim)

> Better Stack is a hosted observability and incident management service from Better Stack, Inc. with uptime monitors, on-call, status pages, logs, metrics, traces and error tracking, reached through REST APIs and a remote MCP server.

- Full: https://www.anchorterminal.com/tools/better-stack.md (~9,500 tokens) · this version ~2,230 tokens · JSON https://www.anchorterminal.com/tools/better-stack.json · canonical https://www.anchorterminal.com/tools/better-stack
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-04 · pricing https://www.anchorterminal.com/tools/better-stack#pricing · reviews https://www.anchorterminal.com/tools/better-stack#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**C · 54.2/100 · rank #878 of 1349 · #9 in Observability & incidents · not agent-ready · confidence medium**


Assessment: One remote MCP server reaches incidents, on-call, monitors, status pages, logs, metrics, traces and errors with OAuth or a team-scoped token, and two headers cut its 148 tools down. Tool schemas and rate limits aren't published, there is no SLA, and audit logs of token use are a paid add-on.

## Facts

- Kind: MCP server · vendor: Better Stack, Inc. · category: Observability & incidents · legal entity: Better Stack, Inc. · provenance 89/100
- Endpoint: `https://mcp.betterstack.com` (Streamable HTTP)
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: Proprietary hosted service under the Better Stack Terms of Use. The Claude, Cursor and Codex plugins and the Terraform providers on GitHub are MIT
- Probe metrics: not measured yet (probes haven't run)
- Surface listed: The remote MCP server at mcp.betterstack.com, read from its docs page, the Claude plugin repository and the REST API docs for the Incidents, Telemetry and Usage APIs on 3 November 2026. No account was made, no tool was called and tools/list was not read
- MCP tools: 148 named on the docs page. On-call and escalation (10), incidents (12), monitors and heartbeats (13), status pages (21), catalogue (7), outgoing webhooks and Slack (8), telemetry queries, sources, dashboards, charts, alerts, explorations and metrics (52), error tracking (17), team management (5), documentation search and file upload
- Tool subsets: X-MCP-Tools-Only lists the tools to expose, X-MCP-Tools-Except removes some. Write tools need Full access at OAuth consent or a Read & write token
- REST APIs: JSON:API with a Bearer token. Incidents API at incidents.betterstack.com/api/v2 (monitors, heartbeats, on-call calendars, incidents, status pages, metadata, integrations, team members, roles), Telemetry API at telemetry.betterstack.com/api/v2 (sources, dashboards, explorations, alerts, connections), Usage API at betterstack.com/api/v2/usage, and a ClickHouse HTTP query endpoint with a username and password
- Credentials: Global API tokens valid across teams, or team-based Incidents and Telemetry API tokens, minted in Settings. The MCP docs distinguish read from Read & write tokens. OAuth for the MCP server with a Full access choice at consent
- Pagination: page from 1 and per_page up to 250 (default 50), with first, last, prev and next URLs in a pagination object. The Usage API is not paginated and spans at most 400 days
- Errors: 422 with errors keyed by field on creates, 401 with an errors string, 429 documented on the Usage API as wait and retry. No error code list and no Retry-After
- Rate limits: Not published. The terms say Better Stack may impose quotas and time limits
- Plugins and providers: Better Stack plugins for Claude (claude-plugin 1.3.12, 2 November 2026, 16 skills, MIT), Cursor, Codex and Antigravity, all pointing at mcp.betterstack.com, and Terraform providers terraform-provider-better-uptime and terraform-provider-logtail
- Status: status.betterstack.com with Better Stack, Uptime backend processing health and Telemetry components. Four Telemetry incidents and two maintenances between 5 August and 3 November 2026
- Plans: Free with 10 monitors, 3 GB of logs and traces, 30 GB of metrics and 100,000 errors a month. Responders $34 a month. Telemetry bundles from $30 (Europe), $45 (US) and $105 (Singapore) a month. Enterprise adds custom clusters, SAML and data residency
- Certifications: SOC 2 Type 2 per the security and enterprise pages, report on request under NDA. EU data centres described as ISO/IEC 27001 certified. GDPR compliant, not HIPAA. Data stored in EU regions by default
- Legal entity: Better Stack, Inc., a Delaware corporation, named in the terms (14 February 2025) and privacy policy (25 November 2022), under New York law. The careers page says the company was founded in 2021 with offices in Prague
- Prices: Responder seat $34 per seat per month; Logs and traces ingestion, Europe $0.10 per GB of traffic; Telemetry Nano bundle, Europe $30 per month (plan); Additional status page $15 per month (plan); Audit logs add-on $250 per month (plan)

- Scores: Reliability 50, Performance pending, Schema & documentation 46, Agent ergonomics 55, Security & auth 60, Payments & pricing 40, Task success pending, Maintenance & community 71, Transparency & trust 69 · total over the 7 assessed categories
- Why: Reliability, Read with the hosted lines and scored on the remote MCP server at mcp.betterstack.com, which fronts the same service as the Incidents and Te… · Schema & documentation, The server is closed and tools/list needs sign-in, so the tool schemas were not read, and no OpenAPI file was found for the REST APIs in the… · Agent ergonomics, 148 tools are named on the docs page, more than 30 (5). · Security & auth, OAuth sign-in with a Full access level chosen at consent, or API tokens that are global or scoped to one team with Read & write or read acce… · Payments & pricing, Read with the hosted rubric. · Maintenance & community, Read as a closed service. · Transparency & trust, Closed service under Terms of Use (14 February 2025) that name Better Stack, Inc., a Delaware corporation, under New York law.
- Sources: 28, open questions: 10, both in the full twin
- Capabilities: observability.logs, observability.incidents, work.oncall, observability.metrics, observability.traces, observability.errors
- JSON: https://www.anchorterminal.com/api/v1/tools/better-stack.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/better-stack.svg` or a link to https://www.anchorterminal.com/tools/better-stack from a page on betterstack.com or one of its subdomains, or the README at the root of github.com/BetterStackHQ/claude-plugin, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: hello@betterstack.com; https://betterstack.com/help; https://betterstack.com/docs/; more in the full twin

## Before you call it

1. Connect with `claude mcp add betterstack --transport http https://mcp.betterstack.com` and sign in, or send a team-based API token as `Authorization: Bearer`; pick Read access unless the task writes
2. Send `X-MCP-Tools-Only: monitors,monitor,incidents` or a similar list to keep the 148-tool list out of context, and `X-MCP-Tools-Except: remove_dashboard,remove_chart` to block deletes
3. Call `Get query instructions` or `Plan query windows` before `Execute query`, since long time ranges are split into windows and nothing documents a result size limit
4. No rate limit is published. Back off on a 429 and don't retry writes blindly, because there are no idempotency keys; `Upsert catalog records` is the one write documented as safe to repeat
5. Reopening an incident only works within 24 hours of its resolution, and a comment can only be edited or removed by its author or an API token

## Connect

```bash
curl -H "Authorization: Bearer $BETTERSTACK_API_TOKEN" https://incidents.betterstack.com/api/v2/monitors
```

```bash
claude mcp add betterstack --transport http https://mcp.betterstack.com
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/better-stack

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Grafana MCP Server | BB | 71 | observability.metrics, observability.logs, observability.traces, observability.incidents, work.oncall | https://www.anchorterminal.com/tools/grafana-mcp-server.min.md |
| Axiom MCP Server | B | 68.2 | observability.logs, observability.traces, observability.metrics, observability.incidents, observability.errors | https://www.anchorterminal.com/tools/axiom.min.md |
| New Relic MCP Server | C | 61 | observability.metrics, observability.logs, observability.errors, observability.traces, observability.incidents | https://www.anchorterminal.com/tools/new-relic.min.md |
| Datadog MCP Server | C | 56.8 | observability.metrics, observability.logs, observability.traces, observability.incidents | https://www.anchorterminal.com/tools/datadog-mcp.min.md |
| Causely MCP server | E | 39.5 | observability.incidents, observability.metrics, observability.logs, observability.errors | https://www.anchorterminal.com/tools/causely.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)