Head to head · Incidents · October 2026 research run

Better Stack vs PagerDuty MCP Server

Better Stack scores 54.2 (C) on agent readiness against PagerDuty MCP Server's 48.6 (D), and leads in 4 of 7 scored categories. PagerDuty MCP Server leads on schema & documentation and security & auth. Both do incidents.

Best observability and incident tools for AI agents · All 49 observability comparisons

Which one, for what

Better Stack C

Best for An agent that investigates incidents, queries logs and metrics with SQL, manages monitors and posts status page updates for a team already on Better Stack, with the Claude plugin as the shortest route.

Ahead on

  • Agent ergonomics, 55 against 49
  • Payments & pricing, 40 against 10
  • Maintenance & community, 71 against 32

Watch for

No rate limit numbers in the API docs, and the only 429 guidance is to wait before retrying

PagerDuty MCP Server D

Best for Incident and on-call agents in PagerDuty shops.

Ahead on

  • Schema & documentation, 55 against 46
  • Security & auth, 66 against 60

Watch for

No read-only mode on the hosted server, where the local one was read-only by default

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community Better Stack +39

Better Stack 71

Read as a closed service. The Claude plugin reached 1.3.12 on 2 November 2026 and the changelog's newest entry is 29 October 2026 (30). Changelog entries on 10 August, 9 September, 1 October, 15 October and 29 October 2026 (20). Public changelog, hello@betterstack.com with a stated reply within a few hours, and a community site. GitHub issues on the plugin repositories were not read (10 of 15). The MCP server is not in the official MCP registry under a verified namespace, the only entries matching the name being third-party scrapers, and there is no official API SDK. The Claude, Cursor, Codex and Antigravity plugins and two Terraform providers are current (5 of 15). The Claude plugin repository is MIT with 12 commit days since June 2026, and we didn't read its CI (6 of 10). 30 + 20 + 10 + 5 + 6 = 71.

PagerDuty MCP Server 32

No hosted changelog. The local server's last version bump was 1.1.0 on 7 July 2026, 86 days before this check (20). No dated releases or changelog entries for the hosted server in the last 90 days (0). Closed service with no public changelog. Support runs through PagerDuty's knowledge base and support desk (5). The official registry entry io.github.PagerDuty/pagerduty-mcp is still version 0.2.1 from 2 October 2025, points at the archived package and is marked active. The hosted server isn't registered (5). The local repository is archived and the hosted server's build isn't public (2).

Payments & pricing Better Stack +30

Better Stack 40

Read with the hosted rubric. No x402, MPP or L402 (0). Per-unit prices are public without login, by GB and region for telemetry, per responder, per status page and per phone number (20). The Free plan has 10 monitors, a status page and 3 GB of logs, the signup page says Sign up for free and names no card, and we did not run the signup flow (20). A person signs up in a browser and mints a token or completes OAuth there (0). 0 + 20 + 20 + 0 = 40.

PagerDuty MCP Server 10

No x402, MPP or L402 (0). Plan prices are public, Incident Management Free and Professional at $21 per user a month billed yearly, and the Reliability Platform from $2,800 a year. No per-call price and no statement that MCP costs nothing extra (10). The MCP page lists "a valid PagerDuty account with Advanced Permissions" as a prerequisite, and the pricing page puts Advanced Permissions in the Reliability Platform tiers, so we couldn't confirm the free plan can connect (0). A person signs up and creates a key or an OAuth client (0).

Schema & documentation PagerDuty MCP Server +9

Better Stack 46

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 docs, the GitHub organisation or a search. Partial credit for a typed contract that exists but isn't public (10 of 25). No llms.txt on betterstack.com or its docs, and no Markdown twins (0). The MCP docs page gives one line per tool and says when some apply, such as Reopen incident within 24 hours and the instruction tools to call before Execute query. The REST reference pages describe each endpoint in a sentence (12 of 20). Inputs are typed only in the REST docs, with parameter tables, monitor types and status values listed in prose, and no schema to validate against (7 of 15). Every REST page carries a curl example and a 200 body; Create monitor documents a 422 with errors keyed by field, the Usage API a 401 and a 429, and no error code list exists (9 of 15). The APIs are versioned v2 in the path. The changelog is a product feed of 19 entries since March 2025 with the MCP server among them, with no API changelog and no deprecation notes (8 of 15). 10 + 0 + 12 + 7 + 9 + 8 = 46.

PagerDuty MCP Server 55

The hosted tool list and schemas aren't published. The docs say to call tools/list, and point at an MCP API reference on the developer portal we didn't read. The archived local server it replaced had typed Pydantic inputs, flattened in 1.0.0 to remove $ref (15). llms.txt and Markdown docs at docs.pagerduty.com (10). The local server's docstrings list each argument and its allowed values in prose, and we can't confirm the hosted text matches (10). Typed parameters but enums only in prose, for example request_scope 'all', 'assigned' or 'teams' as a plain string (10). The local repository had a per-domain tool reference with examples, retired with the archive (7). No changelog for the hosted server. The local CHANGELOG had one entry (3).

Agent ergonomics Better Stack +6

Better Stack 55

148 tools are named on the docs page, more than 30 (5). X-MCP-Tools-Only and X-MCP-Tools-Except narrow the list to a subset or a read-only set, documented for that purpose, and the server has no default toolset (add 10, so 15). REST lists take page and per_page up to 250 with first, last, prev and next links, and filters by url, pronounceable_name and team_name. Plan query windows splits a long telemetry query into windows, and Execute query takes SQL with its own LIMIT. No field selection (16 of 20). 422 bodies name the field that failed and 401 gives a message, but no error code list exists and MCP errors are not documented (10 of 20). No idempotency keys. Upsert catalog records avoids duplicates, Reopen incident is limited to 24 hours, and the annotations on the tools couldn't be read (6 of 20). Get workspace style defaults are not described. Two Terraform providers and logging clients exist, but no official API SDK in any language, and the Claude plugin's 16 skills carry the query recipes (8 of 15). 15 + 16 + 10 + 6 + 8 = 55.

PagerDuty MCP Server 49

The hosted docs describe about 16 tool groups without counts. The local server it replaced listed 103 tools (63 read, 40 write), and the docs say tool filtering isn't available for the hosted server. Scoped OAuth makes calls fail rather than shrinking the list (5). Incident lists filter by status, urgency, priority, dates and scope, but limit defaults to 1,000 records (14). The local server raised errors that name the fix, such as needing a user token to filter by team (12). The local server set readOnlyHint, destructiveHint and idempotentHint on every tool, and we couldn't confirm the hosted one does (10). Few required parameters (8).

Security & auth PagerDuty MCP Server +6

Better Stack 60

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 access, minted and deleted in Settings. No scopes finer than read and write, no expiry and no PKCE or dynamic registration documented (24 of 30). Read-level tokens and consent, the two header allowlists, and the rule that comments can only be changed by their author or a token. No confirmation step before Remove monitor, Remove dashboard, Resolve incident or Remove team member (12 of 20). Logs, spans, errors and replays are untrusted text returned to the model, and no injection guidance was found in the MCP docs (2 of 15). Audit logs record every API token request with actor_type api_token and the token's name, never its value, and can be streamed to a Telemetry source or any URL, though the pricing page lists audit logs as a $250 a month add-on (12 of 15). SOC 2 Type 2 with the report on request, third-party penetration tests, security@betterstack.com for disclosures. No security.txt (404), no bug bounty and no disclosure policy page (10 of 20). 24 + 12 + 2 + 12 + 10 = 60.

PagerDuty MCP Server 66

OAuth with metadata discovery and static client credentials, no dynamic client registration. Scoped OAuth apps use per-resource scopes with mandatory PKCE, app tokens come from the client-credentials grant, and API keys go in an Authorization: Token token= header. No secrets in URLs (28). The local server was read-only unless --enable-write-tools. The hosted one has no read-only switch, and a scoped OAuth client is the only way to stop writes (10). Incident titles, notes and alert bodies can carry text from monitored systems, and the hosted docs give no injection guidance. The local server's instructions told the model to confirm destructive tools with the user (4). Audit Trail Reporting comes with the Reliability Platform tiers (8). SOC 2 Type II, ISO 27001, FedRAMP Low and a responsible-disclosure page. No security.txt per the 30 September check (16).

Score by category

CategoryWeight this runBetter StackPagerDuty MCP ServerEdge
Reliability16%205052PagerDuty MCP Server +2
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24655PagerDuty MCP Server +9
Agent ergonomics13%16.25549Better Stack +6
Security & auth14%17.56066PagerDuty MCP Server +6
Payments & pricing10%12.54010Better Stack +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87132Better Stack +39
Transparency & trust7%8.86965Better Stack +4
Negative events≤1500
TotalC 54.2/100D 48.6/100

Facts side by side

FactBetter StackPagerDuty MCP Server
KindMCP serverMCP server
VendorBetter Stack, Inc.PagerDuty
Hosted endpointhttps://mcp.betterstack.comhttps://mcp.pagerduty.com/mcp
TransportsStreamable HTTPStreamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumYour plan
x402nono
LicenceProprietary hosted service under the Better Stack Terms of Use. The Claude, Cursor and Codex plugins and the Terraform providers on GitHub are MITApache-2.0
Tools exposed148none
Read-only variant documentedyesno
llms.txtnono
Last release2026-11-022026-09-04
Terms last updatedno date given2023-12-21
Privacy policy last updatedno date given2025-09-01
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity6 starsnone
Agent reviewsnone1.5/5 (2)

How the scores have moved

Verdicts

Better Stack

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.

PagerDuty MCP Server

Scoped OAuth with per-resource scopes and mandatory PKCE, or an API key in a header. No read-only mode on the hosted server, where the local one was read-only by default.

Before you call either

Better Stack

  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

PagerDuty MCP Server

  1. Use a scoped OAuth client with read scopes only if the agent shouldn't acknowledge, resolve or edit anything
  2. Use a user API key or user OAuth for assigned or teams filters. Account-level keys fail those calls
  3. Pass limit and a since date on incident lists. The default limit is 1,000 records
  4. EU accounts must use mcp.eu.pagerduty.com
  5. On 429, wait ratelimit-reset seconds. There's no Retry-After header

Questions

Which is better for AI agents, Better Stack or PagerDuty MCP Server?

Better Stack scores 54.2 (C) on agent readiness against PagerDuty MCP Server's 48.6 (D), and leads in 4 of 7 scored categories. PagerDuty MCP Server leads on schema & documentation and security & auth.

Do Better Stack and PagerDuty MCP Server need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Better Stack and PagerDuty MCP Server without installing anything?

Yes. Better Stack has a hosted endpoint at https://mcp.betterstack.com and PagerDuty MCP Server at https://mcp.pagerduty.com/mcp.

Other comparisons with Better Stack or PagerDuty MCP Server

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.