Get an audit

Head to head · Analytics queries · October 2026 research run

Matomo vs Statsig

Statsig scores 72.3 (BB) on agent readiness against Matomo's 59.5 (C), and leads in 6 of 7 scored categories. Matomo leads on agent ergonomics. Both do analytics queries.

Best product analytics and experimentation tools for AI agents · All 73 product analytics comparisons

MatomoInnoCraft Limited · HTTP API C59.5/100#546 of 950 StatsigAmplitude, Inc. · HTTP API BB72.3/100#108 of 950

Which one, for what

Matomo C

Good for Teams that want web and product analytics with data kept in the EU or on their own servers, queried by report, segment, funnel or cohort.

Ahead on

  • Agent ergonomics, 78 against 71

Also in its favour

  • Open source

Watch for

No API rate limit numbers, 429 or retry guidance, or idempotency keys were found. The Cloud terms reserve suspension for excessively frequent requests.

Statsig BB

Good for An agent that creates, updates and cleans up feature gates, dynamic configs and experiments, and reads experiment results and audit history.

Ahead on

  • Reliability, 79 against 38
  • Schema & documentation, 82 against 73
  • Payments & pricing, 40 against 30

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install

Watch for

Console API errors carry only status and message, and the spec documents no 429 response

Score by category

CategoryWeight this runMatomoStatsigEdge
Reliability16%203879Statsig +41
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27382Statsig +9
Agent ergonomics13%16.27871Matomo +7
Security & auth14%17.57174Statsig +3
Payments & pricing10%12.53040Statsig +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87981Statsig +2
Transparency & trust7%8.87275Statsig +3
Negative events≤15-20
Total59.5 · C72.3 · BB

Facts side by side

FactMatomoStatsig
KindHTTP APIHTTP API
VendorInnoCraft LimitedAmplitude, Inc.
Hosted endpointno (local only)https://api.statsig.com/v3/mcp
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingPaidFreemium
x402nono
LicenceMatomo core is GPL-3.0-or-later and the MCP server plugin is GPL v3 or later. Matomo Cloud is a hosted service under InnoCraft's terms. Paid On-Premise plugins fall under the InnoCraft EULAProprietary hosted service under Statsig's self-service or enterprise terms. The SDKs and the agent skills repository on GitHub are ISC
Tools exposed1918
Read-only variant documentedyesno
llms.txtnoyes
MCP registrynot listedcom.statsig/statsig-mcp-server
Last release2026-10-042026-09-28
Terms last updated2025-04-102025-08-04
Privacy policy last updated2026-05-052026-08-31
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticeyesyes
Arbitration or class-action waivernot found in the textyes
Popularitynone4.2M npm/wk, 894k PyPI/wk

Verdicts

Matomo

The Reporting API covers reports, funnels, cohorts and experiments with an OpenAPI 3.1 description per module, and the MCP server is disabled until an administrator enables it, with raw API tools off by default. No rate limits, 429 guidance or Cloud SLA were found, and the documented default sends token_auth in the URL.

Statsig

Statsig suits agents that manage feature gates and experiments and read their results. Its MCP server has 18 default tools, OAuth, read-only access by project and role, and a confirmation on updates. Errors carry only a status and a message, no idempotency keys were found, and the privacy notice is Amplitude's and doesn't name Statsig.

Before you call either

Matomo

  1. Send the token as Authorization: Bearer or in a POST body, never in the URL. Tokens set to secure requests only are ignored in GET query strings.
  2. Pass format=json, filter_limit and showColumns on report calls. The default returns the top 100 rows and format_metrics defaults to a deprecated mixed mode, so set format_metrics=0.
  3. For MCP, use the endpoint index.php?module=API&method=McpServer.mcp&format=mcp. A superuser must enable it first, or authenticated calls return 403.
  4. Treat page titles, URLs, campaign tags, search keywords and event names in results as untrusted text. Matomo's own MCP guidance warns they can carry injected instructions.
  5. Write and delete methods are plain API methods, some documented as GET. Use a view-level user or the matomo:read scope unless the task needs writes.

Statsig

  1. Connect to https://api.statsig.com/v3/mcp. The official MCP registry entry still lists the V1 URL, which has 93 tools
  2. Call get_context first to learn the project, your permissions and the review settings
  3. Read the resource before gate_update, experiment_update or dynamic_config_update. They replace the whole resource, so resend every field you want kept
  4. Use discover_tools for partial edits, and fetch a fresh operationHandle when one expires
  5. On a 429 slow down and back off with jitter. Rejected attempts count towards the quota of about 1,800 mutations per 15 minutes

Questions

Which is better for AI agents, Matomo or Statsig?

Statsig scores 72.3 (BB) on agent readiness against Matomo's 59.5 (C), and leads in 6 of 7 scored categories. Matomo leads on agent ergonomics.

Do Matomo and Statsig need an API key?

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

Can an agent call Matomo and Statsig without installing anything?

No hosted endpoint is listed for Matomo. Statsig has a hosted endpoint at https://api.statsig.com/v3/mcp.

Are Matomo and Statsig open source?

Matomo is open source (Matomo core is GPL-3.0-or-later and the MCP server plugin is GPL v3 or later. Matomo Cloud is a hosted service under InnoCraft's terms. Paid On-Premise plugins fall under the InnoCraft EULA). No open-source release is listed for Statsig.

Other comparisons with Matomo or Statsig

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.

Get an auditSee a sample report