Get an audit

Head to head · Analytics query · October 2026 research run

Countly vs GrowthBook

GrowthBook scores 70.1 (BB) on agent readiness against Countly's 54.8 (C), and leads in every scored category. Both do analytics query.

CountlyCountly Ltd · HTTP API C54.8/100#607 of 841 GrowthBookGrowthBook, Inc. · HTTP API BB70.1/100#155 of 841

Which one, for what

Countly C

Good for An agent whose owner runs Countly on its own infrastructure or a dedicated Flex server and wants analytics, crash and remote-config data through MCP with per-category permissions.

Also in its favour

  • No incidents deducted, where GrowthBook loses 3 points for them

Watch for

No public status page or incident history was found for Flex servers or for mcp.count.ly

GrowthBook BB

Good for Teams that want flags and experiments analysed against their own warehouse, with an open-source core and a self-hosted option.

Ahead on

  • Reliability, 86 against 28
  • Agent ergonomics, 76 against 66
  • Security & auth, 68 against 63
  • Payments & pricing, 40 against 17
  • Maintenance & community, 89 against 80

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card

Watch for

The API tools take a path and a JSON string and don't validate payloads, so correct calls depend on the bundled skills

Score by category

CategoryWeight this runCountlyGrowthBookEdge
Reliability16%202886GrowthBook +58
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27576GrowthBook +1
Agent ergonomics13%16.26676GrowthBook +10
Security & auth14%17.56368GrowthBook +5
Payments & pricing10%12.51740GrowthBook +23
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88089GrowthBook +9
Transparency & trust7%8.87074GrowthBook +4
Negative events≤150-3
Total54.8 · C70.1 · BB

Facts side by side

FactCountlyGrowthBook
KindHTTP APIHTTP API
VendorCountly LtdGrowthBook, Inc.
Hosted endpointhttps://mcp.count.ly/mcphttps://mcp.growthbook.io/mcp
TransportsHTTP, stdio, Streamable HTTPHTTP, Streamable HTTP, stdio
AuthAPI keyOAuth or key
PricingPaidFreemium
x402nono
LicenceCountly Lite is AGPL-3.0 with added branding terms under Section 7. Enterprise plugins are proprietary. Flex is a hosted service under Countly's terms. The MCP server is MITMIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement
Tools exposed2094
Read-only variant documentedyesno
llms.txtyesyes
MCP registrynot listedio.github.growthbook/growthbook-mcp
Last release2026-10-072026-10-06
Terms last updated2026-09-252025-06-19
Privacy policy last updated2026-09-252026-06-08
Customer content may train modelsnot found in the textyes
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 noticeyesnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity28k npm/wk8.5k stars, 1.3M npm/wk, 433k PyPI/wk

Verdicts

Countly

Countly suits an agent working against a server its owner already runs. The official MCP server filters its 209 tools by edition, plugin and permission and has per-category read-only settings. No status page, OpenAPI document or published API rate limit was found, and the Flex trial needs a credit card.

GrowthBook

GrowthBook Cloud's MCP server has four tools with read and write annotations, OAuth with dynamic client registration, and a 414-operation OpenAPI spec behind it. The free plan needs no card. The API tools pass paths and JSON bodies through without validation, every key is limited to 60 requests a minute, and audit logs are Enterprise only.

Before you call either

Countly

  1. Create a dedicated token in the Token Manager, limited to the apps and endpoints the task needs, and send it in the countly-token header, not the URL
  2. Set COUNTLY_TOOLS_ALL=R unless the task needs writes. The token's own permissions still apply and the stricter of the two wins
  3. Call apps_list first. Most tools need app_id or an exact app_name
  4. Check get_version for the detected edition before planning funnel, retention or cohort queries, which need Enterprise plugins
  5. Set ENABLE_ANALYTICS=false to stop usage reports to stats.count.ly, and prefer the stdio server to mcp.count.ly so the server URL and token stay local

GrowthBook

  1. Connect to https://mcp.growthbook.io/mcp and complete OAuth in a browser. Use https://mcp.growthbook.io/mcp/api for the two API tools alone
  2. Call growthbook_list_skills and growthbook_read_skill before writing. The API tools don't validate payloads, so use the paths the skill names
  3. Stay under 60 requests a minute per key. On 429 wait for the RateLimit-Reset seconds before retrying
  4. List calls return 10 items by default. Pass limit up to 100 and offset to page
  5. A 422 is a soft warning. Resubmit with ?ignoreWarnings=true only after reading the message

Questions

Which is better for AI agents, Countly or GrowthBook?

GrowthBook scores 70.1 (BB) on agent readiness against Countly's 54.8 (C), and leads in every scored category.

Do Countly and GrowthBook need an API key?

Countly needs an API key. GrowthBook takes an API key or an OAuth sign-in.

Can an agent call Countly and GrowthBook without installing anything?

Yes. Countly has a hosted endpoint at https://mcp.count.ly/mcp and GrowthBook at https://mcp.growthbook.io/mcp.

Are Countly and GrowthBook open source?

Yes. Countly is open source (Countly Lite is AGPL-3.0 with added branding terms under Section 7. Enterprise plugins are proprietary. Flex is a hosted service under Countly's terms. The MCP server is MIT). GrowthBook is open source (MIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement).

Other comparisons with Countly or GrowthBook

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