Head to head · Analytics queries · October 2026 research run

Mostly Good Metrics vs Userpilot

Userpilot scores 64.4 (B) on agent readiness against Mostly Good Metrics's 41.7 (E), and leads in 6 of 7 scored categories. Both do analytics queries.

Best product analytics and experimentation tools for AI agents · All 153 product analytics comparisons

Which one, for what

Mostly Good Metrics E

Best for Indie and small-team apps that want simple funnels and retention an agent can query.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Public beta run by one developer, with no named legal entity in the terms

Userpilot B

Best for SaaS teams already using Userpilot for onboarding who want an agent to answer analytics questions and draft segments and surveys.

Ahead on

  • Reliability, 82 against 29
  • Schema & documentation, 71 against 49
  • Agent ergonomics, 60 against 49
  • Security & auth, 62 against 33
  • Maintenance & community, 79 against 74
  • Transparency & trust, 59 against 45

Watch for

Plans start at $299 a month, and the HTTP API needs Growth from $849

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.

Reliability Userpilot +53

Mostly Good Metrics 29

Graded on the hosted service with the hosted lines. No status page was found (0) and no incident history could be read (5). Ingestion limits are documented per plan (1,000 to 100,000 events a minute and 10,000 to 1,000,000 an hour), but no limit for MCP or query calls was found (12 of 15). 429 with Retry-After in the header and body, and the SDKs queue events and back off. No idempotency or safe-retry guidance for writes (12 of 15). No SLA (0). The press kit calls the product a public beta (0). 0+5+12+12+0+0 = 29.

Userpilot 82

Graded on the hosted service with the hosted lines. Better Stack status page at status.userpilot.io with components for ingestion in three regions, the SDKs, the web application APIs and the website (20). From August to November 2026 the page shows only scheduled maintenance windows of two to four hours, with no incidents; the MCP server isn't a component (30). 600 requests a minute per token for the real-time APIs, but no numbers for MCP or export (12 of 15). 429 documented with exponential backoff guidance; no Retry-After or idempotency guidance (10 of 15). The SLA is a custom Enterprise contract term, not published (0). The MCP server is 1.0.0 in the registry with no beta label (10). 20+30+12+10+0+10 = 82.

Security & auth Userpilot +29

Mostly Good Metrics 33

OAuth 2.0 with PKCE, dynamic client registration and a revocation endpoint for MCP and the CLI; project ingest keys in a Bearer header that can be pinned to origins or app IDs. The only tool scope advertised is mcp:tools, so a connection gets every tool the user can use (24 of 30). Restricted keys and a confirmation step for unrestricted keys in the CLI; no read-only MCP mode or approval for deletes was found (6 of 20). Event properties come from apps and end users and reach the agent, and no prompt-injection guidance was found (3 of 15). No audit log was found (0). No security.txt, disclosure policy or certification was found (0). 24+6+3+0+0 = 33.

Userpilot 62

The MCP server uses OAuth with PKCE, dynamic client registration, revocation, separate read and write scopes and the user's own role. The HTTP API key is one per environment with many privileges and is regenerated through support. Averaged over both surfaces (22 of 30). Write scopes are optional, profile and replay data need their own scopes, and deletes and administration are unavailable through MCP (19 of 20). Profiles, survey answers and event properties come from end users, and no prompt-injection guidance was found beyond a note that the AI provider processes the data (3 of 15). Access and Activity Logs exist, on Enterprise per the pricing page (9 of 15). SOC 2 Type II with the report on request and penetration tests by certified auditors. No security.txt, disclosure policy or bug bounty (9 of 20). 22+19+3+9+9 = 62.

Schema & documentation Userpilot +22

Mostly Good Metrics 49

No OpenAPI file was found. The docs say every MCP tool describes its own parameters, and the query definition object is documented in full; we didn't open an MCP session to read the schemas (12 of 25). No llms.txt (404) and no Markdown pages served for agents (0). Each tool area is documented with examples, and the docs say when to use query_metrics instead of repeated execute_query calls (10 of 20). The query definition lists metrics, dimensions, date ranges and filter operators (9 of 15). The ingestion API documents its error body and status codes, and query_metrics reports per-item errors (11 of 15). /v1 and /api/v2 paths and dated SDK tags, but no product changelog (7 of 15). 12+0+10+9+11+7 = 49.

Userpilot 71

Every API reference page embeds an OpenAPI 3.0 definition, though no standalone spec file was found (20 of 25). llms.txt and Markdown versions of every page (10). Endpoint pages state their purpose and the MCP docs say what each permission allows; the MCP tool definitions weren't read because that needs a session (12 of 20). Request bodies are typed, mostly as strings and string arrays with few enums (9 of 15). An error reference covers 400, 401, 422 and 429 with causes, and pages carry examples (12 of 15). /v1 paths and dated SDK release notes; no API changelog was found (8 of 15). 20+10+12+9+12+8 = 71.

Transparency & trust Userpilot +14

Mostly Good Metrics 45

The service is closed; the SDKs and CLI are MIT. Terms of December 2025 with no legal entity named (18 of 30). The privacy policy and terms agree on raw-event retention for the subscription's life and deletion within 14 days of account deletion; the about page says data is not used to train models. No DPA was found (18 of 30). The legacy X-MGM-Key header is still supported, and no deprecation policy was found (3 of 20). The terms name eight sub-processors with their purpose, without data locations (12 of 20). 18+18+3+12 = 51.

Userpilot 59

A closed service with terms dated 23 April 2024 (15 of 30). The privacy policy of 11 March 2025 names a DPO and two sub-processors (AWS and Cloudflare), while the security page names AWS, Google Cloud and Stripe. The DPA is on request and no customer-data retention period is stated (14 of 30). No deprecation policy or dated API notices found (3 of 20). Sub-processors are named with addresses but not data locations, though an EU ingestion endpoint exists (10 of 20). 15+14+3+10 = 42.

Agent ergonomics Userpilot +11

Mostly Good Metrics 49

53 tools, more than 30 (5). We added 3 because Goals and Alerts tools load only where enabled and query_metrics batches up to 10 queries (8 of 25). Date ranges, grouping and filters on queries; no documented page or limit parameters for lists (12 of 20). JSON errors with a message, and per-item status in batch results (13 of 20). Annotations weren't readable without a session, the tool list includes deletes and key revocation, and no idempotency keys were found (4 of 20). Five client SDKs and a CLI with --json output (12 of 15). 8+12+13+4+12 = 49.

Userpilot 60

The tool count isn't published; the docs say the assistant can search hundreds of extra read-only operations on demand, which reads as dynamic loading. Without the list we give the middle band (15 of 25). Export jobs filter by date range, users, events and segments, and job lists paginate (14 of 20). A documented error reference (13 of 20). No deletes or admin through MCP by design; annotations weren't readable and no idempotency keys were found (10 of 20). The HTTP APIs have no official server-side SDK; client SDKs for web and six mobile frameworks (8 of 15). 15+14+13+10+8 = 60.

Maintenance & community Userpilot +5

Mostly Good Metrics 74

CLI v0.1.4 was tagged on 16 October 2026 (30). The JavaScript SDK released 0.12.0, 0.13.0 and 0.13.1 between 5 September and 2 October, and the Swift SDK 1.0.0 and 1.0.1 on 2 October (20). A closed service with no public changelog, support by email and GitHub repositories for the SDKs; issue activity wasn't read because the GitHub API refused us for its rate limit (6 of 25). Not in the official MCP registry; official SDKs in five languages are current (10 of 15). CI workflows on the SDK and CLI repositories (8 of 10). 30+20+6+10+8 = 74.

Userpilot 79

io.userpilot/mcp 1.0.0 was published to the registry on 11 October 2026 (30). The iOS SDK alone has dated releases on 6 August, 2 September, 27 September and 2 October 2026 (20). A closed service with no public API changelog, support by email and chat (8 of 25). Verified io.userpilot namespace in the official MCP registry (15). Client SDKs are current; there is nothing else public to inspect (6 of 10). 30+20+8+15+6 = 79.

Score by category

CategoryWeight this runMostly Good MetricsUserpilotEdge
Reliability16%202982Userpilot +53
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24971Userpilot +22
Agent ergonomics13%16.24960Userpilot +11
Security & auth14%17.53362Userpilot +29
Payments & pricing10%12.53030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87479Userpilot +5
Transparency & trust7%8.84559Userpilot +14
Negative events≤1500
TotalE 41.7/100B 64.4/100

Facts side by side

FactMostly Good MetricsUserpilot
KindHTTP APIHTTP API
VendorMostly Good MetricsUserpilot, Inc.
Hosted endpointhttps://app.mostlygoodmetrics.com/mcphttps://mcp.userpilot.io/mcp
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumPaid
x402nono
Tools exposed53none
Read-only variant documentednono
llms.txtnoyes
MCP registrynot listedio.userpilot/mcp
Last release2026-10-162026-10-11
Terms last updated2025-12-012024-04-23
Privacy policy last updated2025-12-012025-03-11
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 textnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textyes
Popularity81 npm/wk236k npm/wk

Verdicts

Mostly Good Metrics

Mostly Good Metrics lets an agent run ad-hoc funnels, retention and up to ten metric queries per call through a hosted MCP server with OAuth, at prices from $0. It is a public beta built by one developer, with no status page, no named legal entity and no security policy found.

Userpilot

Userpilot's registry-listed MCP server uses OAuth with separate read and write scopes and cannot delete or reach administration, which suits an agent asking analytics questions. Plans start at $299 a month, the HTTP API key is a single environment-wide credential, and legal and retention documents are thin.

Before you call either

Mostly Good Metrics

  1. Use query_metrics for several aggregate questions instead of repeated execute_query calls
  2. Pass inline definitions to execute_funnel and execute_retention rather than creating saved objects
  3. Confirm with the user before delete, revoke_api_key or stop_experiment calls, since the server doesn't ask
  4. Start a fresh agent session after connecting, since a running client may not reload the tool list
  5. On 429 from ingestion, wait for Retry-After before resending events

Userpilot

  1. Ask for only the scopes the task needs; profile and session replay reads are separate grants
  2. Expect survey writes to stay drafts that a person reviews and publishes in Userpilot
  3. Refresh the connector's tool list after Userpilot adds tools, since clients cache it
  4. Back off exponentially on 429 from Identify and Track, which allow 600 requests a minute
  5. Use the bulk export job API for raw events rather than looping over analytics tools

Questions

Which is better for AI agents, Mostly Good Metrics or Userpilot?

Userpilot scores 64.4 (B) on agent readiness against Mostly Good Metrics's 41.7 (E), and leads in 6 of 7 scored categories.

Do Mostly Good Metrics and Userpilot need an API key?

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

Can an agent call Mostly Good Metrics and Userpilot without installing anything?

Yes. Mostly Good Metrics has a hosted endpoint at https://app.mostlygoodmetrics.com/mcp and Userpilot at https://mcp.userpilot.io/mcp.

Other comparisons with Mostly Good Metrics or Userpilot

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.