Basedash MCP vs Userpilot

Basedash MCP 74

The editorial half. A closed service under dated terms (14 October 2026) naming Basedash Inc. and Delaware law, with 30 days' notice of material adverse changes to the agreement (15). The privacy policy (1 June 2026), the data processing addendum (6 October 2026) and the security docs agree that customer data isn't used for training by Basedash or its AI providers, and the security docs say table and column names and query results go to AI providers. Retention periods differ by document. The privacy policy says a reasonable period, the terms 60 days after a deletion request, the security docs complete removal on request, and audit events are kept 90 days. Locations differ in wording (San Francisco servers in the security docs, DigitalOcean in the United States in the privacy policy) (18 of 30). No deprecation policy for the MCP server; the REST API is unversioned and breaking changes are communicated in advance when possible, and the dashboard scopes were granted to existing connections without re-authorising (8 of 20). The DPA names ten subprocessors (OpenAI, Sentry, Stripe, DigitalOcean, Anthropic, Amazon Web Services, Microsoft Azure, Fivetran, MotherDuck, Betterstack) in the United States and the Czech Republic (16 of 20). Total 57.

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.

Basedash MCP 57

The served tool definitions can be read only in a signed-in MCP session, which this run doesn't open. The docs and feature page list all ten tools with their inputs, which are required or optional, their scopes, what each returns and which one is annotated destructive, and the REST API counterpart has a public OpenAPI 3.1.0 file (50 paths, 91 operations). Judgement call, 10 of 25 for documented inputs without published JSON Schemas. llms.txt and Markdown copies of every docs page are served (10). Each tool's purpose is stated, with when to use MCP over the REST API and get_data_sources described as the call to make before asking; when not to call a build tool isn't stated (12 of 20). Inputs are a free-text question or instructions plus ids, with no enums or constraints documented (5 of 15). Example questions on the feature page and the launch posts, and troubleshooting for Forbidden or not-a-member, usage blocked and not-found errors, but no error payload shapes (10 of 15). A public dated changelog with MCP entries on 5 June, 14 August, 4 and 25 September and 7 and 9 October 2026, and a server.json version (1.1.0), but the registry entry is still 1.0.0 and the llms.txt of 7 October 2026 still describes two tools (10 of 15). Total 57.

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.

Basedash MCP 70

Graded with the hosted lines, on the remote server at charts.basedash.com. Instatus status page at status.basedash.com with one component, App, and notices back to April 2021; the MCP server isn't a separate component (20). No notices since 14 March 2026 and 100.0 per cent shown for September, October and November 2026, so the last 90 days are clean (30). No rate limit is published for the MCP server. The public API allows 60 requests a minute by default, per the changelog of 7 August 2026, which we count in part since the MCP surface may differ (5 of 15). The OpenAPI file documents a 429 with RateLimitExceeded and retryAfterMs on all 91 operations and an Idempotency-Key on starting a chat, but nothing is documented for 429s or retries over MCP (5 of 15). No uptime SLA; the about page names priority support SLAs on Enterprise only (0). The server isn't labelled beta or preview and is on both paid plans (10). Total 70.

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.

Basedash MCP 68

OAuth on Basedash's own authorisation server, with the authorisation code grant and PKCE S256 only, refresh tokens, public clients, dynamic client registration, client ID metadata documents and a revocation endpoint. Three scopes separate asking, reading dashboards and writing them, and the token goes in the header only (30). Building needs mcp:dashboards:write on top of mcp:chat:ask, edit_dashboard is annotated destructive, no tool deletes, and Basedash's AI can change database rows only from the web app with an approval card, per the accuracy page. No server-side confirmation is documented for dashboard edits, and the consent screen on the feature page shows all three scopes together (15 of 20). Answers are drawn from connected company data, which can include text written by outsiders (tickets, CRM records synced by Fivetran), and no prompt-injection guidance was found. Hidden columns and row-level security narrow what reaches the model (5 of 15). The MCP server is a named audit log source, but AI tool calls and queries are recorded on Enterprise only; AI usage per person and feature is shown on every plan (10 of 15). No security.txt on www or charts, and no bug bounty or disclosure policy found. Basedash says it holds SOC 2 Type II, with the report under NDA, and runs third-party penetration tests (8 of 20). Total 68.

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.

Basedash MCP 55

Ten tools, grouped by the vendor into ask, build and look up. Their definitions' size couldn't be measured without a session, so 20 of 25 rather than 25. No paging, filters or size controls are documented for list_dashboards or list_charts; ask_question returns tables as CSV files rather than inline rows, and the client can page through the tool list, per the changelog of 14 August 2026 (5 of 20). The troubleshooting section names Forbidden or not-a-member, usage blocked and not-found or archived artifacts with what to do, and ask_question and get_data_sources return typed structured payloads since 5 June 2026 (10 of 20). edit_dashboard is annotated destructive and a failed dashboard or chart build is cleaned up, but no readOnlyHint on the look-up tools or idempotency on the create tools is documented (10 of 20). One or two required inputs per tool and nothing to install; the only official SDK is the React embedding SDK, which isn't for MCP (10 of 15). Total 55.

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.