# Reported issues for growthbook-mcp Pod holds 9 of 9 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user. Back to [growthbook-mcp](/mcp/growthbook-mcp-2). ## Most discussed ### MCP get_attributes tool fails with HTTP 400 due to unsupported limit query parameter The get_attributes MCP tool appears to be sending a limit query parameter to the GrowthBook attributes endpoint, which results in a 400 response. This occurs even when using an Admin API key, suggesting this is not a permissions issue but an MCP/API compatibility issue. Environment: GrowthBook Cloud Claude Desktop + Claude Code GrowthBook MCP (@growthbook/mcp@latest) Reproduced with both Global Experimenter and Admin API keys Steps to Reproduce: Configure GrowthBook MCP in Claude Desktop wit [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/60) · 2026-06-03 · open · external user · 0 comments ### create_feature_flag fails with "No data source or assignment query found" when org has no data source **Version:** `@growthbook/mcp@1.8.1` · GrowthBook Cloud **What happens:** Calling `create_feature_flag` for a simple boolean flag fails with: > `No data source or assignment query found. Experiments require a data source/assignment query. Set these up in the GrowthBook and try again.` This happens in any org that has **no data source and no experiments** — e.g. a project using GrowthBook purely for feature flags. The docs state a data source is only needed for experiments, so flag creation sh [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/58) · 2026-05-30 · open · external user · 0 comments ### Creating experiment with targeted attributes supported MCP to support configuring targeting attributes (e.g. conditions, audiences, geo rules) at the time of experiment creation, enabling fully end-to-end experiment setup via MCP. Currently, this limitation requires users to fall back to the UI or API, breaking the otherwise streamlined workflow. Expanding MCP to include targeting configuration would significantly improve automation, consistency, and adoption for enterprise use cases. [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/56) · 2026-05-22 · open · external user · 0 comments ### OAuth Support The ability to log in using OAuth [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/41) · 2026-03-16 · open · external user · 0 comments ### Feature : Custom Field Support We are starting to use your MCP server, but there are some key things missing for us to fully use it: - CustomFields of an experiment cannot be set/modified via the MCP - CustomFields of a feature flag cannot be set/modified via the MCP [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/39) · 2026-03-09 · closed · external user · 1 comment ### Feature: Create per‑environment experiment rules I'm working on automating experiment setup using the GrowthBook MCP with AI agents (Cursor/Claude Code). Running into a limitation I wanted to discuss. The goal: Automatically create feature flags with experiment rules that have different targeting per environment. In other words, I want to create and attach one experiment rule per environment. For example, we need production rules to have a is_test_user: true targeting so test engineering can validate in dark prod, while staging/dev run wi [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/29) · 2026-01-29 · open · external user · 0 comments ### Feature flag validation doesn't allow "." but it should GrowthBook has these requirements for feature flag names: `Only letters, numbers, and the characters _, -, ., :, and | allowed. No spaces. Cannot be changed later!` The current MCP validation logic is too strict, not allowing "." [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/19) · 2025-10-29 · closed · outside contributor · 1 comment ### Add `project` parameter support when creating feature flags First of all, thank you for creating and maintaining this excellent MCP server for GrowthBook! We've been using it at our company and it's been incredibly helpful for streamlining our feature flag workflow. ### 🎯 Feature Request We would love to see support for assigning a **project** to feature flags during creation via the `create_feature_flag` tool. ### 📋 Current Behavior Currently, when creating a feature flag using the MCP tool, we can set: - `id` - `valueType` - `defaultValue` - `fileE [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/18) · 2025-10-28 · closed · external user · 1 comment ## Most recent ### Return `customFields` in read tools Following on from #39 (resolved in v1.8.0), `customFields` can now be set on experiments and feature flags via the MCP — but they are not returned by `get_experiments` or `get_feature_flags`. Please include `customFields` in the output of these read tools so the full round-trip (write and read) is supported. [Read the thread](https://github.com/growthbook/growthbook-mcp/issues/62) · 2026-06-24 · open · external user · 0 comments The remaining reports are on [the project's issue tracker](https://github.com/growthbook/growthbook-mcp/issues).