Langfuse for Meta Muse
Query traces and observations, manage prompts and scores.
Read and write the user's Langfuse LLM observability data: browse traces and observations, list prompts and datasets, score traces, and add dataset items. Use when the user mentions Langfuse or LLM tracing and evaluation.
View original source ↗How to set it up
Paste a promptDraft — these instructions come from the linked source and have not been independently live-tested by OpenTools.
Before you start
- Public+secret key pair (per-project; host declared at connect time)
Steps
- Paste the install prompt into a chat with Muse.
- Muse fetches the pinned SKILL.md and the 2 files in its manifest.
- Authorize your own account through Muse’s secure credential flow.
- Have Muse run the status check shown in the source skill.
Prompt to paste into Muse
Install this connector: https://raw.githubusercontent.com/bluman1/muse-connectors/6e31fd44a71f9f28377a1460e64cd7483c3cce22/connectors/langfuse/SKILL.md Read its Files manifest and install exactly those files. Collect credentials through Muse's secure credential flow; never ask me for raw keys in chat. Run the skill's status check and report the result.
Account access: via the secure credential flow (`credentials.request_api_access`). The credential stores ONE combined value in the format `public_key:secret_key` (e.g. `pk-lf-...:sk-lf-...`), as issued in Langfuse under Settings > API keys. The CLI splits on the first colon into username (public key) and password (secret key) and sends them as HTTP Basic auth (`Authorization: Basic base64(pk:sk)`). Store the combined value exactly once, with exactly one colon separator.
Allowed hosts: cloud.langfuse.com, us.cloud.langfuse.com
Confirm it works: `bin/langfuse.py auth` (must return `"ok": true`)
Services it connects with
These are the services the connector uses. The publisher is identified separately.
Langfuse