Observability - official Langfuse server
Langfuse MCP server
Native, authenticated MCP server built into Langfuse that lets agents read and write project data: prompts, observations, datasets, scores, evaluators, annotation queues, dashboards and metrics. Each project-scoped API key limits access to one project. Langfuse hosts it at https://cloud.langfuse.com/api/public/mcp with API key auth.
Last verified 15 tools4 sources
Install
Claude Code
About Claude Code# Langfuse Cloud (EU)
claude mcp add --transport http langfuse https://cloud.langfuse.com/api/public/mcp \
--header "Authorization: Basic {your-base64-token}"Codex
About Codex[mcp_servers.langfuse]
url = "https://cloud.langfuse.com/api/public/mcp"
http_headers = { "Authorization" = "Basic {your-base64-token}" }Cursor
About Cursor{
"mcp": {
"servers": {
"langfuse": {
"url": "https://cloud.langfuse.com/api/public/mcp",
"headers": {
"Authorization": "Basic {your-base64-token}"
}
}
}
}
}Tools
getPrompt- Fetch a specific prompt by name with optional label or version
listPrompts- List and filter prompts in the project
createTextPrompt- Create a new text prompt version
createChatPrompt- Create a new chat prompt version
updatePromptLabels- Update labels for a specific prompt version
listObservations- Find and review observations such as generations, spans, agent steps and tool calls (requires v4)
getObservation- Get details for a single observation by ID (requires v4)
queryMetrics- Answer analytics questions on usage, cost, latency, errors and scores (requires v4)
listDatasets- List datasets of input and expected-output examples
upsertDatasetItem- Upsert one example in a dataset
listScores- Find quality, evaluation or feedback scores
createScore- Create one score in the current project
listEvaluators- List LLM-as-a-judge, code and decision-model evaluators
createEvaluator- Create a new evaluator
listDashboards- List editable dashboards in the current project
As documented on October 17, 2026. A running server reports its current list through tools/list.
Notes and caveats
- Endpoints per region: EU https://cloud.langfuse.com/api/public/mcp, US https://us.cloud.langfuse.com/api/public/mcp, Japan https://jp.cloud.langfuse.com/api/public/mcp, HIPAA https://hipaa.cloud.langfuse.com/api/public/mcp, self-hosted https://your-domain.com/api/public/mcp.
- Auth is HTTP Basic with base64 of a project-scoped public:secret key pair.
- Read and write tools are enabled by default; use a client allowlist for read-only.
- Several observation and metrics tools require Langfuse v4.
- Langfuse recommends its Agent Skill over the MCP server where agents can run CLI tools.
- The docs page carries no beta or preview label.
- Install snippets shown are the EU Cloud variants; the docs list the other regions alongside.
More MCP servers for observability
- LangfuseStatus: GA
Langfuse Docs MCP server
Public, unauthenticated MCP server that exposes the Langfuse documentation to agents, used for tasks such as having a coding agent add Langfuse tracing to a codebase.
Transport: Streamable HTTPAuth: No auth - ArizeStatus: Preview
Arize AX MCP server
Hosted MCP server that gives agents access to Arize AX projects, traces, spans, datasets, experiments, evaluators, monitors and prompts. It is a thin layer over the Arize REST API v2.
Transport: Streamable HTTPAuth: OAuth or API key - ArizeStatus: GA
Phoenix MCP server
Local npm-distributed MCP server for Arize Phoenix that connects to a Phoenix instance with a base URL and API key. Covers projects, traces, spans, sessions, annotation configs, prompts, datasets and experiments.
Transport: stdioAuth: API key - ArizeStatus: Beta
Phoenix Remote MCP server
MCP server built into Arize Phoenix at the /mcp path of any Phoenix instance, letting agents read and act on traces, spans, datasets, experiments and prompts through Phoenix's REST API, plus read-only SQL and GraphQL queries. By default it exposes code-mode tools that search the operation catalog and run sandboxed Python that chains operations.
Transport: Streamable HTTPAuth: OAuth or API key - AWS
AWS Labs CloudWatch MCP server
Open source local MCP server from AWS Labs that gives troubleshooting agents access to CloudWatch metrics, alarms and Logs Insights for root cause analysis.
Transport: stdioAuth: Other - Axiom
Axiom MCP server
Hosted MCP server that lets AI agents query Axiom event, trace and metrics data with APL and MPL, explore datasets, and manage dashboards, monitors and notifiers.
Transport: Streamable HTTP, SSEAuth: OAuth or API key
Related reading
- AI Agent Eval Tools Compared: Braintrust vs Promptfoo vs DeepEvalAI agent eval tools compared - Braintrust, Langfuse, Promptfoo, DeepEval, Ragas, and OpenAI Evals on offline vs online evals, LLM-as-judge, CI, and datasets.
- Langfuse vs Braintrust vs Helicone: Agent Tracing Tools in 2026Langfuse vs Braintrust vs Helicone, plus LangSmith and Arize Phoenix: 2026 pricing tiers, self-host options, agent-trace features, and OpenTelemetry support.
- Prompt Management Tools Compared: Langfuse vs PromptLayer vs MoreA fair look at Langfuse, PromptLayer, Promptfoo, Helicone, Latitude, and Agenta for versioning, evals, and deploying LLM prompts.
- What's New in Mastra (Late 2026): Harness, AgentController GA, Eval Gates and MCP 2.xMastra in late 2026: goals, schedules, signals, AgentController GA, eval gates and MCP 2.x, with type-checked TypeScript examples and honest tradeoffs.
- MCP vs A2A vs Function Calling: Which Layer Does What in 2026MCP vs A2A vs function calling compared on the 2026-07-28 MCP spec and A2A 1.0: what each protocol does, where they overlap, and how to stack them.
- Pydantic AI V2 in Late 2026: Capabilities, Graphs, Evals and MCPPydantic AI V2 explained through v2.57.0: capabilities, typed output, Conversation storage, caching, graphs, evals, MCP Apps and Logfire, with checked code.
FAQ
What does the Langfuse MCP server do?
Native, authenticated MCP server built into Langfuse that lets agents read and write project data: prompts, observations, datasets, scores, evaluators, annotation queues, dashboards and metrics. Each project-scoped API key limits access to one project. The vendor documents 15 tools, including getPrompt, listPrompts, createTextPrompt and createChatPrompt.
How do I add the Langfuse MCP server to Claude Code?
Langfuse documents a Claude Code config; copy it from the Claude Code section of this page. Snippets for Codex and Cursor are there too.
Does the Langfuse MCP server need authentication?
Yes, API key. Transport: Streamable HTTP. Status: GA, last checked October 17, 2026.
Sources
Last verified against 4 Langfuse pages, then re-checked independently.
- langfuse.comhttps://langfuse.com/docs/api-and-data-platform/features/mcp-server
- mcp.reference.langfuse.comhttps://mcp.reference.langfuse.com/
- raw.githubusercontent.comhttps://raw.githubusercontent.com/langfuse/langfuse/main/LICENSE
- hub.docker.comhttps://hub.docker.com/v2/repositories/langfuse/langfuse/tags?page_size=5&ordering=last_updated
Newsletter
New MCP servers, the week they ship
One email per week. New official MCP servers, the coding tools that support them and how developers wire them up.