"Observability" matching MCP servers:

MCP server for AI agent observability, providing trace and span logging, search, latency/tokens/cost metrics, and anomaly detection using an in-memory buffer.

Provides AI assistants with direct access to Red Hat OpenShift AI observability data, enabling querying of Prometheus metrics, Alertmanager alerts, Loki logs, Grafana dashboards, and Kubernetes cluster state to troubleshoot vLLM inference workloads.

Real-time cost observability for Model Context Protocol tool calls. Wraps any MCP server, attributesspend per tool/project/customer. Free 25K calls/month. EU-hosted, GDPR-ready, MIT.

MCP-native LLM observability. Query your Spanlens traces, stats, cost anomalies, and savings from Cursor, Claude Desktop, or any MCP client. Open source (MIT).

Lets AI agents query, manage, and operate their LLM observability data directly from the conversation. Provides 87 tools for cost analysis, alerting, anomaly detection, and runtime control gates.

AI development observability platform. It silently captures structured data from vibe coding sessions via MCP and codifies deviation patterns into project rules to make AI write better code. 100% local and zero runtime dependencies.

AI-agent observability server whose distinguishing feature is a SHA-256 hash-chained, tamper-evident audit log with chain verification and signed export. Works with Claude Desktop, Cursor, and any MCP client.

Enables observability and governance for local LLMs via Ollama, including auditing model usage, scanning prompts for secrets/PII, and enforcing allow/deny policies.

A Model Context Protocol (MCP) gateway for running Claude Code, Codex, Gemini, Grok, and Mistral (Vibe) CLIs from one MCP endpoint, with durable async jobs, session continuity, cache-aware prompting, observability, and personal-appliance setup tooling. Why developers try it: one local MCP endpoint for cross-LLM validation, multi-agent coding workflows.

Model Context Protocol server for Langfuse observability. Query traces, analyze accuracy, detect failures, track costs, debug latency, manage prompts and datasets.

A powerful Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to Dynatrace's observability platform. Features dual authentication architecture, Davis CoPilot AI integration, and 24 specialized tools for monitoring, automation, and operational intelligence.

A TypeScript framework for building MCP servers with declarative tool, resource, and prompt definitions, built-in auth, multi-backend storage, and observability.

Flask Extension for apcore (AI-Perceivable Core) integration. Expose your Flask routes as MCP tools with auto-discovery, Pydantic schema inference, and built-in observability.

MCP server for Langfuse providing 50 tools for prompt management, observability, instance/organization management, and metrics tracking via natural language.

MCP server for Sonenta translation management, enabling key/translation management, agent observability sessions, and prompt library access via natural language.

Enables AI agents to access observability and evaluation data, including run history, span traces, LLM-as-judge evaluation results, and regression reports.

A Model Context Protocol (MCP) server for comprehensive monitoring and observability of systems using Langfuse.

MCP server for writing structured traces, spans, and decisions, enabling observability and EU AI Act traceability compliance for AI agent tasks.

Enables LLM evaluation and observability by uploading documents, building test sets, running RAG pipelines, and automatically scoring answers for groundedness, hallucination risk, retrieval quality, latency, and cost, with tools exposed to MCP-compatible clients.

Enables MCP clients like Claude Code or Codex to administer a Bifrost LLM gateway's governance API, including virtual keys, teams, customers, budgets, provider configs, routing rules, model/pricing config, request-log observability, and core gateway config.

Enables MCP clients to query a modular RAG knowledge hub with hybrid dense/sparse retrieval, reranking, multimodal image support, and traceable observability, all through natural language tools.

Enables AI clients to retrieve study-abroad admissions knowledge through a local, pluggable RAG pipeline with hybrid search, reranking, citations, and observability. It provides MCP tools, document ingestion, and a Streamlit dashboard for managing and evaluating retrieval.

Connects to Elastic Agent Builder to enable AI-powered application health monitoring using OTEL metrics, traces, and logs from Elastic Serverless Observability.

Enables AI agents to query and debug Langfuse trace data, including traces, sessions, exceptions, route decisions, prompts, datasets, and metrics, for enhanced debugging and observability.

Enables AI agents and MCP clients to query trace, session, exception, prompt, dataset, score, and metric data for enhanced debugging and observability.

Enables AI agents and MCP clients to query Langfuse trace data for debugging and observability, with tools for traces, sessions, exceptions, routing decisions, prompts, datasets, scores, and metrics.

Enables AI agents and MCP clients to query Langfuse observability data locally, covering traces, observations, sessions, exceptions, route decisions, prompts, datasets, annotation queues, scores, and aggregated metrics. Supports selective tool-group loading and a read-only mode for safer debugging and triage workflows.

Enables AI agents and developers to query traces, sessions, exceptions, prompts, datasets, annotation queues, scores, and metrics for local debugging and observability. Runs locally over stdio or HTTP with selective tool-group loading, read-only mode, and compact or file-dump output to control token usage.

Enables AI agents and developers to query Langfuse trace data for debugging and observability, including traces, sessions, exceptions, route decisions, prompts, datasets, and metrics. Supports local stdio/HTTP access through MCP clients with selective tool loading and read-only mode.

Enables AI agents and developers to query traces, sessions, and exceptions for debugging and observability, alongside tools for prompts, datasets, annotation queues, scores, and metrics. Supports selective tool loading and a read-only mode for safer local access from any MCP client.