"Toggl Track" matching MCP servers:

MCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.

Enables AI agents to push and read metrics from EzStat, track counters/gauges, and ask natural-language questions about telemetry.

Fetches Langfuse observability traces directly into a VS Code coding agent's context, enabling querying and viewing trace data through natural language.

Local, payload-free AI cost visibility for agents. Track spend by model, route, customer, or tagged work without storing prompt or response bodies.

Enables analyzing coding-agent session transcripts to measure tool efficiency, detect loops, track test outcomes, and report costs, with MCP tools for listing sessions, analyzing sessions, finding loops, and generating cost reports.

Enables MCP-compatible coding agents to debug applications using runtime log data, by providing tools to start a local log-ingestion server, track debugging sessions and hypotheses, and correlate logs to specific executions.

A MCP server for tracking AI usage metrics and structured logs across applications. Monitor model calls, analyze usage patterns, track costs, and debug AI interactions.

Enables recording and querying MCP tool call traces, including latency, failures, and token costs, per agent run.

An MCP server that monitors and provides analytics on weekly report submissions in a Google Sheet, allowing users to check missing submissions, view statistics, and track individual reporting status.

Enables local-first observability for MCP agent workflows by recording tool calls, prompts, latency, and token usage in a local SQLite database, and provides tools for inspecting, comparing, exporting, and generating dashboards from traces.

Analyzes AI agent traces to diagnose failures, score performance, and provide actionable fixes using tools like judge_trace and trace_breakdown.

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

Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.

Provides an append-only event ledger with MCP tools for workspaces to report completion receipts, query recent events, generate situation reports, and track focus changes.

Enables interaction with the Bigeye Data Observability platform to query data quality issues, analyze data lineage and dependencies, track AI agent data access patterns, and perform root cause analysis for data issues.

Enables tracing of synthetic events through a toy Redis Streams + Postgres ingestion pipeline, answering questions about which events were dropped, duplicated, delayed, or are in flight, plus overall pipeline health. It also supports first-class fault injection and reconciles observed pipeline state against independently recorded producer ground truth to expose real loss or silent failures.

Enables users to manage project-owned operation registries, instrument services end-to-end with OpenTelemetry, analyze traces, and browse a GUI catalog through an MCP App.

Enables AI agents to perform one-shot triage of Playwright trace files, pinpointing root causes like backend API failures or locator issues and generating self-healing code fixes in a single low-token call.

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

Tracks a user's activity by trace ID from application logs stored in ClickHouse. Provides tools for log timeline, trace summaries, and search across services.