"How to review merge requests in GitLab" matching MCP servers:

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

Lets an assistant read recorded production AI agent runs — steps, model and tool calls with arguments, and outcomes — along with the findings of comparison runs that checked a prompt or model change against those recordings, and verify a signed evidence bundle offline with no account or network. It is strictly read-only: no tool starts a replay or comparison, so nothing can spend money or act without a person deciding.

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.

Enables MCP clients to read console logs and network requests from a connected mobile H5 page and, with explicit user authorization, execute JavaScript in that page.

MCP server for monitoring health of MCP servers, GitHub Actions, GitLab pipelines, and HTTP endpoints with health history, TLS expiry, assertions, diagnostics, and alerts.

Enables AI agents to inspect a live Celery deployment over RabbitMQ or Redis — checking which workers are responding, their pools, concurrency and consumed queues, and how many messages are backed up in each queue — so agents can diagnose stuck or unrouted tasks. Read-only by default, with broker credentials masked in all output.

Enables read-only, stack-aware diagnostics for microservices on Kubernetes, turning debugging runbooks into conversational tools that investigate slow requests, changes, leaks, and in-pod conditions without exposing cluster credentials.

Enables grading a website's security headers with per-gap fixes and a README badge, and analyzing logs, code, configs or suspicious messages to determine what happened, how severe it is, and what to fix first. Requests are masked for sensitive data and automatically retried across multiple AI providers when one refuses, subject to a defensive-use-only policy.

Analyzes how search engines and AI systems discover, crawl, cite, and convert traffic via CLI and MCP tools.

A Model Context Protocol server that connects to Veeam Backup for Microsoft 365 to review backup configuration, find protection gaps, and optionally run jobs and restores with opt-in safety controls.

Enables signed-in users and organizations to discover and execute read or owner-confirmed write operations for monitoring sites, TLS certificates, traffic, suspicious requests, HTTP errors, Docker/Podman workloads, storage, data services, jobs, and node health. It connects through OAuth authorization code with PKCE and supports incident and TLS review prompts.

An MCP server that records agent execution metrics and exposes a Context Window Explorer to visualize exactly what entered the model's context window across sessions, tokens, and tool calls.

Provides cryptographically signed, tamper-evident compute usage receipts via a Model Context Protocol server, exposing tools to record usage, verify receipts, list the ledger, and verify ledger integrity without requiring any account, API key, or single cloud provider.

8 standalone MCP servers for SMBs — Guardrails (prompt injection, PII, secrets detection), FinOps (AI cost tracking and budgets), Observability (agent tracing), Smart Router (17+ models, 9 providers), Trust Score (governance scoring 0-100), Memory (persistent agent memory), ThinkSecure (runtime security + SOC2/GDPR audit), and A2A Lite (agent-to-agent protocol). 37 tools total, TNC credits

Web analytics and AI session replay for agents: visitors, breakdowns, funnels, goals, revenue attribution, and AI-found site issues. Connects to the hosted Flowsery MCP server.

Provides MCP tools to create and query SigNoz trace funnels, enabling agents to measure their own step conversion rates from within the agent loop.

MCP server for Kibana / Elasticsearch — log search, aggregations, index discovery, and dashboard browsing. Hits Elasticsearch REST API directly for log queries; falls back to Kibana Console proxy when no direct ES URL is configured. Supports ApiKey auth (best for agents), Basic auth, and anonymous access. All 5 tools are read-only (readOnlyHint: true). Returns structured JSON (outputSchema).

Tells an agent what went wrong with its own Ollama calls, in sentences with the fix: lost prompt cache and where the prompt stopped matching, context overflow, a model running partly on CPU, tool schemas crowding the prompt. Also the last turn in numbers and which local models fit in video memory. Local, read-only, nothing leaves the machine.

Provides Claude with read-only access to PC diagnostics including hardware specs, live performance metrics, disk usage, network checks, and more, enabling natural language queries about PC health and performance.

MCP server for measuring web performance with Google PageSpeed Insights, providing median scores with uncertainty and real-user data. It offers tools for scores, diagnostics, and comparisons to identify regressions.