#observability

Connect AI assistants to AppAmbit — the command center for your mobile & desktop apps. Query real-time analytics, sessions, and crash reports; read and push remote config; send push notifications, provision and query managed per-app SQLite databases, deploy serverless Cloud Code functions; and manage a headless CMS. Also generates SDK setup snippets and runs integration diagnostics. Supports .NET MAUI, Swift, Objective-C, Android and more. Built for indie devs, mobile teams, and agencies.

A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.

Give your coding agent live production context from HeronSignal: read frontend errors, logs (with structured attributes), sessions, funnels, performance, and health — plus list and resolve error issues, over MCP.

Operate Drumbeats monitoring from any AI client — create cron/heartbeat and uptime monitors, triage incidents, and run HTTP/SSL/DNS diagnostics (no account needed for diagnostics).

Check your AI agents' cost, errors, latency & quality — and fix issues — from Claude or Cursor.

Drives a browser - or a native Expo/React Native app on iOS/Android - and your dev server, putting both on one correlated timeline so a browser console error and the backend stack trace from the same moment line up. For Claude Code and AI agents.

Open-source MCP server and PreToolUse hook for Claude Code. Exposes 15 MCP tools that let Claude inspect its own context-hygiene stats mid-session (token waste, duplicate reads, drift, cost forecasts), and caps verbose tool output plus dedups same-session file re-reads to keep context clean. Zero network calls in normal use; all local.

Turn any API or database into agent-ready MCP tools — minimal tokens, structured errors, full observability.

DebugBundle turns runtime failures, critical-path issues, and availability checks into incidents with full context, alerts, remote probes, and deterministic debug bundles for humans and AI agents.

Manage and debug your webhooks from your AI assistant

Cirdan maps and watches the live infrastructure your agent session can reach — Docker, Kubernetes, cloud, IaC, and telemetry — then exposes it over MCP. It fingerprints the environment, builds a dependency graph, detects incidents, and can run evidence-backed actions. It inherits the session's own access and never escalates beyond it.

Hosted, read-only MCP server for Auralogs production logs. Agents search logs, inspect errors with full stack and metadata, and review AI analyses (diagnosis, suggested fix, PR link) over Streamable HTTP with a project-scoped read key. Free tier: 10,000 logs/month.

MCP-native AI SRE. Aient exposes your production OpenTelemetry problems, traces, and logs over the Model Context Protocol, plus an AI remediation loop that opens a reviewed GitHub fix PR and verifies in production (reopening on regression). Tools: list_problems, get_problem, query_traces, detect_anomalies, request_problem_remediation. Remote streamable-HTTP at https://aient.ai/mcp; auth via OAuth (scopes aient.mcp.read / aient.mcp.write). Human-in-the-loop by default. Request access at aient.ai.

Simulate and evaluate voice & text agents from your editor. Generate synthetic-user "Drivers" from your codebase, run multi-turn simulations against your agents, and pull back transcripts, traces, and scores without leaving your AI assistant.

MCP server for Tessera's LLM cost-optimization layer. Anchored spend, drift detection, recommendations as typed tools.

Curated by Archimedes Market. AWS Cost Explorer + Anomaly Detection exposed as MCP tools. Surface unusual spend by service, account, or tag. Pull cost breakdowns, forecasts, savings recommendations. Read-only IAM — refuses to start if the role can modify resources. → archimedes.market/assets/d63f367d-79e5-488c-9e60-b7ba89fd3f91

Curated by Archimedes Market with a verified Trust Report (security, quality, license, complexity). Read-only PostgreSQL analytics agent exposed as an MCP server. Inspect query plans, surface slow queries, audit index usage, detect table bloat, and report vacuum status — without any DDL, DML, or write access. Designed to drop into a production database safely. → Full Trust Report: archimedes.market/assets/aa632521-f830-4adf-9828-7c6079e06a83

MCP server for uptime monitoring, incident management, alerting, and dependency status tracking. Gives AI agents tools to create and manage HTTP/DNS/TCP/ICMP monitors, handle incidents, configure alert channels, and query third-party service health.

Query LCP, INP, and CLS field data from real visitors. Three tools: get_metrics, get_timeseries, get_histogram. Filter and group by device, country, page path, browser, OS, and 20+ dimensions. All data is real user monitoring (RUM) at the p75 percentile, the standard Google uses for Core Web Vitals ranking signals.

Verify AI agent tool calls with content-addressed, HMAC-attested receipts. Free third-party verification API for AI agents. Call verify_action(claim, evidence) to get an independent integrity check on whether your claimed action matches the actual evidence. Useful for catching silent failures: incorrect SQL operations, file-op mismatches, API call inconsistencies, and code-diff scope creep. Five specialized verifier kinds: - code_diff: verb / path / identifier coherence with unified diff - db_op: row delta + SQL operation + ID match - file_op: existence state + line/size delta - api_call: request body and response status coherence - generic: conservative fallback Returns: - aar_verdict: verified | contradicted | insufficient_evidence | unsafe_to_verify - verdict: ok | mismatch | uncertain (legacy 3-value alias) - reasoning, confidence - receipt: verify_action_receipt.v0 with HMAC-SHA256 signature, content-addressed via SHA-256 hashes of claim and evidence Cross-vendor: works with Claude Code, Cursor, Cline, Codex, Codeium, and any MCP-compatible harness. Stateless, per-request, no API key, no registration. Pure Python stdlib (no pip install). Anonymized telemetry only — no PII, no model fingerprint, no raw claim/evidence retention. Honest scope: this is a small reference implementation, not a canonical inter-vendor standard. v0 receipts use HMAC-SHA256 (symmetric, single-issuer); v1 with ed25519 + multi-issuer is on the roadmap. The hosted endpoint has no SLA — self-host for stability (git clone && ./start.sh). 90-day probe with explicit kill criteria. If adoption appears, v1 schema work begins. If response is null, the null is itself a publishable data point.

Lightrun MCP connects AI coding assistants to live runtime context from production and staging applications for safe code-level debugging without redeploying. It lets MCP-compatible clients discover runtime sources, inspect live expression values, capture call stacks, measure execution duration, count executions, and collect numeric runtime metrics directly from the AI workflow.

Selvedge is a local, open-source MCP server that captures the *why* behind every change AI coding agents make — live, in the moment, from the agent's own context (not inferred later by a second LLM). It logs the entity (DB column, table, function, route, env var, dependency), the diff, and the reasoning to a local SQLite store, then reads it back: `selvedge blame users.email` returns the most recent change + the original reasoning, and `prior_attempts` lets the agent check "was this tried here before, and how did it turn out?" before editing. 8 MCP tools: log_change, diff, blame, history, changeset, search, prior_attempts, stale_decisions. As of v0.3.9 it also exports Agent Trace v0.1.0 records (`selvedge export --format agent-trace`) for cross-tool interop. Zero-config and local-first (no telemetry, no network, no LLM calls in core), Python 3.10+, MIT.

Cross-cloud observability for AI agents. Discover resources, correlate logs, and diagnose infrastructure issues across AWS, GCP, Vercel, and Cloudflare — without leaving your editor.

Data observability for engineering teams: alerts, freshness monitoring, schema drift detection, validity rules, lineage. Connect any MCP client (Claude Code, Cursor, Claude Desktop) via 53 structured tools across Snowflake, BigQuery, Postgres, Databricks, Redshift, ClickHouse, MySQL, SQL Server, Athena. Hosted at mcp.anomalyarmor.ai/mcp with OAuth 2.1, or run locally via `pip install armor-mcp` with an API key.

Non-invasive AI Agent operation monitoring — audit every API call your agent makes to Shopify, Meta Ads, and more. Real-time alerts, audit logs, and operation history. Works with Claude Desktop, Cursor, and any MCP-compatible AI tool.

Full MCP server for the Portkey AI Gateway Admin API. 151 tools for managing prompts, configs, virtual keys, analytics, guardrails, integrations, and more from any MCP client.

The first MCP-native eval and observability tool for AI agents. Any MCP-compatible agent discovers and uses Iris automatically — no SDK, no code changes. Log traces with hierarchical span trees, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track what your agents are actually doing and costing you. Real-time dark-mode dashboard, OpenTelemetry-compatible span structure, self-hosted with SQLite. MIT licensed.

MCP server for Valkey and Redis observability. Query real-time health, slow commands, hot keys, anomaly detection, and cluster analytics directly from your AI assistant.

eBPF-based GPU causal observability agent with MCP server. Traces CUDA Runtime/Driver APIs and host kernel events to build causal chains explaining GPU latency

Structural observability for AI conversations and financial risk management. 17-channel pattern detection, loop/convergence/scattering detection, and OHLCV risk overlay with 31/31 validated drawdown reduction.

MCP server for the CI-1T prediction stability engine. 20 tools + 1 resource. Evaluate model stability, probe any LLM for instability (BYOM - bring your own model), manage fleet sessions, detect drift, generate visualizations, and control API keys. 7 tools work locally with no auth or credits. 1,000 free credits on signup.

MCP server for https://oathe.ai security audits. Runtime behavioral analysis and security scanner for AI systems. Check trust scores before installing MCP servers, plugins, or AI agent skills.

ShellGuard is an MCP server that lets LLM agents securely SSH into remote Linux hosts with read-only shell access. Instead of copy-pasting terminal output, your AI can run safe diagnostics, inspect logs, query systems, and troubleshoot production, staging, or dev environments autonomously. All commands are parsed, validated against a strict allowlist, and executed with timeouts and output limits—blocking destructive operations while guiding the LLM to safe alternatives.

AI/ML-powered diagnostic engine for SRE Observability on Konflux and OpenShift. It uses the Model Context Protocol (MCP) and 40+ tools to analyze logs, metrics, and traces, enabling automated RCA and predictive analysis.

Co-create schemas with your AI — typed fields, relationships, SQL-like constraints. Turn unstructured content into a curated database built for insights. Platform integrations such as PostHog and Microsoft built-in and expanding. Any HTTP API via OpenAPI import. One MCP connection gives your agent full CRUD, semantic search, and a structured knowledge base that grows correctly over time.

Production-ready Langfuse MCP Server with 28 tools for LLM analytics, cost monitoring, and dataset management. Features secure dual-mode operation (readonly & readwrite), real-time cost analysis, trace debugging, and comprehensive usage insights. Deploy instantly with npx for seamless Claude Desktop and other LLM Client integration.

Run NRQL, NerdGraph, and REST v2 operations to query data, manage incidents, create synthetics, and annotate deployments — all from your MCP client. A full‑featured New Relic MCP server that goes far beyond basic NRQL. It exposes safe, typed tools for APM discovery, alert policy/incident workflows (including acknowledge), entity search and deep details, creating Synthetics Browser monitors, and New Relic REST v2 coverage for deployments and metrics with region awareness and auto‑pagination.

The Signoz MCP Server lets you connect developer tools like Cursor or Claude Desktop to your Signoz instance. It's an open-source project maintained by DrDroid (not affiliated with Signoz), and allows you to query logs, dashboards, metrics, and more — making observability data directly accessible within your IDE or AI assistant.

The AgentOps MCP server provides access to observability and tracing data for debugging complex AI agent runs. This adds crucial context about where the AI agent succeeds or fails.

🔌 Complete MCP server for Zabbix integration - Connect AI assistants to Zabbix monitoring with 40+ tools for hosts, items, triggers, templates, problems, and more. Features read-only mode and comprehensive API coverage.

Learning what it means to use MCP by trying to interact with Dynatrace MCP server.

A Model Context Protocol (MCP) Gateway. Serves as a central management point for tools, resources, and prompts that can be accessed by MCP-compatible LLM applications. Converts REST API endpoints to MCP, composes virtual MCP servers with added security and observability, and converts between protocols (stdio, SSE).

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

The implementation of Model Context Protocol (MCP) server for VictoriaMetrics

MCP server template based on the Yokai Go framework.

让AI助手直接分析你的Grafana监控数据 - A Model Context Protocol server for Grafana data analysis

Nody provides a powerful MCP Composer for creating and managing custom MCP servers. It enables you to personalize each tool's name and description to add context, helping agents use them with fewer tokens. It manages the configurations and secrets of MCP servers in one secure place, making it easier to deploy and scale your AI toolsets efficiently.

Provides access to your VictoriaMetrics instance and seamless integration with VictoriaMetrics APIs and documentation. It can give you a comprehensive interface for monitoring, observability, and debugging tasks related to your VictoriaMetrics instances, enable advanced automation and interaction capabilities for engineers and tools.

MCP server template based on the Yokai Go framework.

Simple, modular, and observable Go framework for backend applications.

Metoro MCP Server

MCP server for Dynatrace Observability

The Digma MCP Server uses a dynamic code analysis engine to leverage the data in your APM dashboards (Datadog, Grafana, NewRelic etc.) in order to assist the AI agent during code reviews, code and test generation, fix suggestions, etc. It enables the agent to drive performance improvements and cost reduction. Features: - Highlight risky code in the PR and provide impact visibility - Assess the proposed code based on real performance requirements - Highlight the code areas that would have the most impact when optimized - Automatically identify and fix performance bottlenecks, ineffcient queries, scaling problems and other issues

The Rollbar MCP Server implements the Model Context Protocol (MCP), letting you run Rollbar-compatible agents in local or custom environments.

Observability helps. This MCP server adds tracing to all your conversations on Claude (or suitable MCP client) so that you can trace, understand, debug and report on your all your interactions.

Last9 MCP Server

Mirror of