A framework for building MCP servers with built-in enterprise capabilities such as authentication, authorization, telemetry, audit logging, and data classification, allowing domain developers to focus on business logic while maintaining governance and compliance.
Exposes homelab and IT-ops tools to Claude, including system health monitoring, Grafana alert states, Docker container status, Loki logs, SMART disk health, and more.
Enables AI clients to perform safe, read-only IT diagnostics and retrieve local runbooks, asset records, and knowledge articles through MCP, with allowlisted network checks and audit logging.
An MCP server that provides cost and reliability observability for LLM and agent workflows. It records model calls and allows querying and aggregating telemetry data through MCP tools.
Um servidor MCP completo para integração com Sentry no Cursor, oferecendo 27 ferramentas para monitoramento de erros, performance e saúde de aplicações.
Enables tracing mcp-use tool callbacks and capturing tool errors and exceptions in Sentry via MCP middleware, without SDK changes or additional services.
Screens AI agent tool calls before execution and tool results before the agent reads them, acting as an MCP proxy and hooks adapter with shadow, enforce, and strict policy modes.
A read-only MCP server that exposes local coding-agent session logs as three tools for introspection of recent work, debugging tool failures, and tracking token usage and estimated cost without parsing log files.
Fetches Langfuse observability traces directly into a VS Code coding agent's context, enabling querying and viewing trace data through natural language.
Cryptographic accountability for AI agents. Ed25519-signed receipts for every MCP tool call. Constraints, chains, AI judgment, invoicing, and local dashboard included.
Enables interaction with Google Cloud services including billing cost analysis, log querying, and metrics monitoring through natural language commands. Provides comprehensive tools for managing GCP resources, analyzing costs, detecting anomalies, and retrieving operational insights.
It enables agents to discover Rapid7 InsightIDR log sets and logs, run LEQL searches and analytics, and follow paginated results for natural-language investigations.
Provides AI agents with a transparent proxy and journal for every tool action, including pre-state snapshots and approval gates for risky operations. Enables per-action undo, rewind to a point in time, and a kill switch that agents cannot override.
Enables AI agents to self-report every tool call, token usage, decision, and session grade into a local SQLite store, so users can trace execution, audit reasoning, and see per-session costs in a local dashboard. Also supports proxy mode to intercept and trace MCP tool invocations for agents that cannot self-report.
An MCP server that provides append-only, tamper-evident local receipts for AI agent actions, capturing command executions, outputs, and handoff evidence.
Enables a telecom support assistant to look up customers, check balances and orders, suspend lost SIMs, open tickets, and analyze SIP traces to diagnose call failures.
Enables agents to spawn, monitor, and control CLI coding agents running in isolated tmux sessions, with verified input injection, redacted pane capture, fleet and per-session state classification, lineage tracking, blocking exec with exit codes, cross-agent messaging, waste analytics, and log/ledger reading. Ownership checks, policy controls, and audit events keep every control action safe by default.
Provides five read-only tools for AI agents to inspect host system information, memory, disk usage, log tails, and overall health. Enforces path allowlisting and rejects credential-like files to keep local inspection safe and constrained.
Tripwire detection for autonomous AI agents. Plants honeypot files, MCP tripwire tools, and API decoy endpoints to log agent scope creep and unauthorized tool use with full forensic context.
Exposes an MCP interface over a JSONL event stream so agents can query a run summary (task/step success rates with confidence intervals and per-success cost), drill into a single task's step-by-step detail, or pull a risk list of over-granted permissions and policy conflicts. Lets an agent check its historical success rate and true cost for a task type before starting work.
Provides a local MCP interface to query captured, PII-scrubbed prompt telemetry from coding agents and browser chats, enabling time summaries, prompt search, and activity analysis without data leaving the machine.
Enables AI assistants to search, analyze, and debug application API traffic captured by Tusk Drift, including HTTP requests, database queries, distributed traces, latency metrics, and error rates.
Provides cost analysis of AI agent usage by previewing scrubbed metadata before upload and analyzing spend, cache-hit rates, and waste recovery through a local or remote server.
Enables LLM agents to discover and invoke guarded web search, read-only SQLite queries, and sandboxed file read/write tools over the Model Context Protocol. It adds schema validation, rate limiting, output sanitization, request-ID logging, and Prometheus metrics at the protocol boundary.
MCP server for AI agent observability, providing trace and span logging, search, latency/tokens/cost metrics, and anomaly detection using an in-memory buffer.
Enables AI agents to manage prompts and sessions via the ai-agent-logs API, with tools for health checks, login, listing/creating prompts, and retrieving sessions.
agent-bom is an open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure. The default scan profile in MCP server mode exposes 8 MCP tools. Additional profiles provide inventory, findings, compliance, graph, and runtime workflows. See the published Glama release for its packaged version.
Enables agents to report and query performance metrics to build a community-driven quality database for MCP tools. This server helps agents discover and select the most reliable tools based on success rates and user-reported quality scores.
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.
Read-only MCP server for one Docker host: list containers, inspect (without env vars), logs with time windows and search, stats and events. Cannot start, stop, remove or exec.
MCP server that provides structured audit logging for AI agent repair tasks via tools to start, record, end, query, and export event traces, with JSONL persistence and SDK integration.
Enables AI agents and their hosts to record actions, tool calls, and human approvals in an append-only, hash-chained log; verify tamper evidence; mask secrets; retrieve recent events; and export audit-ready JSON or CSV on self-hosted infrastructure.
Enables LLM clients to access DevSecOps tooling such as CI/CD pipeline status, vulnerability triage, log search, and dependency scanning through MCP, turning AI copilots into security-aware engineering partners.
MCP server for monitoring, diagnosing, and auto-correcting observability issues across platform services, integrating with Sentry and PostgreSQL for error tracking and billing pipeline health.
Enables MCP clients to list chaos outage scenarios, trigger autonomous multi-agent investigations of AWS and Kubernetes incidents, and retrieve generated SRE post-mortem reports.
Read-only MCP server for TrueNAS Scale debugging, providing k3s tools for kubectl operations and whitelisted midclt calls for system info, apps, and pools.
Enables AI agents to work with business-document data through MCP tool calls constrained by a registry, data tiers, human approval for writes, and a tamper-evident audit log. Ships with saved evals and a dashboard to prove and inspect those controls.
A read-only observability server that lets external agentic AI clients query CPU, memory, load, uptime, allowlisted filesystem capacity, bounded process snapshots, and permitted journald logs. It also provides a JSON system summary resource and a safe health-check prompt, with no arbitrary shell or destructive operations exposed.
Enables developers to register sync or async MCP tools that are automatically protected by context-budget guards, including DataFrame blockades, payload truncation, and log-line capping. Each invocation is wrapped with correlated trace IDs and fail-closed error envelopes, and the server can be mounted as an SSE endpoint inside a FastAPI application.
MCP-based production monitoring agent for manufacturing OEE, providing real-time monitoring, downtime root-cause analysis, and automated alerts through integration with SQL Server, MES APIs, and incident management systems.
Provides structured MCP tools for local runtime observability and debugging of React Native/Expo apps on Android, enabling evidence-first diagnostics such as screenshots, UI trees, per-request network capture, performance metrics, and CDP-based console/heap/profiling exports.
This server enables coding agents to share local memory and receive scoped task context. It provides live visibility into agent operations and allows the application of structured project skills.
MCP server providing read-only operational tools (logs, metrics, traces, service health, config) for troubleshooting an environment, with one exception for toggling chaos scenarios.