"Understanding Boss Mode" matching MCP servers:

Enables agents to interact with the Logflare API by writing JavaScript functions that run in a Vercel Sandbox, using three tools: search, execute_read, and execute_write.

A Model Context Protocol server for Zoho Site24x7 that uses a JavaScript sandbox to execute API calls, enabling management of monitors, accounts, and MSP/BU tenancy through natural language.

Diagnoses Postgres job queues (pg-boss, graphile-worker) to identify retry storms, stuck jobs, missed schedules, and other issues, providing evidence-based recovery steps.

MCP server for safely exposing SQL Server database capabilities to LLM clients, with read-only mode, security features, and observability.

MCP server that provides read-only analysis of Claude Code session transcripts, enabling queries about project activity, session details, and tool usage.

An MCP server that enables natural language querying and troubleshooting of Kubernetes clusters, supporting multi-cluster switching and providing tools for pods, nodes, events, and logs.

Enables secure, governed interaction with DMTF Redfish-compliant BMCs (iDRAC, iLO, etc.) via MCP, with read-only default and write operations gated behind explicit write-mode elevation and dry-run confirmations.

Enables AI agents to query Oracle WebLogic Server runtime state, health, and JVM metrics through the REST management API, and to start, shut down, or force-shut-down servers via Node Manager, all under a least-privilege account with allowlisting, read-only mode, and JSON audit logging for every call.

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 AI assistants to interact with self-hosted Dynatrace Managed environments to retrieve observability data, security insights, and performance metrics. It allows users to query problems, logs, events, and SLOs through natural language interfaces in both local and remote modes.

Maintenance, recovery, and observability for Claude Code. CLI + MCP server + dashboard.

Enables AI agents to query MQTT message history stored in SQLite, including topic inventories, last values, historical data, silent devices, and collector connection gaps. Supports publishing messages when write mode is enabled.

Governed, read-only OT data tap for substation and utility telecontrol — IEC 60870-5-104, DNP3/IEEE 1815, and IEC 61850 MMS connectors with cross-protocol asset discovery, alarm and downtime RCA, unbypassable audit logging (MCP + CLI), budget/runaway guards, and an airgap no-egress mode. Energy edition of Industrial-AIOps, built on iaiops.core.

Enables querying Wazuh 5 agents, groups, cluster status, MITRE techniques, events, findings, and vulnerability state through the manager and indexer APIs, with optional agent restart when read-only mode is disabled.

Enables Claude Desktop to interact with 57 AWS services using over 200 tools and local machine profiles. It supports multi-profile configurations and features a read-only safe mode by default to manage infrastructure like EC2, S3, and Lambda securely.

An MCP server that connects AI assistants to the ThreatLocker Portal API with 44 tools for managing computers, approvals, action logs, tags, maintenance mode, and more across single-org and multi-tenant setups.

Enables interaction with FireHydrant's incident management API through the Model Context Protocol. Provides programmatic access to FireHydrant's features for managing incidents, retrospectives, and operational workflows.

A remote MCP server that enables real-time interaction with the Dynatrace observability platform, bringing production-level monitoring data directly into development workflows.

Provides structured, tool-based access to a Honeybadger account's API, enabling users to browse projects, inspect faults and notices, work with dashboards, alarms, and check-ins, and retrieve reference documentation such as BadgerQL. Runs in read-only mode by default, with optional write and delete operations, and can connect either through the hosted OAuth endpoint or a self-hosted stdio/Docker deployment.

Enables monitoring and management of an Unraid server in plain English from any MCP client, covering array, parity, disks, Docker, VMs, ZFS, shares, logs, UPS, notifications, and more, with destructive actions gated behind explicit confirmation and an optional read-only mode.

Enables AI assistants to control a local Clash Verge Rev / mihomo core on Windows over its named-pipe controller, discovering the live pipe automatically so it works in both sidecar and service mode. Supports inspecting status, switching proxy nodes, latency testing, changing modes, viewing connections and rules, and updating providers.

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.

Surface Claude Code token usage, estimated cost, and plan-limit status in any MCP client. Enables agents to query usage data from local logs and Anthropic API.

Enables read-only access to operations and telemetry data across 12 domains through 45 agent tools, including asset inventory, metrics, outages, incidents, and platform settings, with support for AWS SigV4-signed live access and a fixture-based mock mode that runs without a backend.

MCP server analyzing Windows ETW (.etl) traces — 54 tools spanning CPU/wait stacks, image-load gaps, file/disk/mmap I/O, VirtualAlloc, network, registry, ALPC, DPC/ISR, CLR (GC/JIT/alloc/exception/contention), NT heap, and any user-mode ETW provider. Domain-neutral; works on any Windows trace.

An MCP server that enables AI assistants to query and explore your OpenObserve observability data. Provides read-only access to logs, metrics, and traces for analysis and troubleshooting.

Enables AI assistants to inspect, query, and diagnose issues within an Octopus instance, and to create releases, deploy them to environments and tenants, and run runbooks. Connects via stdio with API key or short-lived token auth, offering selectable toolsets, a read-only mode, and a structured REST backstop.

Enables token counting, usage tracking, and cost calculation for LLM APIs, with a proxy server mode to automatically intercept and monitor API requests from clients like Cursor and Windsurf.

A self-hosted governance layer for MCP servers that enforces policies, audits tool calls, and manages approvals for AI agents.

Claude Code token usage and cost visibility for MCP-capable agents.

Enables AI agents to locally query and debug traces, sessions, exceptions, route decisions, prompts, datasets, and metrics from any MCP client. Supports token-efficient output control, selective tool-group loading, and a read-only mode for safer access.

Enables AI agents and developers to query Langfuse telemetry locally, fetching traces, sessions, observations, and exceptions, inspecting route decisions, and running metrics, prompt, dataset, and annotation-queue operations. Supports selective tool-group loading and a read-only mode for token-efficient debugging from Claude Code, Codex, Cursor, or any MCP client.

Read-only MCP server that surfaces UniFi network data from a UCG-Fiber console to Claude, enabling monitoring of hosts, sites, devices, clients, ISP metrics, and device stats via read-only API tools.

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 MCP clients to locally debug Langfuse data through first-class tools for traces, observations, sessions, exceptions, route decisions, prompts, datasets, annotation queues, scores, and metrics. Supports selective tool-group loading, compact or file-dump output, and a read-only mode for safer exploration from Claude Code, Codex, Cursor, or any MCP client.

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.

Echo tool MCP server that extracts and logs W3C Trace Context from requests to verify propagation from Claude Code.

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.

Enables AI agents and coding assistants to query trace, session, exception, routing, prompt, dataset, score, and metric data from a Langfuse instance for debugging and observability. Offers selective tool-group loading and a read-only mode to control token overhead and write access.