"A local-only document search tool" matching MCP servers:

A secure MCP server for Grafana that provides read-only access by default, with a separate write-capable command for mutations.

Provides a unified MCP server to interact with multiple middleware (Loki, MySQL, Redis, RocketMQ, Elasticsearch, MongoDB) through a desktop application for connection management and configuration export.

A secure, local-first MCP server for read-only inspection and troubleshooting of development environments, exposing narrow, typed, auditable capabilities for repository inspection, log summarization, Docker review, and security scanning without granting unrestricted machine access.

Enables read-only querying of a local Grafana Loki instance, providing log search, service listing, and health check capabilities.

Enables live tracing and observability of MCP tool calls, persisting execution traces to MongoDB and streaming them in real time to a dashboard.

Enables MCP-aware AI agents to query the local machine's health over stdio, retrieving CPU, memory, disk, and load-average metrics along with boot time and the top processes by CPU usage. It gives coding agents a structured, protocol-standard way to answer questions like whether it is safe to run a build or what is currently consuming resources.

Enables AI assistants to interact with local Docker containers, Kubernetes clusters, and system logs using the Model Context Protocol.

Enables an AI assistant to diagnose on-premise Windows pm2-managed Node/Nitro services by answering read-only questions about deployed builds, process liveness, logs, current configuration, and whether the running process started with the configuration currently on disk.

An enterprise MCP server scaffold that provides secure, governed access to internal tools through RBAC, audit logging, rate limiting, and prompt-injection boundaries, with a FastAPI control plane and OpenTelemetry observability.

Provides MCP tools to perform Looker health checks (health_pulse, health_analyze, health_vacuum) via the MCP Toolbox connector.

Enables safe, read-only interaction with Kubernetes clusters, allowing users to list resources and fetch logs without any create/update/delete operations.

MCP server that stream-parses NDJSON log files without loading them into memory — filter by pattern, detect error spikes via Z-score analysis, summarize severity timelines by time window.

Enables diagnosing Kubernetes clusters without creating or changing cluster objects, with tools to inspect health, workloads, events, storage, RBAC, custom resources, logs, and configuration.

MITM proxy MCP server that intercepts and verifies AI agent tool calls, detecting fabrication, tracking costs, verifying outcomes, and inferring user satisfaction.

Provides read-only access to OpenClaw and Codex operational data like status, tasks, sessions, logs, and Git changes. Ensures safety via redaction, allowlists, and bounded outputs.

Enables AI agents to diagnose Linux server incidents by collecting and structuring system diagnostics from multiple servers via SSH, with tools for finding incident clusters, gathering context (memory, CPU, swap, etc.), and running arbitrary commands.

Enables ingestion and full-text search of Windows application logs via MCP tools. Supports dual-backend indexing with Elasticsearch and SQLite for fast retrieval.

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.

Provides system hardware information (CPU, memory, storage, etc.) and system status (OS, network, resource usage) via MCP tools.

A comprehensive Linux system performance profiler with MCP remote invocation support, featuring advanced process profiling and flame graph generation.