"Servers Offering MCP Prompts as Prompt Primitives" matching MCP servers:

Enables inference engines to match longest common prompt token prefixes via a radix trie, so cached KV-cache blocks are reused instead of re-prefilled. This eliminates redundant prefill computation and lowers time-to-first-token, alongside paged attention allocation, speculative decoding verification, INT8 quantization, and latency telemetry.

Enables MCP clients to triage SOC alerts while enforcing a trust firewall across retrieval, memory, and privileged actions. It exposes tools for alerts, logs, memory, and alert actions, with defenses that refuse risky operations in the presence of attacker-controllable content.

MCP server exposing a fictional payment domain as tools, resources, and prompts, enabling reasoning over transactions, payment hubs, services, and system health.

MCP server that exposes OSSEC HIDS security monitoring capabilities as tools, resources, and prompts for AI assistants.

Hosted MCP server that exposes your self-hosted Bugsink error tracker as tools for LLMs, enabling issue management, release tracking, and stacktrace retrieval via chat prompts.

Enables benchmarking of Large Language Model APIs by measuring performance metrics such as generation throughput, prompt throughput, and Time To First Token (TTFT) with configurable concurrency levels and parameters.

Enables AI agents to use upstream MCP tools safely by scanning every tool result for indirect prompt injection and allowing, fencing as untrusted data, or blocking it while logging audit events.

Diagnose MCP servers — health checks, tool testing, token cost audits, conflict detection, and security scanning with 50+ prompt injection patterns. Works as CLI or MCP server inside Claude Desktop.

Enables agents to autonomously diagnose Linux performance issues by exposing production-debugging primitives such as perf, strace, /proc, flamegraphs, and eBPF as safe, structured, budgeted tools.

Enables classification of GPU workloads as training, inference, or idle from telemetry data, with tools for one-shot classification, benchmarking, and audit log verification.

MCP server exposing rlg (RustLogs) log files as tools for on-call / SRE agent workflows. Three tools over JSON-RPC stdio — tail_log (last N events, filtered by level/target), filter_log (predicate filtering), summarize_errors (grouped error taxonomy). Pure Rust. MIT OR Apache-2.0.

Provides read-only access to daily trading figures for multi-site restaurant groups, detecting anomalies in control blocks such as void rates and labor percentages to uncover subtle financial leaks.

Enables recurring website maintenance checks — domain registration, SSL certificates, uptime, technical SEO and accessibility — across a portfolio of client sites, using publicly available information. Results are returned as structured data and can be sorted by urgency into a client-ready report.

A local, read-only stdio MCP server that lets a Grok Build CLI agent check how much of its weekly SuperGrok / Grok Build usage pool is left, when the period resets, and its Extra Usage cap via tools like get_budget. It reads the existing grok login session and returns per-product figures as JSON, mirroring the TUI /usage screen, so agents can pause before expensive work when quota runs low.

Enables a Claude Code agent to fetch remaining 5-hour and weekly subscription usage limits, reset times, and per-window breakdowns as JSON. It provides the same figures as /usage through a local, read-only tool.

MCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.

An MCP server that exposes a dbt project's run state as tools, enabling AI assistants to answer questions like 'is the warehouse healthy?' or 'what broke and why?' via plain English, using read-only access to dbt artifacts and warehouse data.

Provides AI assistants with read access to Clamp analytics data including pageviews, visitors, referrers, and custom events. Enables traffic analysis, conversion funnel evaluation, and metric alerts through natural language queries.

A lightweight npm MCP server for deep Redis diagnostics, offering tools for memory, slowlog, clients, keyspace, latency, and config analysis with AI-powered recommendations.

Exposes an observability REST API as MCP tools, enabling incident investigation through automated correlation of deploys with errors, log and metrics queries.

Pull open jobs from Workday, Greenhouse, Lever and Ashby career sites as normalized JSON with one tool call. Change tracking returns only jobs added, edited or closed since the previous run. Calls the hosted Apify Actor: set APIFY_TOKEN; tool calls are billed pay-per-event on Apify. No browser, login or proxy.

Registers a set of inert, tempting decoy tools with any MCP-capable client so that any call from a hijacked or prompt-injected agent instantly raises an alert with full attack context and a per-call trace token. Also plants worthless canary tokens in honeypot files that trigger zero-false-positive leak alerts when they surface in agent output, files, or outbound requests.

Enables Claude to discover and understand infrastructure-as-code drift by listing projects with drift, analyzing Terraform plan outputs, and providing remediation information.

MCP server for Smart Compost platform that lets LLM agents list composting processes/devices and pull measurements as read-only tools.

Exposes network-monitoring tools (query metrics, analyze windows, compare, logs, status, runbooks, speed tests) as an MCP server for agentic workflows. Designed with evaluation suites, cost-aware model routing, and semantic tool retrieval.

An MCP server for Grafana Loki that enables LLMs to query, tail, and analyze logs, featuring fuzzy container-name matching, compact output, and tools for log patterns, volume, and label discovery. It can run as a local stdio server or a containerized HTTP service.

More than just an MCP server that covers the entire range of Docker management tasks, it helps you create workflows to easily manage your Docker environments at scale. It allows you manage multiple local or remote (TCP, TLS, SSH) docker instances and exposes things like logs and stats as resources so that you can monitor and triage all of them.

Health doctor for a home AI stack (Ollama nodes, GPUs, tailnet) with graded confidence, as a CLI, an MCP server and a DSH plugin.

MCP server exposing SuperAudit’s free website audit as a callable tool, enabling AI agents to audit any public URL and receive scores across SEO, security, legal, performance, and more. No API key required; respects rate limits and caches results.

Enables AI assistants to triage an Atera help desk by ranking open tickets with plain reasons, summarizing site health and alerts, and producing a one-call morning brief. It redacts personal data, fences user-written text as untrusted, and stays read-only unless writes are explicitly enabled.