"Understanding the Concept of LLM Context" matching MCP servers:

An MCP server that records agent execution metrics and exposes a Context Window Explorer to visualize exactly what entered the model's context window across sessions, tokens, and tool calls.

MCP server providing lossless file reads with deduplication, per-repo token metering, and HMAC-signed context receipts. Enables auditable, vendor-neutral measurement of what an AI agent saw.

MCP server providing deep PostgreSQL context to AI assistants, including schema DDL, index health, foreign key associations, query execution plans, and performance statistics via read-only tools.

Enables offline, read-only forensic analysis of Claude Code session transcripts, providing exact token usage, cost estimates, context growth, and compaction suggestions.

Enables autonomous context window management, prompt caching, token optimization, and real-time observability for AI coding agents across multiple IDEs, reducing token costs and improving performance.

MCP server for tracking LLM costs, setting spending limits, and receiving budget alerts directly within AI editors via slash commands like /guard.

Enables assistants to read-only explore and analyze Grafana dashboards and data sources, execute queries against Prometheus and Azure Log Analytics, and run guided investigation workflows.

Enables AI agents to access real-time Windows PC context including active window, system performance, screen time, productivity analytics, and historical usage through MCP tools.

Windows tray process that exposes local ambient context (presence, foreground app, battery, etc.) as MCP tools with privacy classification and opt-in controls.

Provides a read-only interface to Kubernetes clusters, enabling LLMs to list pods, get pod status and logs, fetch deployment manifests, and perform pod health analysis with resource trend tracking.

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

A verifying MCP gateway that pins approved tool manifests and skill files to content addresses, blocking tampered descriptions before they reach model context.

Provides MCP tools to create and query SigNoz trace funnels, enabling agents to measure their own step conversion rates from within the agent loop.

Enables natural language interaction with Plausible Analytics data to query traffic, visitors, engagement, and more using conversational questions.

Privacy-first, tamper-evident receipts for MCP tool calls. It hashes and signs arguments/results so you can verify what ran, when, without storing raw payloads.

A comprehensive gateway and registry that unifies MCP, REST, and Agent-to-Agent services into a single secure endpoint for AI clients. It provides advanced capabilities including federation, virtual servers, rate-limiting, and OpenTelemetry observability.

Reads local Codex rollout logs to expose context-window usage snapshots, remaining-token estimates, and log-event freshness through a read-only MCP tool.

Federates MCP, A2A, and REST/gRPC APIs with centralized governance, discovery, and observability, optimizing agent and tool calling with plugin support.

A feature-rich gateway and proxy that federates MCP, REST, and gRPC services into a unified endpoint for AI clients. It enables virtualization of legacy APIs as MCP-compliant tools while providing built-in security, rate-limiting, and OpenTelemetry observability.

A fully compliant MCP gateway and registry that federates any MCP, A2A, or REST/gRPC API behind one unified endpoint, adding centralized discovery, auth, rate limiting, retries, and OpenTelemetry observability. It virtualizes legacy services and agents into MCP-compliant tools, prompts, and resources, with 40+ plugins extending transports and protocols.