"A guide for reducing token count in AI requests" matching MCP servers:

Local-first dashboard + MCP server that parses Claude Code and Codex JSONL files into a SQLite cost / token tracker. Per-MCP and per-tool breakdown, session drill-down, dedup by request_id; never talks to vendor APIs

Provides intelligent analysis of token usage patterns and optimization recommendations to improve efficiency and reduce costs in Claude Code sessions. Offers real-time analysis, cost metrics, and actionable insights for better context window and tool usage optimization.

Enables LLMs to interact with Kibana through composable toolboxes for building dashboards, managing data, and handling alerts, among other operations.

Enables observability and governance for local LLMs via Ollama, including auditing model usage, scanning prompts for secrets/PII, and enforcing allow/deny policies.

Enables AI agents to interact seamlessly with Splunk environments through 20+ tools for search, analytics, data discovery, administration, and health monitoring. Features AI-powered troubleshooting workflows and supports multiple Splunk instances with production-ready security.

Perimeter security for your AI Infrastructure.

Enables local-first tracking of AI token usage and costs from Claude Code and OpenCode, answering queries about tokens, models, sessions, and cost through MCP tools and a CLI, with no network calls.

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

Read-only MCP server for querying AI usage metrics (exact tokens, cost, latency, errors, productivity) from a local SQLite database, enabling charts and analysis in Claude Code and Cursor.

MCP server that diagnoses Apache Spark job failures and optimizes performance using stack-trace analysis and LLM providers, supporting EMR and local sources.

Enables an LLM agent to investigate a Kong Gateway through fourteen read-only, schema-validated tools and a deterministic diagnostic engine, so it can trace routes, services, plugins and upstream health and explain faults such as why authentication is failing on a path. Every fact comes from the gateway itself, and the model only selects tools and writes the evidence-backed explanation.

Model Context Protocol server for Verlon AI that exposes gates, logs, recommendations, and experiments as MCP tools, enabling coding agents to inspect and manage AI infrastructure natively.

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.

Enables LLMs to query telemetry data via the Spyglass AI agent, providing intelligent insights about application performance, errors, and bottlenecks.

A MCP server for tracking AI usage metrics and structured logs across applications. Monitor model calls, analyze usage patterns, track costs, and debug AI interactions.

MCP server for measuring, tracking, scoring, and improving AI agent reliability with tools for recording interactions, scoring reliability, analyzing failures, recommending improvements, generating audit reports, and checking MCP health.

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.

Connects AI assistants to the Vectra AI security platform to enable intelligent analysis of threat detection data and automated incident response workflows. It allows users to investigate threats, take response actions, and generate security reports using natural language.

Connects AI-powered tools to the Confident AI platform for evaluating, observing, and iterating on AI quality, enabling cloud evaluations, dataset management, prompt versioning, production tracing, and human annotations directly from editors like Cursor and Claude Code.

Ships only the MCP server, not the recorder. Recording works by wrapping a process on the host — a local proxy, a PATH shim, a shadow git index. None of that survives a container boundary, so orca record inside here would watch an empty namespace. What does travel is the read side: the six MCP tools serve runs that already exist on disk, so a client mounts its .orca directory and r