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

A minimal MCP server that exposes Gemini's web and multimodal understanding (video, audio, document, image) through five dedicated tools.

Share code context with LLMs via MCP or clipboard

An MCP server that analyzes local or remote GitHub repositories, providing intelligent code context and structure to AI coding assistants.

MCP server that provides AI assistants with real-time, current information about AI models from OpenAI, Anthropic, and Google, including pricing, capabilities, and context windows.

This MCP server enables MCP clients such as Claude Desktop to run LLM-generated code in a secure, isolated sandbox across multiple container backends and programming languages.

An MCP server that uses Google's Gemini API to analyze videos and convert them to text descriptions that Claude Code can understand and act upon.

Wraps Tool and ToolPackage instances from the llm-chat ecosystem behind the Model Context Protocol, enabling stdio and Streamable HTTP transports for MCP servers.

Enables cost-aware LLM routing over MCP with verification-based cascading, offering tools for routing queries, resuming escalated approvals, estimating costs, comparing policies, and explaining routing decisions, plus read-only resources and a policy-selection prompt.

Enables interacting with the GTA7 Lab city bank through MCP tools, including balance checks, transaction searches, PIX transfers, bill payments, card issuance, loan simulation and requests, and investments.

MCP server for managing a project backlog as Markdown files in Git, enabling AI agents to read, create, and update tasks programmatically.

Context Mode is an MCP server that reduces context window waste by sandboxing data-heavy tools, tracking session state in SQLite, and promoting code-based analysis over raw data reads, achieving up to 98% context savings.

Records a sale of a vehicle, equipment or stock and produces a printable bill of sale with signature lines. Drafts can be edited and finalized into a frozen signing copy rendered as Markdown or self-contained HTML for print-to-PDF.

Serves an LLM-maintained markdown wiki to agents over MCP, providing tools for querying and navigating wiki pages without direct filesystem access.

Give your AI agents access to 8,500+ community curated awesome lists with over 1 million curated resources.

Enables building client statements of account from existing invoices, credit notes, and deposits, with aged outstanding balances, PDF/plain-text output, and drafted payment chasers at friendly, firm, or final levels.

Enables Claude Code to leverage Chinese LLMs for multimodal tasks including image analysis, audio transcription, and deep synthesis via MCP protocol.

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions

Enables checking project files like Dockerfile, .nvmrc, and CI workflows to determine whether pinned runtime, database, and OS versions are still supported, providing end-of-life dates, latest patches, and upgrade targets for 470+ products.

Long AI conversations fail in predictable ways. Context-First fixes all four: Failure Mode What Goes Wrong Context-First Solution Context Drift AI forgets earlier decisions and intent as the conversation grows context_loop + detect_drift continuously re-anchor every turn Silent Contradiction New inputs silently overrule established facts — the AI doesn't notice detect_conflicts compares every inp

A local MCP server that packages LLM evaluation gates as reusable CI/CD primitives, enabling AI agents to run datasets against models, score responses, and enforce quality thresholds.