"Rewriting or modifying Debian packages" matching MCP servers:

Enables AI agents to trade forex, metals, indices, and cryptocurrencies via the Model Context Protocol using the XBTFX Trading API. It provides comprehensive tools for managing account balances, retrieving market data, and executing trade operations like opening, modifying, or closing positions.

Allows AI to interact with Autodesk Revit via the MCP protocol, enabling retrieval of project data and automation of tasks like creating, modifying, and deleting elements.

A modular, extensible Model Context Protocol server framework designed for Claude Desktop that uses convention-based automatic module discovery to easily extend AI application functionality without modifying core code.

Enables an LLM agent to measure where a session's tokens actually go and whether rewriting history pays for the prompt-cache prefix it invalidates, so it can pick clearing thresholds or decline to compress. Exposes the token-cost accounting and cache-preserving optimization layers over MCP.

Emulates Claude Skills with any LLM via MCP, enabling agents to use modular skill packages for specialized workflows and tool integrations.

MCP hub server that aggregates tools from multiple domain packages into a single globally-available interface.

Enables any MCP-capable agent to optimize prompts across code, writing, image, and chat scenes, returning a rewritten prompt plus change explanations and element coverage, or to diagnose a prompt with a 100-point score and issue list without rewriting it. Runs over stdio against any OpenAI-compatible endpoint configured once through environment variables or a shared config file.

Enables AI coding agents to query a unified local index of all their sessions through native tools, supporting session summaries, full-text search, listing, message timelines, and handoff context packages for another agent.

A local MCP server that discovers and shares session file paths between AI coding agents, enabling cross-referencing without modifying existing workflows.

Turns existing REST/OpenAPI APIs into governed MCP tools for AI agents without modifying the APIs themselves, generating agent-friendly tools from specs, Postman collections, HAR files or cURL commands. Owners enable tools and set policies, while every call injects upstream credentials, redacts PII, projects responses to fit context limits, and produces a full audit trail.

Enables AI agents and MCP clients to run Playwright-compatible browser automation over stdio or Streamable HTTP, covering research, testing, persistent login profiles, Chrome extensions, proxy matching, and humanized interactions. It ships as npm and Docker packages for cross-platform deployments.

Enables agents to search and inspect behavioral packages from the BPM registry and install or remove them with mandatory human approval, all without leaving the agent session.

Enables independent code review and multi-round discussions between Claude and Codex, allowing either agent to inspect project files read-only and exchange feedback without modifying the repository.

Provides local, read-only recommendations for reasoning effort, retry or escalation guidance, and integration boundaries, enabling compatible desktop apps to suggest effort levels without modifying the active conversation.

RavensPort is an MCP proxy that lives in your tray and listens on 127.0.0.1. Point Claude, Cursor, VS Code or any other MCP client at it, and each agent gets one endpoint carrying exactly the tools you granted, from as many MCP servers and APIs as you like. Windows is the supported platform; Debian/Ubuntu build is available for x86-64 and arm64.

An MCP server that autonomously optimizes ONNX ML models for Arm64 deployment, providing tools to analyze models, apply real INT8 quantization, benchmark performance, and generate Arm64-optimized Docker deployment packages.

A stdio MCP server that wraps DeepSeek Harness's local /api into 9 tools, letting any standard MCP client create or adopt named dsh sessions, dispatch task briefs, poll asynchronously, and retrieve auditable per-turn results. It also enforces pre-validated model allowlists, workspace/alias boundaries, and a persistent session ledger, so agents can collaborate across harnesses without modifying dsh or installing client plugins.

Collect primary sources through GitHub Actions and retrieve portable research packages with capture hashes, provenance ledgers, and explicit review requirements. The stdio MCP server exposes collect and fetch_corpus.

A MCP server that allows AI assistants to interact with the browser, including getting page content as markdown, modifying page styles, and searching browser history.

Enables AI models to seamlessly integrate with external tools and data sources via the Model Context Protocol, extending functionality without modifying the core model.