"Rewriting or modifying Debian packages" matching MCP servers:

Kill switch + spend guard for AI agents that spend money: one policy, one sub-second freeze, and one signed audit ledger across every wallet vendor at once (Coinbase, Turnkey, Openfort + cards). Tools include a pre-flight request_spend guard, freeze, apply_policy, ledger, and x402/AP2 payment-mandate guards — free self-serve key, no account.

MCP server that packages DeepSeek agents as callable tools, offering a bare model for quick Q&A and a full agent capable of executing real coding and file-modifying tasks in a workspace.

Enables language models to interact with a deterministic limit order book exchange through MCP tools, including submitting, canceling, and modifying orders, reading books and trades, and managing scenarios and snapshots for experimentation.

An MCP server that turns deployed n8n workflows into callable tools for AI agents, enabling discovery and execution of tagged workflows via a standard interface without rewriting integrations.

Package intelligence MCP server. Stops AI agents from installing hallucinated/malicious packages across 17 ecosystems. 22 tools, free, no auth.

Enables AI agents to autonomously manage incoming packages by logging parcels, cross-referencing unit directories, surfacing aging uncollected items, and recording pick-up signatures without physical locker hardware.

Enables AI assistants to manage Debian package repositories through natural language using the Aptly package management tool. Supports repository creation, package operations, snapshot management, publishing, and mirror synchronization.

A secure Node.js execution environment that allows coding agents and LLMs to run JavaScript dynamically, install NPM packages, and retrieve results while adhering to the Model Control Protocol.

A lightweight and extendable MCP server toolkit that allows developers to build and integrate custom tools with AI assistants through automatic tool discovery from local directories or npm packages.

Account-less access to 45 Gemini models & autonomous agents, 71 edge microservices across 6 modular domain packages via L402, x402, MPP.

Enables agents to request physical-world tasks such as 3D printing, CNC fabrication, assembly, measurement, testing, on-site verification, and receive-repack-ship services from a human operator, with fixed-price quotes, status tracking, and evidence packages.

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

Enables selective context handoff for Codex by curating past conversation blocks based on a next topic. It preserves essential blocks, removes unnecessary ones, and keeps sensitive data local without modifying the active chat history.

Enables AI agents to investigate and repair Python/pytest repositories in isolated Git worktrees with audit trails, without modifying the original repository.

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.

Restores OpenAI Codex Computer Use on macOS 13 by building a clean-room MCP backend that adapts to the bundled sky interface, enabling screen interaction and app control without modifying system libraries.

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.

Enables teachers to turn plain-language teaching requests into interactive HTML demos and Mannim-rendered narrated animations through a confirm-once workflow, with automatic lesson design, generation, review, and revision. Shares a local work library with the standalone web workbench so finished lessons can be exported as offline HTML, MP4, or ZIP packages.

Enables agents to capture task-scoped residue evidence during test and build workflows, exposing files, directories, processes, and ports for user-authorized cleanup and post-cleanup verification without deleting or modifying anything itself.

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.