"Exploring Computer Usage" matching MCP servers:

An MCP server giving coding agents context-window-aware code search and safe, atomic multi-file edits — built to cut token usage on large codebases without sacrificing correctness.

Enables AI agents to perform software engineering tasks inside an isolated, deterministic sandbox—exploring repositories, reproducing failures, applying patches, running tests, and verifying solutions against hidden suites through MCP tools.

Enables MCP clients to run Cline CLI prompts and isolated repository-wide analyses, returning terminal text responses with model, duration, and usage/cost.

Wraps the cursor-agent CLI to provide cost-effective tools for repository analysis, code search, planning, and editing. Offloads heavy thinking tasks from the host AI to reduce token usage while maintaining precise, scoped workspace operations.

A local MCP bridge that lets ChatGPT control opencode sessions for code modification, file reading, and repository management on your own computer.

A local project intelligence, batch coding, and self-learning engine for Codex that enables task-level batch coding, reduces token usage, and automatically learns skills.

Enables AI coding assistants to drive spec-driven development through slash-command workflows for planning, exploring, implementing, updating, and finalizing changes, with local daemon and project registry support.

Context compiler for AI coding agents that indexes TypeScript codebases to extract and serve only the relevant symbols and files for a task, reducing token usage and search overhead.

Enables MCP-compatible coding agents to run the local Antigravity CLI as a coding agent, manage conversation context and common options, and inspect usage, quota, models, version, help, and read-only slash commands.

Enables ChatGPT conversations to directly inspect local workspaces and delegate coding tasks to a local Codex agent, with controlled concurrency, reusable sessions, and task/usage tracking.

A local MCP bridge that lets ChatGPT chat mode operate the user's own computer, running project, file, and shell tasks through a local executor and returning progress and results to the conversation. It also coordinates Codex sessions (persistent or one-off) and other agent CLIs as sub-agents.

Enables external MCP clients to drive DeepSeek Harness agents for real coding tasks, providing tools for task execution and queueing, session management, sandboxed file access, preset switching, and usage statistics.

Implements Agentic Context Engineering to create self-improving AI coding assistants that learn from execution feedback and build persistent knowledge playbooks. Reduces token usage by 86.9% while improving code accuracy by 10.6% through incremental context updates.

Provides file caching and diff tracking for AI coding agents, reducing token usage by returning changes or confirming no changes instead of full file contents on repeated reads.

Lets Claude Code delegate tasks to the OpenCode CLI, choosing cost-effective models by intelligence tier and tracking usage.

Enables AI coding agents to efficiently query code context via a symbol graph, reducing token usage by up to 20x.

Provides AI coding agents with persistent architectural memory of codebases, enabling impact analysis, test generation, and code generation with reduced token usage.

A secure, local-first MCP coding and computer-use harness for ChatGPT and Codex, enabling guarded file operations, durable terminals, Git review, local skills, and macOS computer control.

Local-first MCP toolkit that provides coding agents focused repository context via read_file, search_files, and edit_file tools, reducing token usage and task cost.

Enables hybrid agentic coding by delegating token-heavy implementation, editing, and test-debug loops to local open-source models while frontier cloud models handle architecture and review, reducing premium API token usage and keeping code private.