"Enhancements for Claude Desktop App with Large Contexts and Long Documents" matching MCP servers:

Self-hosted MCP coding server and unified local Control Center for ChatGPT web, enabling file editing, command execution, Git operations, and optional upstream MCP tools with conversation access controls.

Enables users to safely read, write, edit, create directories, and list trees within a structured local Windows environment, with strict path validation and Git-based undo/version control.

Provides a read-only MCP bridge that lets Claude Web inspect workspace files, git state, and recorded test results while Codex remains the sole executor of changes.

A read-only MCP connector that lets ChatGPT on the web plan tasks and independently review real Git diffs for local coding agents across many registered projects through one shared OAuth-protected hub connection, with no API key required. It exposes only file reads — never edits or shell tools — so the coding agent keeps full ownership of execution while the web subscription handles the reasoning and review.

Fetches public GitHub repositories and uses an LLM to generate a json-render UI specification.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.

Adds a live git branch status bar to the Claude interface for monitoring multiple repositories simultaneously. It provides tools for managing repository tracking and visibility through natural language commands.

MCP server that pushes GitHub Actions CI/CD results and PR events into Claude Code sessions, enabling automatic investigation and remediation.

MCP server that integrates with VS Code to enable file operations, git diffs, and line highlighting via MCP clients like Claude.

Enables secure GitHub App authenticated Git operations and GitHub API workflows through MCP, using ephemeral containers and a private key broker to protect credentials.

Enables two people's Claude agents to hold a live conversation about the same project, using GitHub Issues as channels and Issue comments as messages. Each side can list channels, open new ones, send and read messages, and wait for the other's reply, while both users follow and join in directly on GitHub.

This MCP server bridges ChatGPT to GitHub, letting you use natural language to read repositories, modify code, create branches, and open pull requests while enforcing security policies like repository whitelists and branch protection.

A stdio MCP server that lets Codex Desktop/CLI delegate implementation tasks to Claude Code CLI with workspace validation, Git status checks, and session resume capabilities.

Adds a live git branch status bar to the Claude footer for tracking multiple active and reference repositories. It allows users to manage repository visibility and configuration directly through natural language MCP tools.

Enables Codex and other MCP clients to read kickoff cards, acceptance criteria, Git evidence, and next steps, then append validated, audited progress events for resumable project handoffs.

Enables agents to read a project's kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, and to append validated, audited progress events with matching Git commits through short-lived scoped credentials.

Enables Codex agents to read a project's kickoff card, acceptance criteria, handoff package, progress, Git trail and next step, then append validated, audited, idempotent progress events that become matching project-record Git commits. Access is scoped to one workspace and project through short-lived, revocable, hash-stored credentials that cannot touch members, keys, deletion, publication or deployment.

It enables AI agents to retrieve Git-backed project context, handoff packages, and next actions, then append validated, audited progress events as project-record commits.

It lets AI coding clients read a project’s kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, then append a validated, audited, idempotent progress event with a matching project-record Git commit.

Enables Codex to read a project's kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, and to append validated, audited, idempotent progress events with a matching Git commit.

Enables auditing public GitHub repositories over MCP Streamable HTTP, including classifying URLs, cloning repositories, scanning manifests, CI workflows, and credential signals, and producing findings, file trees, summaries, and PDF reports.

Turns Claude Code into an engineering project manager by orchestrating feature development with isolated Git worktrees, structured task validation, and approval-gated integration.

Enables AI agents and humans to read a project's kickoff card, acceptance criteria, handoff package, progress, Git trail, and next step, then append audited, idempotent progress events that are committed to the project's Git record. Access is scoped per project through short-lived, revocable credentials, keeping high-risk actions outside the tool surface for human approval.

Enables Codex projects to read Git-backed context, acceptance criteria, progress, and handoff packages, and to append validated, audited progress events with matching project-record commits.

A Model Context Protocol server that provides comprehensive GitHub integration for Claude Desktop, allowing users to manage repositories, issues, and pull requests. It supports file operations, branch management, and repository searches through natural language commands.

Enables Codex users to retrieve Git-backed project context and append validated, audited progress events as matching Git commits, so work can resume safely across sessions.

Enables two coding assistants to coordinate task creation, claiming, messages, and completion through a shared local workflow queue while using GitHub issues, branches, commits, and PRs as the source of truth.

Enables Codex agents to read a project's context — kickoff card, acceptance criteria, handoff package, progress, Git trail, and next step — over MCP, and to append one validated, audited, idempotent progress event that is committed to a Git-backed project record using scoped, short-lived credentials.

It reads a project's kickoff card, acceptance criteria, AGENTS rules, progress, Git trail, and handoff package, and appends validated, audited progress events tied to project-record Git commits. This gives Codex agents scoped, credential-bound access to resumable project context and safe handoffs.

Enables local Claude Code to interact with Snowflake, Asana, M365, GitHub, and Hive Mind with automatic response truncation to prevent memory overload.