diffctx
Selects the minimum code an LLM needs to review a git diff
Serveur MCP · par nikolay-e
Aperçu
diffctx est un serveur MCP publié par nikolay-e. Places de marché que nous lisons et qui le référencent : 1 (Official MCP Registry). Nous l'avons vu pour la première fois le 2026-10-11 et n'avons enregistré aucun changement depuis. Selon notre passage sur les places de marché du 2026-10-12.
Ce qu'il demande
- S'exécute sur votre machine
Aucune des places de marché que nous lisons ne publie ses outils ni les réglages qu'il demande.
Ce qu'il déclare, demande et exécute, en détail
N’installez que des plugins de développeurs en qui vous avez confiance. Nous reprenons ce que publient les places de marché et ne testons pas les plugins.
Connecter
Commandes et configurations construites uniquement à partir de ce que déclarent ses places de marché. Nous ne les exécutons pas pour vous et ne testons pas les plugins.
En serveur MCP local : paquet PyPI
Construit à partir de ce que déclare Official MCP Registry.
claude mcp add --transport stdio diffctx -- uvx diffctx
[mcp_servers.diffctx]
command = "uvx"
args = ["diffctx"]
{
"mcpServers": {
"diffctx": {
"command": "uvx",
"args": [
"diffctx"
]
}
}
}
Nous ne gardons pas les arguments de lancement. Si le serveur en demande, sa propre documentation les donne.
Où il est publié
| Place de marché | Statut | Version | Chiffres | Vérifié | Vu pour la première fois |
|---|---|---|---|---|---|
| Official MCP Registry (Ouvrir la fiche du registre) | Référencé | 1.18.4 | Forks (GitHub): 1 Étoiles (GitHub): 6 |
Non marqué |
Chaque chiffre est celui de la place de marché et n'est jamais additionné entre places de marché. Une place de marché qui ne publie pas de chiffre n'en affiche aucun : pas de nombre ne veut pas dire zéro.
Ce qui a changé
Rien n'a bougé sur ce plugin depuis que nous le suivons.
Plugins similaires
Produits dont les noms, descriptions, outils et skills sont les plus proches de celui-ci par le sens, sur toutes les places de marché que nous lisons. La proximité n'est classée qu'à l'intérieur de cette liste.
-
The official Letmediff MCP server helping you review your code with an agent first workflow
-
Git diff and markdown review with a web UI plus MCP stdio for AI agents.
-
git io.github.rog0x/git
Git log, diff, blame, branch stats for AI agents
-
diffgate io.github.srbsa/diffgate
Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens.
-
GitWhy — The Context Layer for Git
The shared AI context engine for git — save, search, and share the reasoning behind code changes.
-
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
-
MCP server for AI-assisted coding with development history: git, tests, Copilot.
-
Local-first code context, impact analysis, and merge-readiness verdicts for AI agents.
-
git-enhanced io.github.davidweb3-ctrl/git-enhanced
Enhanced Git MCP Server - Code review, commit analysis, and branch management
-
AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor
Plugins similaires par place de marché
La même question posée à chaque place de marché séparément : y a-t-il là un équivalent de ce plugin ?
Référencé sur Claude Code: claude-plugins-community (5)
-
Code review with any AI model via OpenRouter. Run standard and adversarial reviews against your working tree or branch using Claude, GPT, Gemini, Llama, or any other model…
-
Deep repository analysis to realign project plans with actual code reality. `/drift-detect` discovers drift between documented plans (CHANGELOG, ARCHITECTURE.md, design docs…
-
Claude Code plugin to detect AI slop PRs — placeholder tests, overcommented code, and hallucinated changes. Free Layer 1 + optional LLM judge.
-
Adversarial planning and code review workflow between Claude Code and OpenAI Codex CLI. Enables iterative convergence loops where Claude creates plans/code and Codex provides…
-
Deep code indexing for AI agents. FTS5 + embeddings + call graphs + git intelligence. Fully local.
Référencé sur Claude Code: claude-plugins-official (5)
-
AI code review agent for GitHub and GitLab. View and resolve Greptile's PR review comments, run reviews on your working branch, and search your organization's knowledge base and…
-
Official GitHub MCP server for repository management. Create issues, manage pull requests, review code, search repositories, and interact with GitHub's full API directly from…
-
Upstash Context7 MCP server for up-to-date documentation lookup. Connects to Context7's hosted remote MCP server (https://mcp.context7.com/mcp) — no local Node.js or npx required…
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
-
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
Référencé sur Claude: knowledge-work-plugins (5)
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
MCP server for terminal commands, file operations, and process management
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
Référencé sur Codex: openai-curated (openai/plugins) (5)
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
AI-powered code review in Codex, powered by CodeRabbit.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Inspect recent issues and events in Sentry from Codex.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
Référencé sur Community GitHub marketplaces (5)
-
Self-hosted GitHub MCP server. PAT auth, stdio transport, transport-agnostic so it works with…
-
Sourcery security findings for AI coding agents: triage and minimal-change remediation via the public Sourcery API (12 MCP tools + skills).
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
-
Local Git via MCP: status, log, diff, file history, branches, and gated stage/commit. Pure-JS.
-
Dash0 Observability
OpenTelemetry observability for OpenAI Codex sessions. Captures prompts, tool calls, MCP calls, sub-agent activity, and token usage as OTel traces.
Référencé sur Copilot CLI: github/awesome-copilot (5)
-
Visualize and guide the GitHub Copilot Modernize CLI Assess, Plan, and Execute workflow for .NET, Java, and C++ application repositories.
-
Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates…
-
Review GitHub pull requests in a read-only canvas with AI-grouped changes, expandable diffs, and questions scoped to groups, files, or hunks.
-
Shows live prompt-cache reuse, expiry, token composition, and AIU cost for the current GitHub Copilot session without making model calls.
-
Generic cross-repo command center canvas for GitHub Copilot with onboarding, focus planning, repo health, work signals, and session cleanup.
Référencé sur Copilot CLI: github/copilot-plugins (5)
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for GitHub Copilot.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Référencé sur Cursor: cursor/plugins (5)
-
Render PR diffs as review canvases grouped by importance.
-
Manage repos, issues, pull requests, and Actions.
-
Skills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Internal team workflows for CI, code review, shipping, local automation, and verification.
Référencé sur Docker MCP Catalog (5)
-
Git repository interaction and automation.
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
Tools for interacting with Git repositories.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Référencé sur Official MCP Registry (5)
-
The official Letmediff MCP server helping you review your code with an agent first workflow
-
Git diff and markdown review with a web UI plus MCP stdio for AI agents.
-
git io.github.rog0x/git
Git log, diff, blame, branch stats for AI agents
-
diffgate io.github.srbsa/diffgate
Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens.
-
GitWhy — The Context Layer for Git
The shared AI context engine for git — save, search, and share the reasoning behind code changes.
Trouvés par le sens, et non par un code ou un dépôt commun : les plugins similaires restent des produits distincts, et ceci n'est ni un avis ni une recommandation.
C'est votre plugin ?
Prouvez que vous maintenez ce plugin avec un fichier dans son dépôt, un fichier sur votre domaine ou un enregistrement DNS. Vous recevez des alertes quand une place de marché le publie, le retire, change sa marque vérifiée ou ce qu'il demande, et vous pouvez mettre son endpoint distant sous surveillance comme service web.
Données issues de Official MCP Registry. Les chiffres proviennent de nos propres passages réguliers sur les places de marché, dernière lecture le . Nous ne publions aucune coordonnée des éditeurs de plugins.