CompletionKit
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Serveur MCP · par completionkit.com
Aperçu
CompletionKit est un serveur MCP publié par completionkit.com. 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 2026-10-13.
Ce qu'il demande
- S'exécute à distance
Aucune des places de marché que nous lisons ne publie ses outils ni les réglages qu'il demande.
Demande: en-tête Authorization
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.
Fonctionne avec
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Un lien en un clic ouvre le client, qui demande une confirmation avant d'ajouter le serveur.
D'après les marketplaces qui le listent et le transport MCP qu'il déclare, tels que chaque client les documente. Nous 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 distant
Construit à partir de ce que déclare Official MCP Registry.
claude mcp add --transport http evals https://completionkit.com/mcp --header "Authorization: Bearer <YOUR_TOKEN>"[mcp_servers.evals]
url = "https://completionkit.com/mcp"
http_headers = { "Authorization" = "Bearer <YOUR_TOKEN>" }{
"mcpServers": {
"evals": {
"url": "https://completionkit.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}Remplacez les valeurs entre chevrons par les vôtres. Nous montrons les noms des paramètres, jamais de valeurs.
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 | 1.0.0 | Forks (GitHub): 1 Étoiles (GitHub): 3 |
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.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
-
mcp io.scorecard/mcp
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
-
Give your AI a research team. Forecast, score, classify, or research every row of a dataset.
-
Run data annotation and evaluation tasks with vetted domain experts: create, publish, get results.
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Mini Data Engine Runtime Copilot
MCP runtime copilot for health checks, regressions, explainability, and operational memory.
-
golden-dataset-mcp io.github.nipunkhanderia/golden-dataset-mcp
Version-controlled golden datasets and RAG evaluation, no API key needed.
-
Run AI agent evaluations on your own model keys, and publish runs others can review and re-run.
-
Context engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
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)
-
Context engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
AI agent evaluation sandbox for Claude Code. Holdout scenario testing with Doer/Judge/Adversary/Observer roles, probabilistic satisfaction scoring, and append-only JSONL audit…
-
End-to-end data analysis workflow plugin for Claude Code. Covers the full pipeline from EDA to model training - EDA, preprocessing, statistical analysis, feature engineering, and…
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
Référencé sur Claude Code: claude-plugins-official (5)
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
Référencé sur Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
Atlan data catalog plugin for Claude Code. Search, explore, govern, and manage your data assets through natural language. Powered by the Atlan MCP server with semantic search…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
Référencé sur Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Answer product and business questions with data
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
PostHog gives your AI agent direct access to your product analytics, feature flags, experiments, error tracking, surveys, logs, and LLM analytics. Ask questions about your data…
Référencé sur Community GitHub marketplaces (5)
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
-
Create, connect, and interact with an AlloyDB for PostgreSQL database and data.
-
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)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
Référencé sur Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Référencé sur Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Work with PostHog from chat: query product analytics and run SQL, manage feature flags and experiments, triage error tracking issues, and review session replays, surveys, and…
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
Référencé sur Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
-
Analyze documents, images, videos, and audio.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
Référencé sur Official MCP Registry (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
-
mcp io.scorecard/mcp
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
-
Give your AI a research team. Forecast, score, classify, or research every row of a dataset.
-
Run data annotation and evaluation tasks with vetted domain experts: create, publish, get results.
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 ?
Ajoutez-le à vos projets et prouvez que vous le maintenez : un fichier dans son dépôt, un fichier sur votre domaine ou un enregistrement DNS. Vous recevez des alertes quand une marketplace le publie, le retire, change sa marque vérifiée ou ce qu'il demande, et son endpoint distant est surveillé comme un 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.