Kosha Model Discovery
Tells your agent which model to use and what it costs, across 46 providers and local runtimes.
MCP server · by sriinnu
About
Kosha Model Discovery is an MCP server published by sriinnu. Marketplaces we read that list it: 1 (Official MCP Registry). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 2026-10-12.
What it asks for
- Runs on your machine
- Secrets: 6
- Settings: 7
Requires: ANTHROPIC_API_KEY (secret), GOOGLE_API_KEY (secret), OPENAI_API_KEY (secret), OPENROUTER_API_KEY (secret), TYPESAFE_API_KEY (secret), XAI_API_KEY (secret)
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Package
npm @sriinnu/kosha-discovery (@sriinnu/kosha-discovery on npm)
- npm downloads/week: 388 (2026-10-12)
- npm downloads/month: 2 134 (2026-10-12)
- Latest version on npm: 1.8.1, published 2026-10-06
npm facts come from the public npm registry (registry.npmjs.org, api.npmjs.org). Each figure is the registry's own and is never added to another. A registry that publishes no figure shows none: no number is not zero.
Works with
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a local MCP server: npm package
Built from what Official MCP Registry declares.
claude mcp add --env "ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>" --env "GOOGLE_API_KEY=<YOUR_GOOGLE_API_KEY>" --env "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" --env "OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY>" --env "TYPESAFE_API_KEY=<YOUR_TYPESAFE_API_KEY>" --env "XAI_API_KEY=<YOUR_XAI_API_KEY>" --transport stdio kosha-discovery -- npx -y @sriinnu/kosha-discovery[mcp_servers.kosha-discovery]
command = "npx"
args = ["-y", "@sriinnu/kosha-discovery"]
[mcp_servers.kosha-discovery.env]
ANTHROPIC_API_KEY = "<YOUR_ANTHROPIC_API_KEY>"
GOOGLE_API_KEY = "<YOUR_GOOGLE_API_KEY>"
OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>"
OPENROUTER_API_KEY = "<YOUR_OPENROUTER_API_KEY>"
TYPESAFE_API_KEY = "<YOUR_TYPESAFE_API_KEY>"
XAI_API_KEY = "<YOUR_XAI_API_KEY>"{
"mcpServers": {
"kosha-discovery": {
"command": "npx",
"args": [
"-y",
"@sriinnu/kosha-discovery"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GOOGLE_API_KEY": "<YOUR_GOOGLE_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"TYPESAFE_API_KEY": "<YOUR_TYPESAFE_API_KEY>",
"XAI_API_KEY": "<YOUR_XAI_API_KEY>"
}
}
}
}Replace the values in angle brackets with your own. We show the names of the settings, never values.
Optional settings it also lists: KOSHA_CACHE_TTL_HOURS.
We do not store launch arguments. If the server needs any, its own documentation names them.
Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Official MCP Registry (Open the registry record) | Listed | 1.8.1 | Downloads/month (npm): 2 134 Downloads/week (npm): 388 Forks (GitHub): 0 Stars (GitHub): 2 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
modelglass io.github.Modelglass/modelglass
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
-
Live registry of AI model specs, context windows, and per-token pricing.
-
ModelsLab v8 generation APIs: discover models, providers and endpoints, then run them.
-
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor
-
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
-
ToolDrift: Current AI model pricing and which models coding tools route to.
-
modelcostsaver io.github.sachinuppal/modelcostsaver
Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.
-
AI API cost calculator, recommender & MCP server. 29 models across text/image/video/audio.
-
LLM provider intelligence: recommendations, pricing, and status
-
Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
together-ai-skills
A collection of skills that teach coding agents how to use the Together AI platform, including chat completions, image generation, video, audio, embeddings, fine-tuning, batch…
-
Multi-LLM orchestration MCP server. Delegate tasks to Claude Code, Codex, and Gemini CLIs with session management, retry logic, async job orchestration, and token optimization.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
Has a listing on Claude Code: claude-plugins-official (5)
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
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.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
Has a listing on Claude: knowledge-work-plugins (5)
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
Has a listing on Community GitHub marketplaces (5)
-
Accurate API model IDs, pricing, and specs for 46 models across 7 AI providers.
-
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.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
Has a listing on 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.
-
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
-
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform…
-
Comprehensive collection for building declarative agents with Model Context Protocol integration for Microsoft 365 Copilot
-
foundry-hosted-agent-copilotkit
Build CopilotKit + AG-UI web apps on Microsoft Foundry hosted agents (Microsoft Agent Framework): wiring, native Foundry primitives, human-in-the-loop approvals, azd deploy, and…
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
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…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
-
mobile-app
Build and deploy Power Apps code apps for mobile using Expo (React Native), with native device functionality and Power Platform connectors
Has a listing on Cursor: cursor/plugins (5)
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
Has a listing on Docker MCP Catalog (5)
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Seamless interaction with Novita AI platform resources.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
Has a listing on Official MCP Registry (5)
-
modelglass io.github.Modelglass/modelglass
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
-
Live registry of AI model specs, context windows, and per-token pricing.
-
ModelsLab v8 generation APIs: discover models, providers and endpoints, then run them.
-
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor
-
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Add it to your projects and prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.