{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_nn2kvzjx3wdd","handle":"ez-mcp-toolbox","url":"https://wellknown.network/agents/ez-mcp-toolbox","links":{"self":"https://wellknown.network/agents/ez-mcp-toolbox/record.json","html":"https://wellknown.network/agents/ez-mcp-toolbox","markdown":"https://wellknown.network/agents/ez-mcp-toolbox/record.md","api":"https://wellknown.network/api/v1/agents/ez-mcp-toolbox","status":"https://wellknown.network/api/v1/agents/ez-mcp-toolbox/status","claim":"https://wellknown.network/agents/ez-mcp-toolbox/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ez-mcp-toolbox/claim.json","badge":"https://wellknown.network/agents/ez-mcp-toolbox/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/ez-mcp-toolbox/history","tools":"https://wellknown.network/api/v1/agents/ez-mcp-toolbox/tools"},"ard":{"identifier":"urn:air::server:ez-mcp-toolbox","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ez-mcp-toolbox","summary":"Utilities for creating and debugging MCP tools","description":"# EZ MCP Toolbox\n\n*A Comet ML Open Source Project*\n\nThis Python toolbox contains four command-line easy to use utilities:\n\n1. `ez-mcp-server` - turns a file of Python functions into a MCP server\n2. `ez-mcp-chatbot` - interactively debug MCP servers, with traces logged to [Opik](https://www.comet.com/site/products/opik/)\n3. `ez-mcp-eval` - evaluate LLM applications using Opik's evaluation framework\n4. `ez-mcp-optimize` - optimize LLM applications using Opik's optimization framework\n\n## Why?\n\nThe `ez-mcp-server` allows a quick way to examine tools, signatures, descriptions, latency, and return values. Combined with the chatbot, you can create a fast workflow to interate on your MCP tools.\n\nThe `ez-mcp-chatbot` allows a quick method to examine and debug LLM and MCP tool interactions, with observability available through [Opik](https://github.com/comet-ml/opik). Although the [Opik Playground](https://www.comet.com/docs/opik/opik-university/prompt-engineering/prompt-playground) gives you the ability to test your prompts on datasets, do A/B testing, and more, this chatbot gives you a command-line interaction, debugging tools, combined with Opik observability.\n\nThe `ez-mcp-eval` and `ez-mcp-optimize` commands provide evaluation and optimization capabilities for your LLM applications, enabling you to measure performance and automatically improve your prompts using Opik's evaluation and optimization frameworks.\n\n## Installation\n\n```\npip install ez-mcp-toolbox --upgrade\n```\n\n## Quick start\n\n### Interactive Chat with MCP Tools\n```\nez-mcp-chatbot\n```\n\nThat will start a `ez-mcp-server` (using example tools below) and the `ez-mcp-chatbot` configured to use those tools.\n\n### Evaluate LLM Applications\n```\nez-mcp-eval --prompt \"Answer the question\" --dataset \"my-dataset\" --metric \"Hallucination\" --output \"reference=answer\"\n```\n\nThis will evaluate your LLM application using Opik's evaluation framework with your dataset and chosen metrics. The `--output` parameter is required for cla…","publisher":null,"homepage":"https://github.com/comet-ml/ez-mcp-toolbox#readme","repository":"https://github.com/comet-ml/ez-mcp-toolbox/issues","version":"1.5.0","license":"Apache License\n                                   Version 2.0, …","protocols":["mcp"],"tags":["opik","mcp","model-context-protocol","llm","observability","debugging"],"pricing":null,"endpoints":[{"url":"pypi:ez-mcp-toolbox","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"code.debugging","name":"Debugging","confidence":1,"provenance":"declared"},{"slug":"dev.monitoring","name":"Monitoring & Observability","confidence":1,"provenance":"declared"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.791,"provenance":"derived"},{"slug":"ai.prompting","name":"Prompt Management","confidence":0.791,"provenance":"derived"}],"categories":["ai","code","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"ez-mcp-toolbox","registry":"pypi","observedAt":"2026-09-15T14:27:02.908Z","publishedAt":"2026-01-09T03:59:39.011971Z","latestVersion":"1.5.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ez-mcp-toolbox","url":"https://pypi.org/project/ez-mcp-toolbox/","firstSeenAt":"2026-09-09T15:22:11.490Z","fetchedAt":"2026-09-15T14:25:18.938Z","normalizedAt":"2026-09-15T14:25:18.938Z"}]},"firstSeenAt":"2026-09-09T15:22:11.490Z","updatedAt":"2026-09-15T14:27:02.908Z"}