{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_vcmrm8k56ejx","handle":"llm-api-benchmark-mcp-server","url":"https://wellknown.network/agents/llm-api-benchmark-mcp-server","links":{"self":"https://wellknown.network/agents/llm-api-benchmark-mcp-server/record.json","html":"https://wellknown.network/agents/llm-api-benchmark-mcp-server","markdown":"https://wellknown.network/agents/llm-api-benchmark-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/llm-api-benchmark-mcp-server","status":"https://wellknown.network/api/v1/agents/llm-api-benchmark-mcp-server/status","claim":"https://wellknown.network/agents/llm-api-benchmark-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/llm-api-benchmark-mcp-server/claim.json","badge":"https://wellknown.network/agents/llm-api-benchmark-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/llm-api-benchmark-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/llm-api-benchmark-mcp-server/tools"},"ard":{"identifier":"urn:air::server:llm-api-benchmark-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"llm-api-benchmark-mcp-server","summary":"Runs a throughput benchmark for LLM APIs, measuring generation throughput, prompt throughput, and Time To First Token (TTFT) under various concurrency levels.","description":"# LLM API Benchmark MCP Server\n\nThis project provides an MCP (Model Context Protocol) server designed to benchmark Large Language Model (LLM) APIs. It allows you to measure various performance metrics such as generation throughput, prompt throughput, and Time To First Token (TTFT) for your LLM endpoints.\n\n## Features\n\n*   **Comprehensive Benchmarking:** Measure key performance indicators like generation throughput, prompt throughput, and Time To First Token (TTFT).\n*   **Flexible Deployment:** Supports both remote SSE server for quick trials and local deployment via stdio or SSE transport.\n*   **Customizable Benchmarks:** Configure various parameters for your LLM API benchmarks, including concurrency levels, model names, token limits, and more.\n*   **Detailed Output:** Provides structured JSON output with aggregated and distributed metrics for in-depth analysis.\n*   **Easy Integration:** Designed as an MCP server for seamless integration with MCP clients.\n\n## Table of Contents\n\n- [LLM API Benchmark MCP Server](#llm-api-benchmark-mcp-server)\n  - [Features](#features)\n  - [Table of Contents](#table-of-contents)\n  - [Prerequisites](#prerequisites)\n    - [Install uv](#install-uv)\n  - [Quick Start](#quick-start)\n    - [Demo (Recommended for Simple Trials)](#demo-recommended-for-simple-trials)\n    - [Local Deployment (stdio)](#local-deployment-stdio)\n    - [Local Deployment (sse)](#local-deployment-sse)\n  - [Usage Example](#usage-example)\n  - [Benchmark Parameters](#benchmark-parameters)\n  - [License](#license)\n\n## Prerequisites\n\nThis project uses [`uv`](https://docs.astral.sh/uv/getting-started/installation/#installation-methods) for environment management. Please ensure you have `uv` installed on your system.\n\n### Install uv\n\nRefer to the [official `uv` documentation](https://docs.astral.sh/uv/getting-started/installation/#installation-methods) for installation methods.\n\n## Quick Start\n\nYou can experience this MCP server through a remote SSE server for quick trials or …","publisher":null,"homepage":null,"repository":null,"version":"0.1.4","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:llm-api-benchmark-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"derived"}],"categories":["ai"],"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":"llm-api-benchmark-mcp-server","registry":"pypi","observedAt":"2026-10-28T09:22:54.045Z","publishedAt":"2025-06-26T04:58:25.014105Z","latestVersion":"0.1.4"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"llm-api-benchmark-mcp-server","url":"https://pypi.org/project/llm-api-benchmark-mcp-server/","firstSeenAt":"2026-09-09T23:25:48.471Z","fetchedAt":"2026-10-28T09:20:54.326Z","normalizedAt":"2026-10-28T09:20:54.326Z"}]},"firstSeenAt":"2026-09-09T23:25:48.471Z","updatedAt":"2026-10-28T09:22:54.045Z"}