RealRun

com.baseledgerip.realrun由 realrun.baseledgerip.com 发布官方发布者v0.1.1更新于 Oct 24, 2026

独立AI模型在5项任务上的测试得分：收件箱、日程安排、收据、财务、支持回复。

AI 翻译由 AI 模型根据下方的原文描述翻译，可能有误。

原文描述

Independent AI model test scores on 5 tasks: inbox, scheduling, receipts, finance, support replies.

已验证Streamable HTTP可网页运行AI 与机器学习

概览

RealRun 的托管 MCP 服务（realrun.baseledgerip.com），由 realrun.baseledgerip.com 发布；无需登录；Streamable HTTP；4 个工具。

暂无 AI 概览：以下信息来自注册中心条目和服务本身。

发布者
realrun.baseledgerip.com
端点
realrun.baseledgerip.com
最近检查

安装

在 SourceWeft 中

  1. 打开 控制台中的 RealRun，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.baseledgerip.realrun%2Frealrun/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "realrun": {
      "type": "http",
      "url": "https://realrun.baseledgerip.com/mcp"
    }
  }
}

README

RealRun MCP server

[RealRun logo]

[Listed on mcpservers.org]

Read-only lookups over RealRun's published, independent tests of AI models on everyday tasks (inbox triage, meeting scheduling, receipts, small-business finance, customer support replies). It lets an agent ask "which model should I use for task X?" and get scores and safety warnings back.

Connect (remote, no install)

Streamable HTTP endpoint: https://realrun.baseledgerip.com/mcp

json
{ "mcpServers": { "realrun": { "url": "https://realrun.baseledgerip.com/mcp" } } }

Claude Code: claude mcp add --transport http realrun https://realrun.baseledgerip.com/mcp

Cline: add this to cline_mcp_settings.json (keep "type": "streamableHttp"; without it Cline falls back to SSE and the connection fails). Full agent-readable steps: llms-install.md.

json
{ "mcpServers": { "realrun": { "type": "streamableHttp", "url": "https://realrun.baseledgerip.com/mcp", "disabled": false, "autoApprove": [] } } }

Run locally (stdio)

npx -y realrun-mcp

(once published to npm; from a checkout: npm install && node src/stdio.mjs)

Tools

ToolInputReturns
list_tasksnoneTested tasks, item counts, dates, results pages, playbook prices
get_scorestaskEvery model's headline score (best first), cost tier, metric definition
recommend_modeltask, priority (accuracy/cost/balanced), include_subscriptionOne pick + 2 alternatives; never picks a model flagged not recommended
get_warningstaskNot-recommended and caution flags (scam failures, invented data, inconsistency)

Task ids: inbox-triage, meeting-scheduling, receipts, finance, support-replies.

All tools are read-only. The server stores nothing and has no auth. It is stateless, with JSON responses.

Data

src/data.json holds only the published headline numbers. Full prompts and item-level results are in the paid playbooks ($29 each, links in list_tasks). Scores reflect our tests on the dates shown, not a guarantee.

Billing (not active)

Every call passes through src/metering.mjs. The plan is a free allowance of about 20 lookups a day, then per-call billing via Stripe or x402. It is off: nobody is charged, and no payment objects exist.

Test

npm test runs stdio end to end. node test/smoke.mjs https://realrun.baseledgerip.com/mcp tests the remote endpoint.

Layout

  • src/server.mjs: tools
  • src/stdio.mjs: CLI
  • src/http.mjs: exports for the HTTP function
  • ../netlify/functions/mcp.mjs: Netlify Function at /mcp
  • server.json: official MCP registry metadata

License: MIT. © Base Ledger IP LLC.

来源：README.md，提交 c13cc94

工具

4

list_tasks

List tested tasks

List the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.

无需输入参数。

get_scores

Get model scores for a task

Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.

输入参数task必填

recommend_model

Recommend a model for a task

Recommend which AI model to use for a task given a priority: 'accuracy', 'cost' or 'balanced'. Never recommends models RealRun flagged as not recommended.

输入参数task必填priorityinclude_subscription

get_warnings

Get safety warnings for a task

Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).

输入参数task必填

版本历史

2
  1. v0.1.1最新Oct 19, 2026
  2. v0.1.0Oct 15, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分