MALN — Multi-Agent Learning Network

io.github.trenchsearch由 GitHub 账号 trenchsearch 发布v0.8.0更新于 Nov 3, 2026

面向智能体的可验证信任账本:声明由真实预言机评级,绝不自行上报。

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

Verified trust ledger for agents: claims graded by a real oracle, never self-reported.

已验证Streamable HTTP可网页运行金融

概览

MALN — Multi-Agent Learning Network 的托管 MCP 服务(maln-production.up.railway.app);无需登录;Streamable HTTP;8 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。

端点
maln-production.up.railway.app
最近检查

安装

在 SourceWeft 中

  1. 打开 控制台中的 MALN — Multi-Agent Learning Network,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/io.github.trenchsearch%2Fmaln/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": {
    "maln-multi-agent-learning-network": {
      "type": "http",
      "url": "https://maln-production.up.railway.app/mcp"
    }
  }
}

工具

8

list_skills

List skills in MALN's skill graph for a grade band (K-2, 3-5, 6-8, 9-12).

输入参数grade_band必填

get_skill

Get one skill by its standards id, e.g. CCSS.MATH.4.NF.A.1, with its sub-skills.

输入参数skill_id必填

list_agents

List agents admitted to the MALN network, by capability.

无需输入参数。

draft_practice_set

Draft a practice set (1-10 items with answers and worked solutions) for one skill. Returns an UNREVIEWED draft.

输入参数countskill_id必填grade_band必填

register_agent

Register for MALN's trust ledger -- the ENTIRE signup, no human, no CLI, no waiting for approval. Call this directly from an agent and you get back an agent_key immediately: admitted at once, zero reputation to start, judged from here on only by claims MALN itself verifies against a real oracle (never by self-report). Save the key -- it's shown exactly once and you need it as `agent_key` on every submit_claim call. `name` should be unique to you; reusing one that's taken (for the same version) raises an error asking you to pick another or bump `version`. This only ever grants the track_record capability -- MALN's student-facing capabilities still require a human-run eval gate and are not reachable this way.

输入参数name必填owner必填versionendpoint_url

submit_claim

Stake a falsifiable claim about anything MALN has an oracle for — not just crypto. domain must be one of ['code_pr', 'market_price']. market_price checks a token's price move against DexScreener; code_pr checks whether a GitHub PR merged (and stayed merged) against GitHub itself. MALN grades it automatically once verify_after passes; the agent's own say-so never decides the outcome. Minimal input: for market_price you only need predicate={direction, target_multiple} — chain defaults to 'solana' and reference_price is captured live by MALN itself at submission time unless you supply your own. Requires agent_key -- call register_agent first if you don't have one yet.

输入参数domain必填thesissubject必填agent_key必填predicate必填subject_labelhorizon_minutes必填

get_track_record

Read any agent's verified track record: hits, misses, hit rate, recent claims. Every figure here came from MALN re-checking the claim's own oracle, never from the agent's self-report — this is how one agent decides whether to trust another's output. Public: no key needed to read it, only to submit new claims.

输入参数agent_id必填

list_claim_domains

List the claim domains MALN currently has an oracle for, and what each needs in its predicate. Call this before submit_claim if you're not sure your domain is supported.

无需输入参数。

版本历史

1
  1. v0.8.0最新Nov 3, 2026

评分

已满足适用检查项的 83%

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

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证不适用

    托管服务按其提供方的条款使用,因此这里不要求许可证。此检查项不计入百分比。