Stellar Agent Search

Name: Stellar Agent Search
Author: berkingurcan

作者：berkingurcan版本 0.1.0i★ –i在你的电脑上运行

注册名称io.github.berkingurcan/stellar-agent-search

安装

概览

作者提供的说明（英文原文）

Discover and rank Stellar 8004 agents with a read-only MCP server and fail-closed contract probes.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 搜索与 AI 记忆

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： STELLAR_NETWORK, EXPLORER_BASE_URL, STELLAR_RPC_URL, VERIFY_ONCHAIN

你需要

npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "stellar-agent-search": {
      "command": "npx",
      "args": [
        "-y",
        "stellar-agent-search"
      ],
      "env": {
        "STELLAR_NETWORK": "your-value",
        "EXPLORER_BASE_URL": "your-value",
        "STELLAR_RPC_URL": "your-value",
        "VERIFY_ONCHAIN": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add stellar-agent-search --env STELLAR_NETWORK=your-value --env EXPLORER_BASE_URL=your-value --env STELLAR_RPC_URL=your-value --env VERIFY_ONCHAIN=your-value -- npx -y stellar-agent-search

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "stellar-agent-search": {
      "command": "npx",
      "args": [
        "-y",
        "stellar-agent-search"
      ],
      "env": {
        "STELLAR_NETWORK": "your-value",
        "EXPLORER_BASE_URL": "your-value",
        "STELLAR_RPC_URL": "your-value",
        "VERIFY_ONCHAIN": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "stellar-agent-search": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "stellar-agent-search"
      ],
      "env": {
        "STELLAR_NETWORK": "your-value",
        "EXPLORER_BASE_URL": "your-value",
        "STELLAR_RPC_URL": "your-value",
        "VERIFY_ONCHAIN": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

STELLAR_NETWORK env
Stellar network to target: mainnet | testnet. testnet also requires EXPLORER_BASE_URL — the default explorer indexes mainnet only, and the server refuses to start on the mismatched pair.
EXPLORER_BASE_URL env
Override the stellar-8004 explorer API base URL.
STELLAR_RPC_URL env
Override the Soroban RPC URL used for the bounded Reputation-contract probe.
VERIFY_ONCHAIN env
Set to 'false' to skip the bounded contract probe; reputation fields remain Explorer-declared either way.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 berkingurcan 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

星标数多于此分类中其他 5670 个服务器的 0%
发布到注册中心的时间比此分类中其他 5670 个服务器的 26% 更新
基础检查结果等于或优于此分类中其他 5670 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Stellar Agent Search 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（0.1.0）于3个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它？

同一分类中有：Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者：upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT昨天更新

安装

Codebase Memory

作者：DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT21天前更新

安装

Exa

作者：exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT2个月前更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

stellar-agent-search

A read-only discovery layer on top of the [stellar-8004](https://stellar8004.com) registry — the ERC-8004-style Identity/Reputation/Validation contracts on Stellar mainnet.

It adds no contracts and forks nothing: it exposes the existing on-chain registry to MCP clients, keeps indexed reputation explicitly declared-vs-verified, and proves the full agent-finds-agent loop with recorded mainnet transactions.

npm · GitHub · Docs · Evidence package

npm	MCP Registry	Remote endpoint	Mainnet proof
✅ `0.1.0`	✅ published & verified	⏳ not deployed yet	✅ x402 payment · feedback

There are two official interfaces, not two copies of the stack. TypeScript applications, registration, and signed writes use the canonical @trionlabs/stellar8004 SDK from trionlabs/stellar-8004; MCP clients and terminal discovery use this package, which exact-pins that SDK internally. The upstream repo's restricted Supabase Studio /mcp is database-operator tooling behind SSH/IP controls, not an agent-registry MCP and must never be exposed as this runtime. See the integration boundary.

A read-only, keyless MCP server (and human CLI) that lets an AI agent — or you — discover, rank, and vet on-chain [stellar-8004](https://stellar8004.com) agents on Stellar mainnet, then prepare an x402 (USDC pay-per-call) payment. One binary speaks the Model Context Protocol over stdio to Claude Code / Cursor / Windsurf / Cline / VS Code, and doubles as a plain-terminal tool. A separate Cloudflare Worker implementation exposes the same surface over stateless Streamable HTTP, but that remote endpoint is not live yet; use the local stdio transport until its deployment canary passes.

npx -y stellar-agent-search@0.1.0 find "a paid web scraper with a good reputation"

AI agents: read [AGENTS.md](AGENTS.md) first. It routes each goal to the right document: using the

tools, integrating from code, building a service other agents can find and pay

(provider guide), or changing this repo. Link index:

llms.txt · machine-readable schemas: mcp-surface.json.

Why this exists: declared data vs. what the chain read can prove

Off-chain agent directories (A2A cards, the MCP Registry, OASF, NANDA) list self-declared agents. That is exactly where the trust gap lives. A 2026 study of the ERC-8004 ecosystem (arXiv 2606.26028) found that only 3–15% of registrations have a live endpoint, and 59–91% of "reviewers" are Sybils.

stellar-8004 is the only non-EVM ERC-8004 implementation we are aware of running on mainnet (66 agents on Stellar mainnet as of July 2026; get_registry_stats returns the current count). No published survey enumerates non-EVM deployments — the study above restricts itself to Ethereum, BSC and Base, "the three chains with the highest registration and feedback volume" — so read that as unrefuted, not as proven. This server adds something a directory listing cannot give you: a bounded Reputation-contract reachability probe. The current path calls get_clients_paginated once with a six-slot observation window. The contract exposes no authoritative client count/cursor, and expired client-index entries create holes, so even an empty or short page cannot prove that no later live client exists. Calling get_summary over that set would manufacture a false match or mismatch; this release therefore does not call it and verifies no reputation fields. An attempted, reachable probe returns unavailable with reason client-set-exhaustion-unprovable; verifiedFields is empty and average, feedback count, and unique clients all remain unverified. verified/partial/mismatch are reserved for a future authoritative aggregate. The full status set remains verified | partial | mismatch | unavailable | skipped. Self-declared marketing text (name, description, service labels, feedback tags) remains untrusted data, never instructions (see Security).

That fail-closed boundary — plus a versioned declared-evidence heuristic — is the product. Normalized Explorer quality is multiplied by fixed evidence strength (0.4 × capped volume + 0.6 × effective breadth). Effective unique clients cannot exceed feedback rows, and repeated rows per declared client are capped. These are cost-of-manipulation proxies, not chain verification, proof of personhood, or Sybil resistance.

What it exposes

All three MCP primitives, all read-only:

Tools

Tier	Tool	What it does
0 · SOW	`find_agent`	Natural-language discovery → ranked candidates
	`rank_agent`	Rank an explicit id set or a query, full 3-axis declared-reputation breakdown + bounded chain reachability
	`get_agent_profile`	Deep profile: identity, capabilities, declared reputation + contract-probe limits, recent feedback, unverified A2A projection
	`list_services`	Self-declared x402/MPP endpoint candidates; liveness, ownership, conformance, and payment stay unverified
1 · complete-core	`list_agents`	Paginated, filterable listing, ranked
	`leaderboard`	Top agents in a bounded scan (client-side 3-axis rank + coverage)
	`resolve_agent`	Any handle (id / stellar:…#id / owner G-address) → canonical identifiers
	`get_agents_by_owner`	Current owner API page (up to 20 agents) with explicit continuation coverage
	`get_agent_feedback`	Recent on-chain reviews (sanitized, labeled)
	`verify_reputation`	Fail-closed Reputation-contract reachability probe; no current fields are verified
	`get_agent_card`	Derived, unverified A2A-shaped projection + x402 hint; not protocol-conformance proof
	`get_registry_stats`	Exact-count queries + capped sampled metrics, with definitions and coverage
	`get_registry_health`	Per-registry indexer staleness
2 · provider network	`get_provider_manifest`	A Provider Standard v1 provider's prices in USDC, network, payee and result retention; its binding to the on-chain registration and wallet; conformance badges from trusted validators

Full per-tool reference (inputs, outputs, defaults): [docs/tools.md](docs/tools.md).

Resources — `stellar8004://` (pinnable context)

registry · leaderboard · health · agent/{id} · agent/{id}/card · agent/{id}/feedback · agent/{id}/reputation · owner/{address}. Each returns a dual JSON + rendered-markdown payload.

Prompts — slash workflows

/find-and-vet-agent (flagship) · /vet-agent · /compare-agents · /prepare-x402-call · /explore-registry. prepare-x402-call lays out the exact x402 flow and stops before signing — this server holds no keys.

Quickstart

One-command MCP setup (Claude Code):

npx -y stellar-agent-search@0.1.0 setup --client claude --scope user --handshake

This downloads the package, registers a version-pinned npx -y stellar-agent-search@0.1.0 mcp stdio launch through Claude Code's own CLI, then performs a real MCP initialize + tools/list handshake. It is idempotent: rerun with --check --handshake to verify without changing config, or use --dry-run to preview the registration. Cursor and Codex examples, config paths, and scope limitations are in [docs/getting-started.md](docs/getting-started.md). Manual configs for other clients remain in [docs/integration.md](docs/integration.md).

Optionally install the skill first — the usage guide your agent reads before it calls anything:

npx skills add berkingurcan/stellar-agent-search --skill mcp

Terminal (human CLI):

npx -y stellar-agent-search@0.1.0 find "web scraper" --x402       # discover

npx -y stellar-agent-search@0.1.0 profile 10 # full profile for agent 10 npx -y stellar-agent-search@0.1.0 rank "scraping agents" --json # rank + fail-closed contract-probe status, machine-readable npx -y stellar-agent-search@0.1.0 services --x402 # declared paid-endpoint candidates npx -y stellar-agent-search@0.1.0 doctor # self-check: env, explorer, RPC, bounded read path npx -y stellar-agent-search@0.1.0 setup --client cursor --scope project --dry-run # preview client config

New here? Start with [docs/getting-started.md](docs/getting-started.md).

Remote endpoint status

The intended hosted URL is https://mcp.stellar8004.com/mcp. The Worker, transport tests, routing, and hardening are implemented, but the route has not been deployed: /mcp currently falls through to the landing site and returns 404. Deployment remains deliberately blocked until the Cloudflare rate-limit namespace is replaced from its sentinel value and a live canary proves that the original caller identity is preserved through the Service Binding. Do not configure a remote MCP client against that URL yet.

The landing page and MCP runtime are separate Workers. The assets-only landing Worker owns the mcp.stellar8004.com custom domain; exact /mcp and /healthz zone routes will send only those two paths to the runtime Worker. The runtime reads the existing stellar8004-web API through a Cloudflare Service Binding. It does not connect to Supabase, hold a service-role key, or create a second indexer. See [docs/architecture.md](docs/architecture.md) and [docs/stellar8004-integration.md](docs/stellar8004-integration.md).

Configuration

All configuration is via environment variables (canonical for MCP mode); CLI flags override them (precedence: flag → env → default).

Env var	Default	Purpose
`STELLAR_NETWORK`	`mainnet`	`mainnet` or `testnet`. With no other data source set, `testnet` reads its newest agents straight from the Identity contract, see below
`EXPLORER_BASE_URL`	`https://stellar8004.com` on mainnet	Explorer HTTP API base. Indexes mainnet only, so testnet never falls back to it
`REGISTRY_AGENT_IDS`	—	Registry mode over an allowlist: comma-separated agent ids (at most 50) read straight from the Identity contract, no explorer. Not combinable with `EXPLORER_BASE_URL` or `REGISTRY_SCAN_LIMIT`
`REGISTRY_SCAN_LIMIT`	`50` on testnet	Registry mode over the newest agents: how many (1–50) of the most recently registered agents lists and searches read. Testnet's default source; set it on mainnet to use it there instead of the explorer. Not combinable with `EXPLORER_BASE_URL` or `REGISTRY_AGENT_IDS`

| TRUSTED_VALIDATORS | — | Comma-separated G… or C… addresses (at most 20) of the verifiers whose Validation Reg

只显示了开头部分；其余内容请在仓库中阅读