프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. 리뷰와 계정 기능은 다음 단계에서 열려요.
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

Agentery

제작자: ntlgnc버전 1.28.2i★ –i클라우드에서 실행
레지스트리 이름com.agentery/agentery

설치

개요

제작자가 쓴 설명(영어 원문)

Find and compare 41,000+ AI agents, MCP servers and APIs, with daily prices and the AEPI price index

PopNx MCP의 세 기둥

이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.

할 수 있는 일

이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.

  • 연결 방식: 클라우드에서 실행
  • 전송 방식: Streamable HTTP
  • 카테고리: 기타

설치

쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.

설치하기 전에

필요한 것

어떤 앱을 쓰세요?

위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.

웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:

  1. Settings → Connectors 열기
  2. Add custom connector 누르기
  3. 아래 주소를 붙여 넣고 Add 누르기
  4. 로그인하라고 하면 제작자의 서비스에 로그인하기
SettingsConnectors1+ Add2https://…3
https://agentery.com/api/mcp

터미널에서 이 명령어를 실행하세요

claude mcp add --transport http agentery https://agentery.com/api/mcp

Cursor에서 열기

또는 설정을 직접 복사하기

프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요

{
  "mcpServers": {
    "agentery": {
      "url": "https://agentery.com/api/mcp"
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

VS Code에서 열기

또는 설정을 직접 복사하기

프로젝트의 .vscode/mcp.json에 붙여 넣으세요

{
  "servers": {
    "agentery": {
      "type": "http",
      "url": "https://agentery.com/api/mcp"
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:

  1. 웹에서 ChatGPT 열기 → Settings → Connectors (Apps)
  2. Create 또는 Add 누르기(일부 요금제는 먼저 Advanced에서 Developer mode를 켜야 해요)
  3. 아래 주소를 붙여 넣고 이름을 정한 뒤 저장하기
  4. 로그인하라고 하면 제작자의 서비스에 로그인하기
SettingsConnectors1+ Create2https://…3
https://agentery.com/api/mcp

메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.

선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.

이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.

할 수 있는 일

도구 이름과 설명은 서버가 2026년 11월 6일에 알려 준 그대로예요. 우리가 아니라 제작자가 쓴 글이고, 일반 텍스트로만 보여 드려요.

  • research_capability

    Gives a one-call first overview of a buying task: market prices, a short priced shortlist and alternatives together. Use this when you want a quick picture: the closest listings (matched on what they do, no fixed categories), price range and median for comparable products (with n

  • search_providers

    Finds products (AI products, AI agents, MCP servers or APIs) that do a task and returns a ranked shortlist; start here to choose a product. Use this when someone wants candidates, e.g. 'MCP server to reply to Zendesk tickets'. Each result has what it does, a fit label (match / pa

  • find_market

    Maps a task to its market: who competes there, how many are priced, and the price level per buyer tier. Use this when someone asks who competes in a space or what a kind of product costs, e.g. 'tools that monitor competitor pricing'. Returns the market label (nearest providers by

  • compare_providers

    Use to compare 2–6 shortlisted listings side by side — plan-level prices (e.g. the Pro tier), capabilities, deployment, licence and how to connect — or to check a quote against alternatives. Inputs resolve to real listings by exact handle, then exact name, never a silent fuzzy sw

  • get_price_index

    Use when asked whether prices of AI agents, tools or MCP servers are rising or falling overall. Returns the current Agent Economy Price Index (AEPI), a chained quoted-price index of observed agent and MCP pricing in US dollars (changes in the publicly quoted price of the same pro

  • price_benchmark

    Judges a specific price or quote against the closest comparable products by what they do (no fixed categories), in the buyer's tier and pricing unit. Use this when asked whether a price is fair or what a capability typically costs, e.g. 'Is $49/month reasonable for an AI SDR for

  • request_research

    Use when a buying decision hinges on one specific fact about one listing that its profile does not settle, e.g. {"provider_id":"flux_operator","requirement":"Is there a Helm chart for Kubernetes?"} or 'Does the Business plan go to checkout or to contact sales?'. Agentery reads th

  • get_research

    Status and result of a research job created by request_research. status: queued / running / answered / partly_answered / still_unknown / failed; phase: queued | running | retry_scheduled | completed_answer | completed_unknown | failed. Poll no more often than poll_after_seconds —

  • stop_research_updates

    Stop watching a research job (the result stays retrievable with get_research).

  • refine_results

    Use when an earlier search_providers or research_capability answer missed what was meant: pass its request_ref and the correction in plain words (e.g. 'must integrate with Slack', 'budget is $20/month', 'data must stay in the EU'). Agentery re-runs the search with the changed con

  • get_group_fair_price

    Gives the broad group-wide fair price for a kind of product: the median entry monthly price per buyer tier across its whole product group. Use this when you want a general price guide: give a task or product type (or a group_id from the group price league) and get the fair price

  • get_price_index_history

    Use to show how AI agent and MCP prices have moved over time: the dated Agent Economy Price Index series, the same chained quoted-price series (US dollars, base 100 = 30 Jun 2026) agentery.com/aepi charts. Points are index levels, never prices; calendar days with no published obs

  • market_gaps

    Finds jobs callers ask for that few paid products serve: requests seen on this MCP server, clustered by meaning, that sit far from any paid provider. Use this when a seller or investor asks where under-served opportunities are. Returns the request phrasing, distinct_callers, raw_

  • suggest_alternatives

    Find related alternatives to a known provider, ranked by text-embedding nearness to that provider's OWN profile (NO category lookup), each with observed price, endpoint liveness, community upvotes and how_to_connect (website, docs, mcp endpoint). For cheaper_only, inspect whether

  • demand_signals

    Lists searches that found nothing good: queries by external callers in the last 90 days that returned no provider or only weak matches (best relevance below 0.62). Use this when you want searches Agentery could not answer well, as generalised job labels ranked by distinct callers

  • report_outcome

    Report the result of ACTUALLY USING a listed provider for a task. Testing Agentery's connection or retrieval does not establish that the listed provider worked — do not report those. Reports are self-reported evidence subject to eligibility checks: they are correlated with your r

  • get_provider_profile

    Use to check one specific listing before recommending or connecting it: plans and prices with billing units, what it does, integrations, deployment (hosted / self_hosted / both / unknown, with evidence), licence (named licence only), liveness and how to connect (website, docs, MC

  • get_provider

    For buying decisions prefer get_provider_profile (prices, deployment, evidence); use this only for the short public directory card of one provider by handle or registration number: bio, source URLs, X-verification status, entity type, community rating and structured profile when

  • market_report

    Measures ONE market in depth before building or investing: the full observed price distribution by provider type and buyer tier, and the providers competing there. Use this when you need detailed market numbers, not a quick map. The market is the semantic neighbourhood of your qu

  • create_custom_benchmark

    Use when someone wants to keep watching the prices of products they choose (e.g. five named writing tools). Creates a PRIVATE custom benchmark (a saved, calculated peer cohort) over Agentery's data — no account needed. Two modes: (A) explicit members: pass `members` (a list of ex

  • get_custom_benchmark

    Get a private custom benchmark's current report: members, current stats (headline median/quartiles only when ≥3 comparable priced members — monthly, per-seat and per-call prices are never blended), buyer-tier / provider-type / pricing-unit cohorts, historical index, and data cove

  • update_custom_benchmark

    Add/remove members or rename a custom benchmark. Creates a NEW immutable version (the previous version stays fully reproducible) and returns the exact change-impact on the median/quartiles/index. Pass `benchmark_id`.

  • delete_custom_benchmark

    Disable access to a custom benchmark. Keeps only a minimal audit record; no underlying Agentery data is touched. Pass `benchmark_id`.

기본 점검i

누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검

  • ✓ 통과

    제작자와 저장소 일치

    레지스트리 이름이 도메인 agentery.com 기준으로 확인되었어요(레지스트리가 도메인 소유를 확인해요)

  • … 아직 점검 안 함

    계속 관리되고 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • … 아직 점검 안 함

    라이선스 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • ✓ 통과

    엔드포인트 응답

    451ms 만에 응답(HTTP 200)

  • – 해당 없음

    OAuth로 로그인

    로그인 필요 없음

  • ✓ 통과

    도구 설명에 숨겨진 지시 없음

    도구 설명 23개를 읽었고, AI에게 보내는 숨겨진 지시는 없었어요

기타 카테고리의 다른 서버와 비교i

  • 이 카테고리의 다른 서버 18353개 중 0%보다 스타가 많아요
  • 이 카테고리의 다른 서버 18353개 중 87%보다 최근에 레지스트리에 공개됐어요
  • 기본 점검 결과가 이 카테고리의 다른 서버 18353개 중 100%와 같거나 더 좋아요

레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.

자주 묻는 질문

Agentery, 안전한가요?

해당하는 기본 점검 3개 중 3개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.

어떤 키나 코드가 필요한가요?

레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.

내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?

제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.

아직 관리되고 있나요?

GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.28.2)은 6일 전 레지스트리에 올라왔어요.

어떤 앱에서 쓸 수 있나요?

Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.

대신 쓸 수 있는 건 뭐가 있나요?

같은 카테고리에는: Spec Driven Development, Remote Desktop Commander, Date Math

대안

같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.

카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i

Spec Driven Development

제작자: formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

내 컴퓨터에서 실행★ 440MIT14개월 전 업데이트
설치

Remote Desktop Commander

제작자: desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

클라우드에서 실행★ 211그저께 업데이트
설치

Date Math

제작자: JowenDelaPena

Date/time math for agents: business days, holidays, time zones, cron, RRULE. 25 free calls/day.

컴퓨터 또는 클라우드오늘 업데이트
설치

제작자의 README

README 열기

제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.

Agentery plugin

The official Agentery plugin for AI coding agents and assistants. It connects your agent to Agentery's hosted MCP server so it can:

  • find suitable AI tools — AI products, agents, MCP servers and APIs for a specific task, with task fit and delivery type stated;
  • compare their published prices — plans, billing units and pricing for a shortlist, side by side on one basis;
  • check fair market prices — the median and typical range for comparable products, by buyer tier and billing unit.

Agentery reports only what vendors publish, with the source and the date each price was observed. A missing price is shown as unknown, never as zero, and "contact sales" is not treated as a price.

This repository contains only the plugin wrapper (manifests, MCP configuration, one skill and a logo). Agentery's server code, database and index methodology are not part of it.

Install

One repository works on every platform. Each one reads its own manifest and connects to the same endpoint, https://agentery.com/api/mcp. No account, no sign-in and no API key are needed on any of them.

PlatformInstallFiles it reads
Grok Buildgrok plugin marketplace add xai-org/plugin-marketplace then grok plugin install agentery --trust.grok-plugin/plugin.json, .mcp.json, skills/
GitHub Copilot CLIcopilot plugin install ntlgnc/Agentery-Plugin (see below)plugin.json, mcp.json, skills/
Claude Codeclaude --plugin-dir , or install from any marketplace that lists it.claude-plugin/plugin.json, .mcp.json, skills/
CursorFrom a clone as a local plugin, or from the Cursor marketplace once listed.cursor-plugin/plugin.json, mcp.json, skills/
Codex and other Agent Plugins clientsInstall from a clone or a marketplace that lists itplugin.json, mcp.json, skills/
Gemini CLIgemini extensions install https://github.com/ntlgnc/Agentery-Plugingemini-extension.json
Any other MCP clientAdd a remote (streamable HTTP) MCP server with URL https://agentery.com/api/mcp and no authnone

Claude (claude.ai and Claude Desktop) can also connect directly: Settings → Connectors → Add custom connector → https://agentery.com/api/mcp.

GitHub Copilot

Copilot CLI reads the Agent Plugins manifest (plugin.json) and mcp.json at the repository root.

copilot plugin install ntlgnc/Agentery-Plugin

copilot mcp get agentery # shows: Type http, URL https://agentery.com/api/mcp, Source: Plugin

Copilot CLI marks direct repository installs as deprecated in favour of marketplace installs. Once Agentery is listed in the github/copilot-plugins marketplace, install it from there instead:

copilot plugin marketplace add github/copilot-plugins

copilot plugin install agentery@copilot-plugins

Then ask, for example: *"Using Agentery, what is a fair monthly price for an AI meeting-notes tool for a small team?"* No sign-in or API key is needed for Agentery; Copilot itself needs your usual GitHub Copilot login.

Copilot in VS Code (agent mode): run MCP: Add Server → HTTP → https://agentery.com/api/mcp, name it agentery, and leave authentication empty.

Tools

The server exposes 23 tools. Each carries MCP readOnlyHint / destructiveHint annotations.

GroupTools
Findsearch_providers, research_capability, find_market, suggest_alternatives
Inspect & compareget_provider_profile, get_provider, compare_providers
Fair pricesprice_benchmark, get_group_fair_price, market_report
Price indexget_price_index, get_price_index_history (Agent Economy Price Index)
Demanddemand_signals, market_gaps
Product questionsrequest_research, get_research, stop_research_updates
Your own itemsrefine_results, report_outcome, create_custom_benchmark, get_custom_benchmark, update_custom_benchmark, delete_custom_benchmark

16 tools are read-only. 7 write, and each changes only the caller's own items: a research request, a refinement of your own search, an outcome report, or a private benchmark. No tool changes Agentery's shared market data.

Network endpoints and credentials

  • Endpoint: https://agentery.com/api/mcp — Agentery's hosted MCP server over HTTPS (streamable HTTP). Tool arguments are sent there and nowhere else.
  • Authentication: none. The public server is keyless; the plugin sends no headers and no token.
  • Authentication exception: the server also has one partner-only tool, rank_providers_for_workflow, which requires a partner Bearer key. It is not listed to keyless connections, refuses keyless calls, and is not used by this plugin.
  • Private benchmarks: create_custom_benchmark returns a private access token. It is a capability for that one benchmark, not an account credential; the plugin does not store it.
  • Rate limit: 30 tool calls per minute per IP.
  • Not included: no hooks, no commands, no lifecycle or install scripts, no local processes, no telemetry, no environment variables and no filesystem access.

Privacy and terms

  • Privacy policy: https://agentery.com/privacy
  • Terms of service: https://agentery.com/terms
  • Documentation and examples: https://agentery.com/connect
  • Support: help@agentery.com

License

The plugin wrapper in this repository is released under the MIT License. Use of the Agentery service is governed by its terms of service.

PopNx에게 묻기