Skip to main content
Glama
deenesjakoruzh
ygdotcom

Banana Peel

by ygdotcom
OverviewSchemaRelated ServersScoreDiscussions
Remote

Banana Peel MCP — 브라우저 에이전트용 OpenRouter

@banana-peel/mcp

Banana Peel용 공식 Model Context Protocol 서버입니다.

코딩 에이전트는 curl을 직접 작성하는 대신 Banana Peel을 네이티브 MCP 도구로 호출합니다.

문서: https://bananapeel.com/docs/mcp

용어: routing은 요청하는 대상이며, banana_peel.runner는 실행을 담당한 runner입니다.

한 줄 설치

npx -y @banana-peel/mcp

또한: npm install -g @banana-peel/mcp (bananapeel-mcp로 실행됩니다).

배포 (관리자)

# requires npm login with rights to @banana-peel (and bare bananapeel for the alias)
cd mcp && npm publish --access public
cd alias && npm publish --access public   # after @banana-peel/mcp is live

Related MCP server: browser-gateway

인증

export BANANA_PEEL_API_KEY=bp_live_…   # or BANANAPEEL_API_KEY
export BANANA_PEEL_BASE=https://bananapeel.com  # optional

Cursor

~/.cursor/mcp.json (또는 프로젝트 .cursor/mcp.json):

{
  "mcpServers": {
    "bananapeel": {
      "command": "npx",
      "args": ["-y", "@banana-peel/mcp"],
      "env": {
        "BANANA_PEEL_API_KEY": "bp_live_…"
      }
    }
  }
}

Claude Desktop

claude_desktop_config.json:

{
  "mcpServers": {
    "bananapeel": {
      "command": "npx",
      "args": ["-y", "@banana-peel/mcp"],
      "env": {
        "BANANA_PEEL_API_KEY": "bp_live_…"
      }
    }
  }
}

도구

도구

API

create_response

POST /api/v1/responses (선택 사항 출력 정규화: normalize + output_schema, +$0.10 / 실행)

get_response

GET /api/v1/responses/:id (선택 사항: 종료 상태/requires_action까지 폴링)

submit_input

POST /api/v1/responses/:id/input (MFA/OTP/텍스트)

cancel_response

POST /api/v1/responses/:id/cancel (진행 중인 실행 중지)

list_runs

GET /api/v1/runs

list_rankings

GET /api/v1/rankings

list_capabilities

GET /api/v1/capabilities

도구 이름과 HTTP 매핑은 src/tool-catalog.ts(MCP 서버 레지스트리)에 정의되어 있습니다.

출력 정규화 (+$0.10)

create_response에 output_schema(JSON Schema 또는 속성 맵)와 함께 normalize: true를 전달하면 실행 후 runner 결과를 재구성합니다. 해당 실행에는 +$0.10이 정액으로 부과됩니다. 스키마 빌더: Console → Normalize (/normalize).

이 저장소에서 개발하기

npm install
npm run build
npm start
# or: npm run dev

MFA 흐름

  1. background: true와 함께 create_response 호출

  2. status: "requires_action"가 될 때까지 wait: true로 get_response 호출

  3. { "code": "123456" } 또는 { "answer": "…" }와 함께 submit_input 호출

  4. completed / failed 상태가 될 때까지 wait: true로 get_response 호출

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd
A
license - permissive license
Not graded
quality - not tested
B
maintenance

How are these scores calculated?

Maintenance

1Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • browser-gateway

    browser-gateway
    A
    license
    Not graded
    quality
    A
    maintenance
    Reliable, scalable browser infrastructure for AI agents. Route, pool, and failover across any browser provider. 8 built-in browser tools using raw Chrome CDP - navigate, screenshot, snapshot, interact, evaluate. Zero-config with auto Chrome detection & concurrent sessions support
    1,305
    7
    MIT

  • Leapfrog MCP

    anthonybono21-cloud
    A
    license
    B
    quality
    D
    maintenance
    Multi-session browser MCP server that gives AI agents up to 15 fully-isolated browsers running in parallel. 36 tools including navigation, extraction, network intercept, stealth, and self-improvement. Each session has its own cookies, storage, and fingerprint so agents never collide.
    37
    65
    5
    MIT

  • Rove

    noncelogic
    A
    license
    C
    quality
    D
    maintenance
    Hosted Playwright browser automation for AI agents. Returns accessibility trees instead of screenshots, cutting token usage by 77%. Navigate, interact, extract structured data, and take screenshots — all via MCP. Zero infrastructure, credit-based pricing.
    6
    104
    MIT

View all related MCP servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ygdotcom/banana-peel-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server