Skip to main content
Glama
deenesjakoruzh
yripper

Remote MCP Server on Cloudflare

by yripper
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Cloudflare의 원격 MCP 서버

Cloudflare Workers에서 OAuth 로그인을 포함한 원격 MCP 서버를 구동해 보겠습니다!

지역적으로 개발하다

지엑스피1

브라우저에서 http://localhost:8787/ 열 수 있어야 합니다.

Related MCP server: Remote MCP Server on Cloudflare

MCP 검사기를 서버에 연결하세요

새로운 MCP API를 살펴보려면 MCP Inspector를 사용하세요.

  • npx @modelcontextprotocol/inspector 로 시작하세요

  • 검사기 내에서 전송 유형을 SSE 로 전환하고 연결할 MCP 서버의 URL로 http://localhost:8787/sse 입력합니다.

  • 베어러 토큰을 추가하고 "연결"을 클릭하세요.

  • "목록 도구"를 클릭하세요

  • 검사기에서 설정한 Authorization 헤더를 반환해야 하는 "getToken" 도구를 실행하세요.

Claude Desktop을 로컬 MCP 서버에 연결하세요

{
  "mcpServers": {
    "remote-mcp-server-bearer-auth": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8787/sse",
        "--header",
        "Authorization: Bearer ${AUTH_TOKEN}"
      ]
    },
    "env": {
      "AUTH_TOKEN": "..."
    }
  }
}

Cloudflare에 배포

npm run deploy

원격 MCP 클라이언트에서 새로 배포된 원격 MCP 서버를 호출합니다.

위의 "로컬에서 개발"에서 한 것처럼 MCP 검사기를 실행합니다.

npx @modelcontextprotocol/inspector@latest

그런 다음 검사기에 Worker의 workers.dev URL(예: worker-name.account-name.workers.dev/sse )을 연결할 MCP 서버의 URL로 입력하고 "연결"을 클릭합니다.

이제 원격 MCP 클라이언트에서 MCP 서버에 연결되었습니다. 위에서 언급한 것처럼 Bearer 토큰을 전달할 수 있습니다.

디버깅

문제가 발생하면 Claude를 다시 시작하거나 다음 명령을 사용하여 명령줄에서 MCP 서버에 직접 연결을 시도하면 도움이 될 수 있습니다.

npx mcp-remote http://localhost:8787/sse

드물지만 ~/.mcp-auth 에 추가된 파일을 지우는 것이 도움이 될 수 있습니다.

rm -rf ~/.mcp-auth

Available Tools

1 tool
get_list_tweetsC

Get tweets from a specific list

ParametersJSON Schema
NameRequiredDescriptionDefault
list_idYesID of the list to get tweets from
max_resultsNoMaximum number of tweets to return

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions 'Get tweets' but doesn't disclose behavioral traits like read-only vs. destructive, authentication needs, rate limits, or response format. This leaves the agent with insufficient information for safe invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with zero waste, making it highly concise and well-structured. It efficiently conveys the core purpose without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description is incomplete. It doesn't cover behavioral aspects, usage context, or return values, making it inadequate for a tool with parameters and potential complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters (list_id and max_results). The description adds no additional meaning beyond what the schema provides, such as format details or usage tips, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get tweets from a specific list' clearly states the action ('Get') and resource ('tweets from a specific list'), making the purpose understandable. However, it lacks specificity such as mentioning retrieval or listing, and with no sibling tools, it doesn't need to differentiate, so it's not a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool, such as prerequisites, alternatives, or context. It simply states what it does without indicating usage scenarios, which is a significant gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • Addedget_list_tweets
Deploy Server
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.

Naming Consistency5/5

A single tool inherently has consistent naming, as there are no other tools to compare it against. The name 'get_list_tweets' follows a clear verb_noun pattern.

Tool Count2/5

One tool is generally too few for a server's purpose, as it limits functionality and suggests an incomplete or narrow scope. This is borderline inadequate for typical MCP server operations.

Completeness2/5

Inferring the domain as Twitter list management, the tool surface is severely incomplete. It only allows getting tweets from a list, with no capabilities for creating, updating, deleting lists, or interacting with tweets beyond retrieval, leading to significant gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches