Skip to main content
Glama
salman-khandu

Remote MCP Server on Cloudflare

by salman-khandu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Remote MCP Server on Cloudflare

Let's get a remote MCP server up-and-running on Cloudflare Workers complete with OAuth login!

Develop locally

# clone the repository
git clone https://github.com/cloudflare/ai.git
# Or if using ssh:
# git clone git@github.com:cloudflare/ai.git

# install dependencies
cd ai
# Note: using pnpm instead of just "npm"
pnpm install

# run locally
npx nx dev remote-mcp-server

You should be able to open http://localhost:8787/ in your browser

Related MCP server: Remote MCP Server on Cloudflare

Connect the MCP inspector to your server

To explore your new MCP api, you can use the MCP Inspector.

  • Start it with npx @modelcontextprotocol/inspector

  • Within the inspector, switch the Transport Type to SSE and enter http://localhost:8787/sse as the URL of the MCP server to connect to, and click "Connect"

  • You will navigate to a (mock) user/password login screen. Input any email and pass to login.

  • You should be redirected back to the MCP Inspector and you can now list and call any defined tools!

Connect Claude Desktop to your local MCP server

The MCP inspector is great, but we really want to connect this to Claude! Follow Anthropic's Quickstart and within Claude Desktop go to Settings > Developer > Edit Config to find your configuration file.

Open the file in your text editor and replace it with this configuration:

{
  "mcpServers": {
    "math": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8787/sse"
      ]
    }
  }
}

This will run a local proxy and let Claude talk to your MCP server over HTTP

When you open Claude a browser window should open and allow you to login. You should see the tools available in the bottom right. Given the right prompt Claude should ask to call the tool.

Deploy to Cloudflare

  1. npx wrangler kv namespace create OAUTH_KV

  2. Follow the guidance to add the kv namespace ID to wrangler.jsonc

  3. npm run deploy

Call your newly deployed remote MCP server from a remote MCP client

Just like you did above in "Develop locally", run the MCP inspector:

npx @modelcontextprotocol/inspector@latest

Then enter the workers.dev URL (ex: worker-name.account-name.workers.dev/sse) of your Worker in the inspector as the URL of the MCP server to connect to, and click "Connect".

You've now connected to your MCP server from a remote MCP client.

Connect Claude Desktop to your remote MCP server

Update the Claude configuration file to point to your workers.dev URL (ex: worker-name.account-name.workers.dev/sse) and restart Claude 

{
  "mcpServers": {
    "math": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://worker-name.account-name.workers.dev/sse"
      ]
    }
  }
}

Debugging

Should anything go wrong it can be helpful to restart Claude, or to try connecting directly to your MCP server on the command line with the following command.

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

In some rare cases it may help to clear the files added to ~/.mcp-auth

rm -rf ~/.mcp-auth

Available Tools

2 tools
get_current_dateB

获取当前日期, 如果用户没有提供日期, 则返回当前日期, 如果用户提供的是相对单位, 如前天, 昨天, 明天, 则返回相对单位后的日期

ParametersJSON Schema
NameRequiredDescriptionDefault
dateYes日期 比如2025-05-29 或者 前天 昨天 明天

TDQS

B3.1/5.0
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 describes the core behavior (returning current date or calculating relative dates) but lacks important details: format of returned date, timezone handling, error behavior for invalid inputs, or whether this is a read-only operation. The description doesn't disclose these behavioral traits.

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

Conciseness4/5

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

The description is appropriately concise with two sentences that efficiently explain the tool's functionality. It's front-loaded with the main purpose and follows with usage details. There's no wasted text, though it could be slightly more structured for clarity.

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 the tool has no annotations and no output schema, the description is incomplete. It doesn't explain the return format (e.g., date string structure), error handling, or timezone considerations. For a date-handling tool with 1 parameter, more contextual details are needed to ensure proper agent usage.

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%, with the parameter 'date' clearly documented in the schema. The description adds some semantic context by explaining the two types of inputs (absolute dates like 2025-05-29 and relative units like yesterday), which complements the schema. However, it doesn't provide additional syntax or format details beyond what the schema already states.

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 clearly states the tool's purpose: '获取当前日期' (get current date) and explains it returns the current date or calculates relative dates like yesterday/tomorrow. It distinguishes from sibling 'get_current_weather' by focusing on dates rather than weather. However, it doesn't explicitly contrast with the sibling tool in the description text itself.

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

Usage Guidelines3/5

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

The description implies usage context: when users need current date or relative date calculations. It mentions handling both absolute dates (e.g., 2025-05-29) and relative units (e.g., yesterday). However, it doesn't provide explicit guidance on when to use this vs. alternatives or any exclusion criteria.

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

get_current_weatherC

Get weather info for a given city.

ParametersJSON Schema
NameRequiredDescriptionDefault
cityYes城市名称, 比如北京 上海 广州

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 the full burden. It mentions 'Get weather info' which implies a read-only operation, but doesn't disclose any behavioral traits like rate limits, error conditions, data freshness, or what 'weather info' includes (e.g., temperature, humidity). This leaves significant gaps for an agent.

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, efficient sentence with zero waste. It's front-loaded with the core action and resource, making it easy to parse quickly 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 explain what 'weather info' includes, potential errors, or any operational constraints. For a tool with one parameter but undefined output and behavior, this leaves too much ambiguity for reliable agent use.

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%, with the parameter 'city' fully documented in the schema. The description adds no additional meaning beyond implying the tool requires a city input, so it meets the baseline of 3 where the schema does the heavy lifting.

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 clearly states the verb ('Get') and resource ('weather info') with a specific scope ('for a given city'), making the purpose unambiguous. However, it doesn't explicitly differentiate from the sibling tool 'get_current_date', though the distinction is obvious from the names.

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?

No guidance is provided on when to use this tool versus alternatives or any contextual prerequisites. The description simply states what it does without indicating any constraints, dependencies, or comparison with the sibling tool beyond the obvious domain difference.

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. 2 tool updatesv1.0.0
    • First observedget_current_date
    • First observedget_current_weather
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes: one handles date calculations and the other provides weather information. There is no overlap in functionality, making it impossible for an agent to confuse them.

Naming Consistency5/5

Both tools follow a consistent verb_noun naming pattern (get_current_date and get_current_weather). The structure is uniform and predictable, with no deviations in style or convention.

Tool Count2/5

With only two tools, the server feels thin and under-scoped for a 'Remote MCP Server on Cloudflare', which implies broader capabilities. The tools are unrelated (date and weather), suggesting a lack of cohesive domain coverage.

Completeness2/5

The server's purpose is unclear from the toolset, but the two tools cover unrelated domains (date and weather) without any supporting operations. There are significant gaps, as neither domain has a complete lifecycle (e.g., no date formatting or historical weather), and the overall surface is severely incomplete for any coherent workflow.

Resources

Related MCP Connectors

Related MCP Servers