Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Time Server what's the current time in Tokyo?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server providing time-related tools with dual-mode support:
Stdio transport for local MCP clients (via npm)
Streamable HTTP transport for remote access (via Cloudflare Workers)
This server allows LLMs to access various date/time functions through multiple connection methods.
MCP Central Server Card: https://guide-gen.mcpcentral.io/servers/io-github-mcpcentral-io-mcp-time
Provides the following MCP tools:
current_time: Get the current date and time in specified formats and timezones.
relative_time: Get a human-readable relative time string (e.g., "in 5 minutes", "2 hours ago").
days_in_month: Get the number of days in a specific month.
get_timestamp: Get the Unix timestamp (milliseconds) for a given time.
convert_time: Convert a time between different IANA timezones.
get_week_year: Get the week number and ISO week number for a given date.
Related MCP server: Time MCP Server
mcp-time/
├── src/
│ └── index.ts # Cloudflare Worker entry point & MCP logic
├── package.json # Project dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── wrangler.toml # Cloudflare Worker configurationInstall the package globally or use with npx:
# Global installation
npm install -g @mcpcentral/mcp-time
# Or use directly with npx
npx @mcpcentral/mcp-timeConnect directly to the deployed Cloudflare Worker:
Example:
https://mcp.time.mcpcentral.ioConfigure your MCP client (e.g., Claude Desktop) to use the stdio transport:
{
"mcpServers": {
"time-server": {
"command": "npx",
"args": ["@mcpcentral/mcp-time"]
}
}
}Or with global installation:
{
"mcpServers": {
"time-server": {
"command": "/path/to/node/bin/mcp-time"
}
}
}Configure your MCP client to use the remote HTTP endpoint:
{
"mcpServers": {
"time-server": {
"url": "https://mcp.time.mcpcentral.io",
"transport": "streamable-http"
}
}
}Clone the Repository:
git clone https://github.com/mcpcentral-io/mcp-time.git
cd mcp-timeInstall Dependencies:
npm installBuild: Compile the TypeScript code:
npm run build(This compiles src/index.ts to dist/index.js)
Test Locally:
Test Stdio Mode:
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | node dist/index.jsTest HTTP Mode (via Wrangler):
npx wrangler devThis will start the server on http://localhost:8787. You can then test with curl or point your MCP client to this local endpoint.
Configure Cloudflare:
cp wrangler.toml.example wrangler.tomlEdit wrangler.toml to configure your domain (optional).
Login and Deploy:
wrangler login
npx wrangler deployBuild the package:
npm run buildPublish:
npm publish --access publicNEW: Major providers have adopted the Model Context Protocol and now support Streamable HTTP servers directly. Anthropic, OpenAI, and Microsoft have all adopted this modern transport protocol.
📋 Protocol Note: Streamable HTTP is the modern replacement for the deprecated HTTP+SSE transport.
Anthropic's MCP Connector allows you to use Streamable HTTP servers directly through the Messages API without needing a separate MCP client.
The MCP Connector is perfect for this server since it uses the Streamable HTTP architecture. Simply include the server in your API requests:
curl https://api.anthropic.com/v1/messages \
-H "Content-Type: application/json" \
-H "X-API-Key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "anthropic-beta: mcp-client-2025-04-04" \
-d '{
"model": "claude-sonnet-4-20250514",
"max_tokens": 1000,
"messages": [{
"role": "user",
"content": "What time is it in Tokyo?"
}],
"mcp_servers": [{
"type": "url",
"url": "https://your.worker.url.workers.dev",
"name": "http-time-server"
}]
}'No client setup required - Connect directly through the API
Native Streamable HTTP support - Designed for servers like this one
OpenAI also supports Streamable HTTP servers through their Agents SDK using the MCPServerStreamableHttp class:
from agents.mcp.server import MCPServerStreamableHttp
# Connect to this Streamable HTTP server
server = MCPServerStreamableHttp({
"url": "https://your.worker.url.workers.dev",
"headers": {"Authorization": "Bearer your-token"}, # if needed
})
# Use the server in your OpenAI agent
await server.connect()
tools = await server.list_tools()
result = await server.call_tool("current_time", {"timezone": "Asia/Tokyo"})Microsoft Copilot Studio now supports Streamable HTTP servers with MCP integration generally available. You can connect this server to Copilot Studio by:
Building a custom connector that links your MCP server to Copilot Studio
Adding the tool in Copilot Studio by selecting 'Add a Tool' and searching for your MCP server
Using the server directly in your agents with generative orchestration enabled
Keep an eye out as more MCP clients adopt support for Streamable HTTP. Here are a few resources that maintain lists of MCP clients and their capabilities:
PulseMCP Client Directory - Comprehensive list of MCP clients
Official MCP Servers Repository - Official collection including client information
MCP.so Client Listings - Community-maintained client directory
Test your server using these web-based inspection tools:
MCPCentral Lab - Interactive testing environment for MCP servers
MCPCentral Inspector - Streamable HTTP server inspector
The official MCP Inspector is also available:
Or run: npx @modelcontextprotocol/inspector
Start your server:
# Local HTTP server
npx wrangler dev
# Or use deployed URL: https://mcp.time.mcpcentral.ioConnect with an inspector:
Transport: Streamable HTTP
URL: http://localhost:8787 or https://mcp.time.mcpcentral.io
Click Connect
Test the stdio transport directly:
# Test initialization
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | npx @mcpcentral/mcp-time
# Test tool call
echo '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"current_time","arguments":{"timezone":"America/New_York"}}}' | npx @mcpcentral/mcp-timeThe inspector will show all six time-related tools:
current_time: Test with different timezones (e.g., "America/New_York", "Europe/London")
relative_time: Test with various time strings (e.g., "2024-12-25T00:00:00Z")
days_in_month: Test with different months and years
get_timestamp: Convert date-time strings to Unix timestamps
convert_time: Convert between different timezones
get_week_year: Get week numbers for specific dates
Try these test cases in the inspector:
// current_time
{"timezone": "Asia/Tokyo", "format": "iso"}
// relative_time
{"time": "2024-12-25T00:00:00Z"}
// days_in_month
{"month": 2, "year": 2024}
// get_timestamp
{"time": "2024-06-15T12:00:00Z"}
// convert_time
{"time": "2024-06-15T12:00:00", "from": "UTC", "to": "America/Los_Angeles"}
// get_week_year
{"date": "2024-06-15"}Use the inspector to verify:
✅ Server connects successfully
✅ All 6 tools are listed
✅ Tool schemas are properly defined
✅ Tools execute without errors
✅ Results are formatted correctly
✅ Error handling works for invalid inputs
The MCP Inspector provides the most comprehensive way to test your server before integrating it with AI clients.
⚠️ IMPORTANT: This example server has NO authentication or security measures implemented.
Converts a time from a source IANA timezone to a target IANA timezone.
| Name | Required | Description | Default |
|---|---|---|---|
| time | Yes | The time to convert (e.g., "2025-03-23 12:30:00") | |
| sourceTimezone | Yes | Source IANA timezone name (e.g., "Asia/Shanghai") | |
| targetTimezone | Yes | Target IANA timezone name (e.g., "Europe/London") |
| Name | Required | Description |
|---|---|---|
| convertedTime | Yes | |
| hourDifference | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds the IANA timezone detail, which is useful. However, it does not disclose edge-case behaviors (e.g., invalid timezones, DST handling) beyond what the schema and annotations provide. With annotations present, a score of 3 is appropriate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence with no redundant information. Every word contributes to the meaning, and it is front-loaded with the core operation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity, the presence of a complete output schema, and thorough annotations, the description is sufficiently complete. It correctly identifies the operation without needing to cover return values or error cases, which are handled elsewhere.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% — every parameter has a description with examples. The description adds no additional parameter semantics beyond what the schema already provides, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool's verb ('converts'), resource ('a time'), and scope ('from a source IANA timezone to a target IANA timezone'). It clearly distinguishes this from sibling tools like current_time or relative_time, which serve different time-related purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies a clear usage context: use this tool when you need to convert a time between two IANA timezones. It does not explicitly mention alternatives or exclusions, but the clarity of the purpose makes it easy for an agent to select the tool appropriately. A slight deduction for lacking explicit contrast with sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns the current time in UTC and a specified or guessed IANA timezone.
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | Format for the returned time string (default YYYY-MM-DD HH:mm:ss) | |
| timezone | No | IANA timezone name (e.g., "America/New_York"). Defaults to the server's guessed timezone |
| Name | Required | Description |
|---|---|---|
| utcTime | Yes | |
| timezone | Yes | |
| localTime | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations (readOnlyHint=true, idempotentHint=true) already disclose safety and side-effect profiles. The description adds context that the time is returned in UTC and the IANA timezone can be specified or guessed. However, it does not elaborate on behavior such as error handling, default format, or the fact that repeated calls yield different times, leaving some transparency gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately states the tool's core function. It is front-loaded and contains no filler or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple, and the output schema likely covers return values, but the description lacks usage guidance and sibling differentiation. The absence of any mention of alternatives like get_timestamp creates a completeness gap, though the tool itself is well-scoped.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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. The description adds little beyond the schema, only weakly referencing the timezone parameter ('specified or guessed'). It does not enrich the meaning of the 'format' parameter, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool returns the current time in UTC and an IANA timezone. It uses a specific verb ('Returns') and identifies the resource ('current time'). However, it does not explicitly distinguish itself from sibling tools like get_timestamp, which might also return the current time in a different format.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 versus alternatives. It only states what it does, without mentioning exclusions, prerequisites, or sibling tools. For example, an agent may not know whether to choose current_time or get_timestamp for a given task.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns the number of days in the month of a given date.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | The date to check (format: YYYY-MM-DD). Defaults to current date |
| Name | Required | Description |
|---|---|---|
| days | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and idempotent behavior, so the agent knows it is safe. The description adds no additional behavioral details such as leap-year handling or timezone dependence, but it also introduces no contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that gets straight to the point with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one optional parameter, strong annotations, and an output schema. The description adequately identifies the purpose while the schema handles parameter details; no critical information appears missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention the 'date' parameter; however, the input schema fully covers it with format and default value. With 100% schema coverage, the description need not add parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (returns) and the resource (number of days in a month for a given date). This distinguishes it from sibling tools like relative_time or get_timestamp, which serve different time/date purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no explicit guidance on when to choose this tool over alternatives (e.g., current_time or convert_time). Usage is implied by the function—needing days in a month—but no alternatives or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Converts a date-time string to a Unix timestamp in milliseconds.
| Name | Required | Description | Default |
|---|---|---|---|
| time | No | The time to convert (format: YYYY-MM-DD HH:mm:ss). Defaults to current time |
| Name | Required | Description |
|---|---|---|
| timestamp | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, and the description aligns by describing a pure conversion operation. It adds useful context about the output unit (milliseconds) and input format, going beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no unnecessary words. It conveys the essential information efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one optional parameter, full schema coverage, an output schema, and annotations covering safety. The description, combined with structured data, fully specifies behavior without missing critical details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides complete documentation for the sole parameter 'time', including format and default behavior. The tool description adds no additional parameter semantics beyond what the schema already covers, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb 'converts' and resource 'date-time string to a Unix timestamp in milliseconds', clearly distinguishing it from sibling tools like current_time (retrieves current time) and relative_time (calculates relative times).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies use for converting date-time strings to Unix timestamps, but does not explicitly mention when to avoid this tool or name alternatives such as convert_time. This is clear context without exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns the week number and ISO week number for a given date.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | The date to check (e.g., "2025-03-23"). Defaults to current date |
| Name | Required | Description |
|---|---|---|
| week | Yes | |
| isoWeek | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare read-only and idempotent behavior, and the description adds clarity that both the standard week number and ISO week number are returned. No destructive side effects or auth requirements apply. The description doesn't discuss edge cases like invalid dates, but given the simplicity, this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, directly states the core functionality, and avoids redundant content. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one optional parameter and an output schema, the description is adequate. It explains what is returned and the input is given via schema. However, it could mention the default date behavior in the description itself, but schema covers it, so minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema fully documents the single parameter 'date' with an example and default. The description adds no additional parameter semantics beyond saying 'for a given date', which is already evident. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns week number and ISO week number for a given date. This is specific and distinct from sibling tools like current_time or convert_time. The verb 'Returns' is functionally clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives is provided. The description implies usage via its statement, but there is no mention of when to choose this over relative_time or get_timestamp. Score 3 due to implied usage only.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Calculates the relative time from now to a given date-time string.
| Name | Required | Description | Default |
|---|---|---|---|
| time | Yes | The time to compare (format: YYYY-MM-DD HH:mm:ss) |
| Name | Required | Description |
|---|---|---|
| relativeTime | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint: true, idempotentHint: true) already disclose the safe read-only behavior. The description adds that it computes relative time from now, but it does not provide deeper behavioral context such as timezone handling, date parsing details, or the exact nature of the output. This is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that is front-loaded with the action and resource. It wastes no words and is appropriately sized for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool with an output schema present, the description is sufficient. It explains the core function and the input format. It does not add extra contextual details like result examples or edge cases, but these are not needed given the simplicity and output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with a clear description of the 'time' parameter including format. The description does not add meaning beyond the schema, which already fully documents the parameter. Baseline 3 is appropriate when the schema handles parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Calculates the relative time from now to a given date-time string.' The verb 'calculates' and the resource 'relative time' are specific, and this tool is distinguishable from siblings like current_time or get_timestamp by focusing on relative time.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool (when you need relative time from now to a given date), but it does not explicitly contrast with alternatives or provide exclusions. The tool's purpose alone suggests usage, but there is no direct 'use this when...' or mention of sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.0.5convert_timecurrent_timedays_in_monthget_timestampget_week_yearrelative_timeEach tool targets a distinct time operation: current time, conversion, timestamp, relative time, calendar calculations. There is no functional overlap.
Names mix verb-first patterns (get_timestamp, convert_time) with noun/adjective-first patterns (relative_time, current_time, days_in_month). A consistent verb-noun convention would improve predictability.
Six tools is well-scoped for a time server, covering common time operations without unnecessary bloat.
Core time operations are covered, but a few useful additions (e.g., date arithmetic, timezone list, formatting) are missing. The current set is sufficient for standard use cases.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Current time, timezone conversion & date math for AI agents. On Cloudflare Workers.
Timezone MCP — wraps WorldTimeAPI (free, no auth)
Read-only developer, date, finance, and text utilities. Authless remote MCP server by Clean.tools.
Cloudflare Workers MCP server: cron-parser
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mcpcentral-io/mcp-time'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
