How do I use LeaveManager?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@LeaveManager What's my remaining annual leave balance?" 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.

LeaveManager

by DhanyaHegdek

Overview Schema Source Related Servers Discussions Admin

Python

MCP Server Setup Guide (Windows) — Leave Management Example

This README documents the full process of building a local MCP (Model Context Protocol) server in Python with uv, testing it with MCP Inspector, and connecting it to Claude Desktop on Windows — including the gotchas that come up along the way.

1. Project Setup

cd Desktop\MCP
mkdir my-mcp-server
cd my-mcp-server
uv init .
uv add "mcp[cli]"

Gotcha: Installing mcp[cli] with plain pip install mcp[cli] puts it in your global Python site-packages — NOT in the project's own uv virtual environment. uv run only sees packages installed via uv add (or uv pip install) inside the project. If you see:
Error: typer is required. Install with 'pip install mcp[cli]'
even after installing it, this is almost always the cause. Fix: run uv add "mcp[cli]" from inside the project folder.

Related MCP server: leave_manager

2. Example `main.py`

Build your server using FastMCP from the mcp package: create an mcp = FastMCP("YourServerName") instance, define functions decorated with @mcp.tool() for actions the AI can call (each with a clear docstring describing what it does — Claude uses this to decide when to call it), and optionally @mcp.resource("scheme://{param}") for read-only data resources. End the file with:

if __name__ == "__main__":
    mcp.run()

For this walkthrough, the example server was a simple in-memory "LeaveManager" with three tools (get_leave_balance, apply_leave, get_leave_history) and one resource (greeting://{name}).

stdout is reserved for the JSON-RPC protocol — any stray print() corrupts the stream and causes cryptic JSON parse errors downstream. Use logging configured to stderr if you need debug output.

3. Test with MCP Inspector (recommended before touching Claude Desktop)

MCP Inspector is a browser-based tool for calling your tools directly — no AI, no Claude Desktop needed. Great for confirming your server actually works before wiring it into anything else.

uv run mcp dev main.py

This opens a local page (usually http://localhost:6274). Click Connect, then go to the Tools tab → List Tools → pick a tool → fill params → run it and check the output.

If Connect spams SyntaxError: Unexpected token ... is not valid JSON in the History/Notifications panel, it usually means the underlying command errored out in plain text (e.g. the same "typer is required" issue above) instead of returning JSON. Read the actual error text hiding in the syntax error message — it tells you what broke.

4. Connecting to Claude Desktop

4a. If Claude Desktop isn't installed yet

Download from https://claude.ai/download, install, and launch it at least once (finish sign-in) before doing anything else.

4b. Finding the right config file

This is the step that varies the most and caused the most confusion:

Standard installs usually use: %APPDATA%\Claude\claude_desktop_config.json (i.e. C:\Users\<you>\AppData\Roaming\Claude\claude_desktop_config.json)
Packaged/Store (MSIX) installs — recognizable by a path containing AppData\Local\Packages\Claude_<random-id>\... — use a virtualized config location instead, e.g.: ...\Local\Packages\Claude_<id>\LocalCache\Roaming\Claude\claude_desktop_config.json Windows silently redirects the app's "AppData\Roaming\Claude" reads/writes to this Packages folder, so editing the plain %APPDATA%\Claude copy does nothing for this install type.
Easiest way to find the right one: open Claude Desktop → Settings → Developer (under "Desktop app" section) → Local MCP servers → click Edit Config. This always opens the file the app actually reads, regardless of install type.

Dead end to avoid: Settings → Connectors → Add custom connector looks like the obvious place to add a server, but it's only for remote MCP servers (ones reachable by a URL, e.g. a hosted server on the internet). It has no field for a local command like uv run main.py, so don't waste time there for a local stdio server — go to Developer → Local MCP servers instead.

4c. The config format

The file may already contain other keys (preferences, Cowork settings, etc. on newer builds). Just add mcpServers as a new top-level key — don't delete anything else:

{
  "mcpServers": {
    "leave-manager": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\Users\\<you>\\Desktop\\MCP\\my-mcp-server",
        "run",
        "main.py"
      ]
    }
  }
}

If "command": "uv" isn't found (Claude Desktop doesn't always inherit your terminal's PATH), use the full path instead, e.g.: C:\\Users\\<you>\\AppData\\Local\\Programs\\Python\\Python314\\Scripts\\uv.exe

4d. Restart and verify

Save the config file.
Fully quit Claude Desktop — right-click its icon in the system tray (bottom-right, near the clock) → Quit/Exit. Closing the window alone is not enough.
Reopen Claude Desktop.
Go to Settings → Developer → Local MCP servers — your server should show up with a green "running" badge.
Start a new chat and ask a natural question, e.g.: "How many leave days does E001 have left?" Claude should say "Loaded tools, used <your-server-name> integration" and answer using your tool's actual return value.

5. Quick troubleshooting checklist

Symptom	Likely cause	Fix
`Error: typer is required...`	`mcp[cli]` installed globally, not in project venv	`uv add "mcp[cli]"` inside the project folder
`Claude app not found` from `mcp install`	Claude Desktop not installed, or `mcp install`'s auto-detect is unreliable	Install the app, or skip `mcp install` and edit the config file directly
Inspector shows repeated JSON parse errors	Server process is printing plain text instead of JSON (crash message, or a stray `print()`)	Check the error text embedded in the parse error; fix the underlying issue
Settings → Developer → "No servers added" after editing config	Edited the wrong config file, or `mcpServers` key missing/malformed	Use Settings → Developer → Edit Config to find the actual file in use; verify JSON is valid
Server shows up but Claude never calls it	Ambiguous tool descriptions, or server crashed silently	Check "View Logs" next to the server entry in Settings → Developer

6. Useful commands reference

uv init .                      # create a new uv project
uv add "mcp[cli]"              # add MCP with CLI/dev tools as a dependency
uv run mcp dev main.py          # launch MCP Inspector against your server
uv run mcp install main.py      # (optional) attempt auto-install into Claude Desktop
uv run main.py                  # run the server standalone (useful for checking for crashes)

Available Tools

3 tools

apply_leaveB

Apply leave for specific dates (e.g., ["2025-04-17", "2025-05-01"])

ParametersJSON Schema

Name	Required	Description	Default
`employee_id`	Yes
`leave_dates`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.3/5.0

Behavior2/5

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

With no annotations, the description provides no behavioral context beyond the action itself. It does not disclose side effects, whether approval is required, how conflicts are handled, or permissions needed. The only extra is the date array example.

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 sentence with a concrete example, front-loaded with the verb, and contains no redundant information.

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?

For a two-required-parameter mutation tool, the description omits the employee_id parameter entirely and gives no information about constraints or process. Although an output schema exists, the description does not fully compensate for the 0% schema description coverage.

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

Parameters2/5

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

Schema description coverage is 0%. The description adds meaning only to leave_dates via an example, but leaves employee_id entirely unexplained beyond its property name. No additional semantics for employee_id are provided.

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

Purpose5/5

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

The description uses a specific verb ('apply') and resource ('leave'), and the example clarifies the expected date array format. It is clearly distinct from the read-only siblings (get_leave_balance, get_leave_history).

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 for requesting time off but does not explicitly state when to use this versus the sibling getter tools, nor any prerequisites or exclusion criteria. The contrast is implicit through the tool name and sibling names.

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

get_leave_balanceC

Check how many leave days are left for the employee

ParametersJSON Schema

Name	Required	Description	Default
`employee_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does mention the action is to 'Check', implying a read-only operation, but it does not explicitly state whether authentication is required, what happens if the employee_id is invalid, or the format of the returned data. It also does not confirm there are no side effects, which is critical without annotations.

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, concise sentence with no redundant words. It is front-loaded with the action and resource, making it easy to parse. This is appropriately sized for the tool's simplicity.

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

Completeness3/5

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

The tool is simple with only one parameter and an output schema, so the description covers the core function. However, it misses usage context and does not explicitly frame it as a read-only operation. The absence of annotations and lack of comparison to siblings leaves gaps, but given the tool's simplicity, it is minimally viable.

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

Parameters2/5

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

Schema description coverage is 0% and the description does not mention the employee_id parameter at all. The parameter name and type are self-explanatory, but the description adds no meaning about the expected format, whether it is an internal identifier, or any constraints. Given the low coverage, the description should compensate but fails to do so.

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 function: checking remaining leave days for an employee. It uses a specific verb ('Check') and resource ('leave days'), which distinguishes it from generic operations. However, it does not explicitly compare against sibling tools like get_leave_history or apply_leave, so the differentiation is implied rather than stated.

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?

There is no guidance on when to use this tool versus alternatives. The description simply states what it does, but does not mention that it should be used for current balance checks, nor provide exclusions (e.g., for historical data use get_leave_history). This leaves the agent without clear decision-making context.

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

get_leave_historyC

Get leave history for the employee

ParametersJSON Schema

Name	Required	Description	Default
`employee_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.6/5.0

Behavior2/5

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

No annotations are provided, so the description must carry the burden. It only states the purpose without disclosing behavioral traits such as read-only nature, response format, filtering, or pagination. Minimal disclosure of the operation.

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 a single sentence with no redundant words, making it concise and front-loaded. However, it is somewhat under-specified, but for conciseness it earns high marks.

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 existence of an output schema and one required parameter, the description is very incomplete. It does not explain expected return values, usage context, or any limitations. For a tool with no annotations, this is a significant gap.

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

Parameters1/5

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

Schema description coverage is 0%. The description adds no information about the employee_id parameter beyond what the schema shows. It would need to explain how to specify the employee, but it does not.

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 uses a specific verb 'Get' and resource 'leave history', clearly indicating the tool's function. It distinguishes from siblings like get_leave_balance (balance vs history), though it lacks detail on scope.

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 on when to use this tool versus alternatives. Does not mention conditions, prerequisites, or exclusion criteria.

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.

3 tool updatesv0.1.0Jul 28, 2026
- First observedapply_leave
- First observedget_leave_balance
- First observedget_leave_history

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

B3.2/5.0

Scored 2026-07-28 07:55 across 3 tools

Disambiguation5/5

Each tool clearly targets a distinct function: checking balance, applying for leave, and viewing history. No overlap or ambiguity.

Naming Consistency5/5

All tools follow a consistent 'verb_leave_noun' pattern (get_leave_balance, apply_leave, get_leave_history), making the set predictable.

Tool Count4/5

Three tools is minimal but reasonable for a basic leave manager. A few more (e.g., cancel or update leave) could be helpful, but the count is not inappropriate.

Completeness2/5

The set covers basic read and create operations but lacks essential operations like cancel, update, or approve leave, leaving significant gaps for a full leave management workflow.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

leave A
io.github.theluckystrike
Employee leave and PTO requests: balances, approvals, calendars, and who-is-out summaries.
Workplace & Productivity Calendar Management
121
akilat-spec-leave-manager-mcpOAuth
ai.smithery
Track and manage employee time off with quick balance lookups and streamlined applications. Find t…
ERP Systems Project Management Workplace & Productivity
2
HollyHROAuth
io.github.hollyhr
Governed HR records and confirmed time-off actions for UK SMEs.
ERP Systems
1
Senzii Scheduling
com.senzii
Staff scheduling — manage staff, shifts, assignments, certifications, and requests via AI.
ERP Systems Workplace & Productivity
1

Related MCP Servers

Leave Manager MCP Tool Server
Workplace & Productivity App Automation
ahmad-act
F
license
Not graded
quality
D
maintenance
A centralized employee leave management system that allows users to check leave balances, apply for leave, and view leave history through an OpenAPI interface.
Updated a year ago (2025-06-04 12:07 UTC)
9
-
leave_manager
ERP Systems Workplace & Productivity
RamehNagella
F
license
Not graded
quality
D
maintenance
Enables natural-language-based employee leave management including leave balance checks, leave applications, approvals, and history retrieval through an MCP-compatible client.
Updated 3 months ago (2026-07-01 12:21 UTC)
-
leave-manager-mcp-server
App Automation
RohitKumarPattanayak
F
license
B
quality
C
maintenance
Enables LLMs to manage employee leave by checking balances, applying for leave, and viewing history.
Updated 3 months ago (2026-07-06 07:12 UTC)
3
-
Leave Management MCP Server
ERP Systems Workplace & Productivity
ratankumarthakur
F
license
C
quality
C
maintenance
Enables natural language leave management, allowing users to check leave balances, apply for leave, and retrieve leave history via MCP tools.
Updated 2 months ago (2026-08-04 17:38 UTC)
3
-

MCP Server Setup Guide (Windows) — Leave Management Example

1. Project Setup

2. Example main.py

3. Test with MCP Inspector (recommended before touching Claude Desktop)

4. Connecting to Claude Desktop

4a. If Claude Desktop isn't installed yet

4b. Finding the right config file

4c. The config format

4d. Restart and verify

5. Quick troubleshooting checklist

6. Useful commands reference

Available Tools

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

2. Example `main.py`