Skip to main content
Glama
ksengineerspc

Proplist MCP Hello World

by ksengineerspc
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Proplist MCP Hello World

Minimal FastMCP server that proves this integration path:

MCP Client -> FastMCP Server -> Microsoft Graph -> SharePoint Excel Workbook

The server exposes one MCP tool, list_worksheets, which returns worksheet names, worksheet IDs, and visibility states from an existing Excel workbook stored in SharePoint.

This milestone intentionally does not create workbook sessions, read cell ranges, parse natural language, or interpret proposal data.

Project Tree

proplist-mcp-helloworld/
├── server.py
├── pyproject.toml
├── .env.example
├── .gitignore
└── README.md

Related MCP server: MCP for Microsoft To Do

Configuration

Create a local .env file from .env.example:

cp .env.example .env

Set every value:

TENANT_ID=...
CLIENT_ID=...
CLIENT_SECRET=...
DRIVE_ID=...
ITEM_ID=...

  • TENANT_ID: Microsoft Entra tenant identifier.

  • CLIENT_ID: application registration client identifier.

  • CLIENT_SECRET: application registration client secret.

  • DRIVE_ID: Microsoft Graph drive identifier containing the workbook.

  • ITEM_ID: Microsoft Graph item identifier for the workbook.

Do not commit .env. It is excluded by .gitignore.

Microsoft Graph Permission

The app registration must have this Microsoft Graph application permission:

Files.Read.All

Tenant admin consent must be granted outside this code. A 403 Forbidden response usually means the app can authenticate but does not have the required application permission or admin consent.

Install And Validate

uv sync
uv run python -m py_compile server.py

You can start the stdio server with either command:

uv run server.py
uv run proplist-mcp

To inspect the MCP server:

npx @modelcontextprotocol/inspector uv run server.py

Then call the list_worksheets tool in the Inspector.

Expected Tool Output

When the credentials and workbook identifiers are valid, the tool returns Markdown:

## Worksheets

| Name | Worksheet ID | Visibility |
|---|---|---|
| Proposals | {...} | Visible |
| Lookup | {...} | Hidden |

Do not treat this sample as proof that your workbook is reachable. The integration is live only when the tool returns real worksheet metadata from your configured workbook.

Risks And Troubleshooting

Risk

Treatment

Missing Graph permission

Add Microsoft Graph Files.Read.All as an application permission and grant tenant admin consent.

Incorrect DRIVE_ID or ITEM_ID

The tool returns a 404 Not Found explanation. Verify the drive and item identifiers in Microsoft Graph.

Expired client secret

Replace CLIENT_SECRET in Microsoft Entra ID and update the local .env file.

Secret leakage

Keep .env out of Git. This project .gitignore excludes it.

Graph throttling

The tool surfaces 429 Too Many Requests and includes Retry-After when Graph provides it.

Untested credentials

uv sync and py_compile validate code only. Live integration validation requires real credentials and real worksheet metadata.

Known Scope Limits

  • Uses OAuth 2.0 client credentials only.

  • Uses Microsoft Graph app-only access only.

  • Does not use delegated, interactive browser, device-code, or username/password authentication.

  • Does not call workbook/createSession.

  • Does not read workbook ranges or tables.

  • Does not add storage, LLM calls, LangChain, LangGraph, agents, web UI, Docker, CI/CD, Key Vault, or telemetry.

Available Tools

1 tool
list_worksheetsA

List worksheet names, IDs, and visibility states for the configured workbook.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.7/5.0
Behavior2/5

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

The description does not disclose any behavioral traits such as whether the operation is read-only (though implied), whether it might be expensive, or what error conditions (e.g., no workbook configured) may arise. Annotations are absent, so the description bears full responsibility for transparency but fails to provide meaningful detail.

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 of 10 words, with no filler or redundancy. It is front-loaded with the verb and immediately lists the output fields, making it easy to scan.

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?

Given that there are no parameters and an output schema exists (though not shown), the description is minimally adequate. However, it does not explain the preconditions (e.g., the need for a configured workbook) or any potential side effects, leaving the agent without full context for safe usage.

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

Parameters4/5

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

The tool has zero parameters, and the schema description coverage is 100% (trivially). The description adds value by naming the specific fields returned (names, IDs, visibility states), which goes beyond the empty schema. This is helpful context for an agent using the tool.

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 clearly specifies the verb 'List' and the exact resources ('worksheet names, IDs, and visibility states') that the tool retrieves. Although there are no sibling tools to differentiate from, the description is precise and leaves no ambiguity about what the tool does.

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?

No explicit guidance is provided on when to use this tool versus alternatives (none exist), nor are there prerequisites or recommendations about the configured workbook. The description implies a simple read operation but lacks context such as that the workbook must be loaded or configured first.

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. Dates show when Glama detected each change.

  1. 1 tool updatev0.1.0
    • First observedlist_worksheets
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap; its purpose is trivially distinct.

Naming Consistency5/5

The single tool uses a clear and conventional snake_case verb_noun pattern, so consistency is perfect by default.

Tool Count3/5

One tool is borderline thin for most use cases, but for a 'Hello World' demo it may be acceptable; it fits the lower end of the typical 1-2 tool range.

Completeness2/5

The server only provides a list operation for worksheets, missing any create, update, or delete functionality, which represents a significant gap for worksheet management.

Maintenance

ActivitySlowing
ResponsivenessSyncing

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

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/ksengineerspc/kse-proplist-mcp'

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