Skip to main content
Glama
mdev26

SharePoint MCP Server

by mdev26
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

SharePoint MCP Server

License: MIT

MCP Server for Microsoft SharePoint using modern Azure AD (MSAL) authentication.

Prerequisites

Azure AD App Registration

  1. Go to Azure Portal → Azure Active Directory → App registrations → New registration

    • Name: anything you like

    • Supported account types: "Accounts in this organizational directory only"

    • Redirect URI: leave empty

  2. From the Overview page, note:

    • Application (client) ID → SHP_ID_APP

    • Directory (tenant) ID → SHP_TENANT_ID

  3. Certificates & secrets → New client secret

    • Save the Value immediately (you won't see it again) → SHP_ID_APP_SECRET

  4. API permissions → Add a permission → SharePoint → Application permissions

    • Add Sites.ReadWrite.All (or Sites.Read.All for read-only)

    • Click Grant admin consent — the status must show a green checkmark

  5. Get your SharePoint site URL (e.g. https://contoso.sharepoint.com/sites/yoursite) → SHP_SITE_URL

    • Do NOT include a trailing slash

Security Best Practices

  • Use Sites.Read.All if you only need read access (principle of least privilege)

  • Set a calendar reminder to rotate client secrets before expiry

  • Never commit .env files to Git — use environment variables or a secrets manager

Related MCP server: SharePoint MCP Server

Installation

pip install mcp-sharepoint-us

Or from source:

git clone https://github.com/mdev26/mcp-sharepoint-us.git
cd mcp-sharepoint-us
pip install -e .

Configuration

# Required
SHP_TENANT_ID=your-tenant-id-guid
SHP_ID_APP=your-client-id-guid
SHP_ID_APP_SECRET=your-client-secret
SHP_SITE_URL=https://your-tenant.sharepoint.com/sites/your-site

# Optional
SHP_DOC_LIBRARY=Shared Documents   # default
SHP_AUTH_METHOD=msal               # options: msal (default), certificate, legacy

Certificate-based authentication (optional)

SHP_AUTH_METHOD=certificate
SHP_CERT_PATH=/path/to/certificate.pem
SHP_CERT_THUMBPRINT=your-cert-thumbprint

Claude Desktop Integration

Windows: %APPDATA%\Claude\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "sharepoint": {
      "command": "python",
      "args": ["-m", "mcp_sharepoint"],
      "env": {
        "SHP_TENANT_ID": "your-tenant-id",
        "SHP_ID_APP": "your-client-id",
        "SHP_ID_APP_SECRET": "your-client-secret",
        "SHP_SITE_URL": "https://your-tenant.sharepoint.com/sites/your-site",
        "SHP_AUTH_METHOD": "msal"
      }
    }
  }
}

Using uvx

{
  "mcpServers": {
    "sharepoint": {
      "command": "uvx",
      "args": ["mcp-sharepoint-us"],
      "env": {
        "SHP_TENANT_ID": "your-tenant-id",
        "SHP_ID_APP": "your-client-id",
        "SHP_ID_APP_SECRET": "your-client-secret",
        "SHP_SITE_URL": "https://your-tenant.sharepoint.com/sites/your-site"
      }
    }
  }
}

Available Tools

Tool

Description

Test_Connection

Verify authentication and connection

List_SharePoint_Documents

List documents in a folder

Get_Document_Content

Read document content (supports .docx, .pptx, .xlsx, .pdf)

Upload_Document

Upload a new document

Update_Document

Update an existing document

Delete_Document

Delete a document

List_SharePoint_Folders

List folders

Create_Folder

Create a new folder

Delete_Folder

Delete an empty folder

Get_SharePoint_Tree

Get recursive folder structure

Create_Word_Document

Create a formatted .docx and upload to SharePoint

Edit_Word_Document

Find/replace or section-replace content in a .docx

Create_PowerPoint

Create a .pptx and upload to SharePoint

Troubleshooting

Enable debug logging

LOGLEVEL=DEBUG python -m mcp_sharepoint

"Acquire app-only access token failed"

  • Ensure SHP_TENANT_ID is set and correct (Azure Portal → Azure AD → Overview → Tenant ID)

  • Ensure SHP_AUTH_METHOD=msal (or leave unset — msal is the default)

  • Verify admin consent is granted in Azure Portal (green checkmarks on API permissions)

  • After granting permissions, wait 5–10 minutes for propagation

"403 Forbidden" / "Access denied"

  • Permissions must be Application permissions, not Delegated

  • Admin consent must be granted

  • The site URL must exactly match the SharePoint site (no trailing slash)

"Invalid client secret"

  • Copy the secret Value, not the secret ID

  • Check for extra spaces in your .env file

  • The secret may have expired — create a new one

Connection reset / firewall issues

If authentication succeeds but Graph API calls fail (connection reset during TLS), the endpoint graph.microsoft.us (US Government) or graph.microsoft.com (commercial) may be blocked by a firewall using deep packet inspection. Ask your network team to whitelist the endpoint on port 443. For proxy environments:

export HTTPS_PROXY=http://proxy.company.com:8080

License

MIT License

Available Tools

13 tools
Create_FolderC

Create a new folder in SharePoint

ParametersJSON Schema
NameRequiredDescriptionDefault
folder_pathYesPath where to create the folder
folder_nameYesName of the new folder

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are present, and the description lacks behavioral details such as whether the tool overwrites existing folders, requires specific permissions, or has any side effects. The description does not disclose what happens if the folder already exists.

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 concise sentence with no wasted words. It is front-loaded with the verb and object. However, it could benefit from additional context without losing conciseness.

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 simplicity of the tool (2 parameters, no output schema), the description is under-specified. It does not explain return values, error conditions, or success indicators, leaving the agent without enough context for robust invocation.

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 baseline is 3. The description adds no extra meaning beyond the schema; it only repeats the tool's purpose. The parameter descriptions in the schema are sufficient.

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 creates a new folder in SharePoint. The verb 'Create' and resource 'folder' are specific, and it is easily distinguishable from sibling tools like Delete_Folder or Upload_Document.

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. There is no mention of prerequisites, permissions, or scenarios where another tool might be more appropriate.

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

Create_PowerPointB

Create a formatted PowerPoint presentation (.pptx) with multiple slide layouts, text boxes, bullet points, images, tables, shapes, and rich formatting. Upload directly to SharePoint.

ParametersJSON Schema
NameRequiredDescriptionDefault
folder_pathNoDestination folder path in SharePoint
file_nameYesName of the PowerPoint file (should end with .pptx)
contentYesArray of slide objects with layouts and content

TDQS

B3.2/5.0
Behavior2/5

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

No annotations exist, so description carries full burden. It does not disclose behavioral traits such as whether it overwrites existing files, required permissions, or error handling. Agent lacks critical info.

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?

Single sentence is concise but front-loaded with key info. Could be better structured with bullet points, but no waste.

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?

Complex tool with nested content array, but description is brief. No output schema, so return value is unexplained. Schema covers param details, but description lacks usage examples or error handling context.

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 baseline is 3. Description adds no additional meaning beyond schema for parameters; it lists capabilities but doesn't elaborate on parameter usage.

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 states the tool creates a formatted PowerPoint presentation and uploads to SharePoint, with a specific verb and resource. It distinguishes from sibling tools like Create_Word_Document.

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 vs alternatives, no prerequisites or context provided. The description mentions upload to SharePoint but doesn't specify when this is appropriate.

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

Create_Word_DocumentA

Create a formatted Word document (.docx) with headings, paragraphs, tables, lists, images, hyperlinks, horizontal rules, and page breaks. Supports rich formatting including colors, highlighting, and spacing. Upload directly to SharePoint.

ParametersJSON Schema
NameRequiredDescriptionDefault
folder_pathNoDestination folder path in SharePoint
file_nameYesName of the Word document (should end with .docx)
contentYesArray of content items (headings, paragraphs, tables, lists, images, hyperlinks, horizontal rules, page breaks)

TDQS

A3.8/5.0
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 discloses that the tool creates and uploads to SharePoint and supports rich formatting, but it lacks details on overwrite behavior, required permissions, error handling, or whether it's synchronous.

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 concise with two sentences, front-loading the primary action and key features. Every sentence adds value without unnecessary detail.

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

Completeness4/5

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

Given the rich schema (100% coverage) and no output schema or annotations, the description covers the main functionality well. It could mention that it only creates new documents on SharePoint and perhaps note size limits, but it is sufficiently complete for a typical use case.

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 input schema already has 100% coverage with descriptions. The description adds value by summarizing capabilities (e.g., 'rich formatting including colors, highlighting, and spacing') and linking the folder_path parameter to SharePoint upload, providing context beyond the schema.

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 states the verb 'Create', the resource 'formatted Word document (.docx)', and lists supported elements like headings, paragraphs, tables, etc. It distinguishes from siblings like Create_PowerPoint and Edit_Word_Document.

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 mentions 'Upload directly to SharePoint' which implies usage context, but it does not explicitly state when to use this tool versus alternatives like Upload_Document or Edit_Word_Document. No exclusions or when-not instructions are provided.

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

Delete_DocumentB

Delete a document from SharePoint

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesPath to the file to delete

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are present, so the description carries the full burden. It only states 'Delete' without disclosing whether deletion is permanent, if a recycle bin is used, or if specific permissions are required. Safety implications are entirely unspecified.

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 unnecessary words. However, it could be restructured to front-load critical behavioral details while remaining concise.

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?

For a simple delete tool with one parameter, the purpose is adequately conveyed, but the lack of behavioral disclosure and guidance makes it incomplete. The missing output schema is acceptable for a delete operation.

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?

The input schema already describes the file_path parameter with 100% coverage. The description adds no additional meaning beyond what the schema provides, meeting the baseline for complete schema coverage.

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 states the verb 'Delete' and the resource 'document from SharePoint'. It distinguishes from sibling tools like Delete_Folder, which deletes a folder instead.

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 such as Delete_Folder or when deletion should be avoided. The description does not mention prerequisites, permissions, or conditions for safe use.

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

Delete_FolderB

Delete an empty folder from SharePoint

ParametersJSON Schema
NameRequiredDescriptionDefault
folder_pathYesPath to the folder to delete

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of disclosure. It states the folder must be empty but does not describe what happens if it is not (e.g., error behavior), permission requirements, or whether the operation is reversible. This is minimal disclosure for a destructive action.

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 six words, with no unnecessary information. It efficiently conveys the core functionality.

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 destructive operation with no output schema or annotations, the description should include behavioral details, error conditions, and post-conditions. It only states the requirement for an empty folder, leaving significant gaps for effective 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 coverage is 100% as folder_path is described in the schema. The description adds no additional context about the parameter format, examples, or path conventions, so it meets the baseline without adding value.

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 states the action (Delete), resource (empty folder), and platform (SharePoint). It effectively distinguishes from sibling tools like Create_Folder and Delete_Document by specifying 'empty folder' and 'from SharePoint'.

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 (e.g., Delete_Document) or on prerequisites such as ensuring the folder is empty before deletion. The description lacks situational context.

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

Edit_Word_DocumentA

Edit an existing Word document (.docx) with find/replace operations and SECTION REPLACEMENT for monthly status reports. Preserves all formatting.

SIMPLE REPLACEMENT: Replace individual placeholders ({{company_name}} -> 'Acme Corp')

SECTION REPLACEMENT FOR MONTHLY REPORTS: Replace entire sections (8 bullets, tables) in one operation.

  • Perfect for monthly status reports where sections need to be updated each month

  • Use section markers: {{section:name}} ... {{/section:name}}

  • Replace all content between markers with fresh bullet points or table rows

  • Preserves formatting and list styles

USE CASES:

  • Monthly status reports: Replace {{section:status_bullets}} with 8 new status items

  • Metrics tables: Replace {{section:metrics}} with updated monthly data

  • Template filling: Replace {{company_name}} and other placeholders with actual values

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesPath to the existing Word document in SharePoint
replacementsYesArray of replacement operations. Supports TWO FORMATS: 1. SIMPLE REPLACEMENT (single placeholder): {"find": "{{company_name}}", "replace": "Acme Corp"} 2. SECTION REPLACEMENT (for monthly reports - replaces entire sections like 8 bullets): { "find": "{{section:status_bullets}}", "replace_section": ["Item 1", "Item 2", "Item 3", ...], "section_type": "bullets" } Template must have section markers: {{section:status_bullets}} * Old bullet 1 * Old bullet 2 {{/section:status_bullets}} Section types: "bullets" (for bullet lists) or "table" (for tables)
output_file_pathNoOptional: Path for the modified document. If not provided, overwrites the original file.

TDQS

A4.5/5.0
Behavior5/5

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

Despite no annotations, the description fully discloses behavioral traits: preserves formatting, supports two replacement modes, overwrites original by default unless output_file_path is provided, and explains section markers. 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.

Conciseness5/5

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

Well-structured with clear sections for simple and section replacement, use cases, and formatting notes. Every sentence adds value; no superfluous content. Concise yet comprehensive.

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

Completeness5/5

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

For a tool with 3 parameters, a standard schema, and no output schema, the description covers all necessary behavioral and usage aspects. It explains both replacement modes, markers, and output behavior completely.

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 detailed parameter descriptions. The description adds context and use-case examples but does not introduce new semantic meaning beyond the schema, meeting the baseline expectation.

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?

Clearly states the tool edits existing Word documents with find/replace and section replacement for monthly status reports. Distinguishes from siblings like Create_Word_Document, Delete_Document, etc., by focusing on editing existing .docx files with specific replacement operations.

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

Usage Guidelines4/5

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

Provides explicit use cases (monthly status reports, metrics tables, template filling) and explains when to use simple vs. section replacement. Does not explicitly contrast with similar tools like Update_Document, but the context is clear enough for an AI agent to select appropriately.

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

Get_Document_ContentC

Get the content of a document (supports text extraction from PDF, Word, Excel, and text files)

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesPath to the file (relative to document library root)

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 must fully disclose behavioral traits. It mentions text extraction from specific formats but omits important details such as what happens with unsupported formats, rate limits, file size constraints, or whether it returns plain text or binary data. This lack of detail limits transparency.

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 that directly states the tool's purpose and supported formats. It is front-loaded with verb and resource, and contains no filler. Minor deduction for missing a second sentence about output, but overall very concise.

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 the tool's simplicity (one parameter, no output schema), the description is mostly adequate. However, it fails to clarify the return type (e.g., plain text, extracted content) or error handling for unsupported formats. The absence of an output schema increases the burden on the description, which is not fully met.

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?

With 100% schema description coverage, the schema already documents the sole parameter 'file_path' and its meaning. The description adds no new information beyond the schema, so it meets baseline expectations but does not enhance understanding.

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 the content' and the resource 'document', and lists supported formats (PDF, Word, Excel, text files). This distinguishes it from sibling tools focused on creation, deletion, or listing. However, it does not specify what form the content takes (e.g., raw text vs. extracted text) or the output format, preventing a top score.

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 explicit guidance on when to use this tool versus alternatives like Get_SharePoint_Tree or List_SharePoint_Documents. The description implies it is for reading document content, but does not include exclusions, prerequisites, or context on when it is appropriate.

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

Get_SharePoint_TreeB

Get a recursive tree view of SharePoint folder structure

ParametersJSON Schema
NameRequiredDescriptionDefault
folder_pathNoStarting folder path (leave empty for root)
max_depthNoMaximum depth to traverse

TDQS

B3.1/5.0
Behavior2/5

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

No annotations provided; description doesn't disclose performance implications, recursion limits, or behavior beyond the basic purpose.

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?

Single concise sentence with key qualifier 'recursive tree view', but lacks some context that could improve usefulness.

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?

No output schema, and description doesn't explain return format or tree structure details; incomplete for a tree-view tool.

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 covers both parameters with descriptions; description adds no additional meaning, achieving baseline for high schema coverage.

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 states the tool gets a recursive tree view of SharePoint folder structure, which is specific and distinguishes from sibling tools like List_SharePoint_Folders.

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 (e.g., List_SharePoint_Folders for flat lists), no prerequisites or exclusions.

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

List_SharePoint_DocumentsC

List all documents in a specified folder with metadata

ParametersJSON Schema
NameRequiredDescriptionDefault
folder_pathNoPath to the folder containing documents

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, and the description fails to disclose behavioral traits such as whether the listing is recursive, pagination, or authentication requirements. This is inadequate for a tool with no structured 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?

A single sentence that is concise and front-loaded with the core action. No wasted words.

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 complexity of listing documents (e.g., pagination, recursion), the description is too brief. It omits return format and behavioral details, making it incomplete for an agent to fully understand the tool's capabilities.

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?

The single parameter 'folder_path' is described in the schema with sufficient clarity. The description adds no additional meaning, but schema coverage is 100%, so baseline 3 is appropriate.

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 lists documents with metadata in a specified folder, distinguishing it from siblings like List_SharePoint_Folders. However, 'with metadata' is vague and could be more specific.

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 like Get_SharePoint_Tree or when not to use it. Missing context about applicable scenarios.

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

List_SharePoint_FoldersB

List all folders in a specified directory or root of the document library

ParametersJSON Schema
NameRequiredDescriptionDefault
folder_pathNoPath to the folder (relative to document library root). Leave empty for root.

TDQS

B3.4/5.0
Behavior2/5

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

No annotations are provided, so the description must disclose behaviors. It states 'list all folders' but does not clarify if the listing is recursive, whether hidden folders are included, or any permissions needed. This is insufficient for a read operation with no 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 sentence of 14 words, front-loaded with the action, and contains no superfluous 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?

Given no output schema and no annotations, the description should provide more detail about the output format (e.g., list of folder names or paths) and whether the listing is recursive. Currently it is incomplete for an agent to fully understand the tool's behavior.

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% for the single parameter, and the description does not add any new meaning beyond what the schema already provides. Baseline score of 3 is appropriate.

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 states the verb 'List' and the resource 'folders in a specified directory or root of the document library', distinguishing it from sibling tools like List_SharePoint_Documents which list files.

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 use when listing folders in a SharePoint library but does not provide explicit guidance on when to use this tool versus alternatives like Get_SharePoint_Tree or List_SharePoint_Documents, nor does it mention when not to use.

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

Test_ConnectionA

Test the SharePoint connection and authentication

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.8/5.0
Behavior2/5

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

With no annotations, the description carries full burden but only states the action without disclosing details like whether it's read-only, what it returns, or authentication specifics.

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?

Single, brief sentence that immediately conveys the tool's purpose with no unnecessary words.

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

Completeness4/5

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

For a simple diagnostic tool with no parameters or output schema, the description is sufficient, though it could mention expected results.

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?

No parameters exist, so baseline 4 applies. The description adds meaning beyond the empty schema by clarifying the tool's purpose.

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 states the tool's action ('Test') and resource ('SharePoint connection and authentication'), distinguishing it from sibling tools that perform CRUD operations.

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 on when to use this tool versus alternatives, but the purpose implicitly suggests using it before other SharePoint operations to verify connectivity.

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

Update_DocumentB

Update the content of an existing document

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesPath to the file to update
contentYesNew file content
is_binaryNoWhether the content is base64 encoded binary

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations, the description carries full burden but only says 'Update', implying replacement without specifying whether it overwrites, appends, or requires existing file. No mention of permissions or binary handling beyond schema.

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?

Single sentence, no fluff. Could be slightly more detailed without harming conciseness.

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?

No output schema and no annotations. For a mutation tool with 3 params, description lacks important behavioral details like overwriting behavior and file existence requirements.

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 coverage is 100%, but description adds no extra meaning beyond param names and schema descriptions. Baseline score of 3 is appropriate.

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 states the verb 'Update' and the resource 'existing document', distinguishing it from sibling tools like Create_*, Delete_*, or Edit_Word_Document.

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 usage context, when-to-use, or when-not-to-use guidance is provided. No mention of prerequisites or alternatives like Edit_Word_Document for specific formats.

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

Upload_DocumentC

Upload a new document to SharePoint

ParametersJSON Schema
NameRequiredDescriptionDefault
folder_pathYesDestination folder path
file_nameYesName of the file to create
contentYesFile content (text or base64 encoded for binary files)
is_binaryNoWhether the content is base64 encoded binary

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are present, so the description bears the full burden. It does not disclose important behavior: whether existing files are overwritten, what happens on error, or required permissions. The word 'Upload' implies creation, but details are missing.

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?

A single sentence with no wasted words. It is appropriately concise for a tool with high schema coverage.

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 4 parameters and no output schema, the description is too brief. It fails to mention return values, error handling, or behavior on duplicate file names. Compared to sibling tools, it lacks completeness.

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?

The input schema has 100% coverage with descriptions for all parameters. The description adds little beyond what the schema provides. It explains the tool's purpose but not parameter details. Baseline 3 is appropriate.

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 'Upload a new document to SharePoint', which is a specific verb and resource. However, it does not differentiate from sibling tools like Create_Word_Document or Update_Document, which also involve document creation/modification.

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. There is no mention of prerequisites, such as the folder needing to exist, or when to use Create_Folder first. This lack of context makes it hard for an AI to select correctly among siblings.

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. 13 tool updatesv2.5.6
    • First observedCreate_Folder
    • First observedCreate_PowerPoint
    • First observedCreate_Word_Document
    • First observedDelete_Document
    • First observedDelete_Folder
    • First observedEdit_Word_Document
    • First observedGet_Document_Content
    • First observedGet_SharePoint_Tree
    • First observedList_SharePoint_Documents
    • First observedList_SharePoint_Folders
    • First observedTest_Connection
    • First observedUpdate_Document
    • First observedUpload_Document
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation4/5

Most tools have distinctly clear purposes, but 'Edit_Word_Document' and 'Update_Document' could be confused (both modify a document), and 'Upload_Document' overlaps partially with 'Create_Word_Document' and 'Create_PowerPoint'. However, detailed descriptions help differentiate them.

Naming Consistency3/5

Tool names follow a verb_noun pattern, but the nouns vary in specificity (e.g., 'Create_PowerPoint' vs. 'Create_Word_Document', and 'List_SharePoint_Documents' vs. 'Get_Document_Content'). The mix of 'Get_', 'List_', 'Create_', 'Delete_', 'Edit_', 'Update_', 'Upload_', and 'Test_' is acceptable but lacks full consistency.

Tool Count5/5

With 13 tools covering folder and document operations, plus connection testing and tree view, the count is well-scoped for a SharePoint integration. It provides essential functionality without being bloated or too sparse.

Completeness4/5

The tool set covers CRUD for folders and documents, with specialized creation for Word and PowerPoint. Gaps include inability to delete non-empty folders, lack of rename/move operations, and no search or permission management. These are minor but notable.

Maintenance

ActivityInactive
ResponsivenessNo issues

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/mdev26/mcp-sharepoint-us'

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