Skip to main content
Glama
Office MCP Server

Office MCP Server

by hvkshetry

mail

Manage Microsoft 365 email: list, read, search, send, reply, draft, move messages, and organize folders, categories, attachments, and rules.

Instructions

Unified email management. draft_reply_all creates a threaded reply-all draft and never sends it (it takes emailId, body, mailbox, attachments, cc and bcc, ADDS cc/bcc to the reply-all recipients, and refuses any other parameter by name); reply/send/send_draft are transmission operations.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "operation": "<operation>"
    },
    "name": "mail"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoCC recipients
toNoRecipient email addresses (for send/draft/reply)
bccNoBCC recipients
bodyNoEmail body in HTML format (for send/draft/reply/draft_reply_all)
fromNoFilter by sender email (for search)
pathNoLocal file path (for cleanup_attachment)
batchNoUse batch processing (for move)
colorNoCategory color preset0-preset24 (for create_category)
queryNoSearch text or KQL syntax (for search)
isReadNoFilter by read/unread (for search)
draftIdNoDraft ID (for update_draft, send_draft)
emailIdNoEmail ID (for read, get_attachment, reply, draft_reply_all, move, apply_category)
endDateNoEnd date - ISO or relative (for search)
mailboxNoMailbox to access (default: authenticated user). Use for shared mailboxes.
subjectNoEmail subject (for send/draft)
emailIdsNoEmail IDs to move (for move)
enhancedNoEnhanced mode for rules
folderIdNoFolder ID (for list, search)
replyAllNoReply to all recipients (for reply). draft_reply_all is always reply-all and draft-only.
forwardToNoForward-to emails (for create_rule)
operationYesThe operation to perform
startDateNoStart date - ISO or relative 7d/1w/1m/1y (for search)
categoriesNoCategories (for apply/remove)
categoryIdNoCategory ID (for update/delete)
folderNameNoFolder name: inbox/sent/drafts/deleted/junk/archive (for search)
importanceNoFilter by importance
maxResultsNoMaximum number of results
attachmentsNoLocal file paths to attach (for send/reply/draft/update_draft). Files must be < 3 MB each. On update_draft these are added to the existing draft, not replaced.
displayNameNoName (for create_folder, create_rule, create_category)
attachmentIdNoAttachment ID (for get_attachment — get IDs from read)
moveToFolderNoMove-to folder ID (for create_rule)
useRelevanceNoSort by relevance (for search)
fromAddressesNoFrom filter (for create_rule)
hasAttachmentsNoFilter by attachments (for search)
includeDeletedNoInclude deleted items (for search)
parentFolderIdNoParent folder ID (for create_folder)
subjectContainsNoSubject keywords (for create_rule)
destinationFolderIdNoDestination folder ID (for move)

Output Schema

NameRequiredDescriptionDefault
noteNo
textYesComplete readable result, including IDs and coverage notes
emailsNo
methodNo
hasMoreNo
limitedNo
returnedNo
pageLimitNo
serviceLimitNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3/5.0
Behavior2/5

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

No annotations exist, so the description carries the full behavioral burden. It discloses that draft_reply_all is draft-only and refuses other parameters, and flags three transmission operations, but says nothing about side effects, reversibility, permissions, or risks for the other mutation operations such as move, create_folder, create_rule, apply_category, remove_category.

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?

Two sentences, front-loading the key operation and using a parenthetical for parameters; however, the first sentence is a generic category label and the second is a dense run-on that could be structured more clearly. It avoids waste but could be tighter.

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 22-operation, 38-parameter tool with no annotations, the description is far too thin: it omits any behavioral context for 18 operations, including destructive/mutating ones. The output schema relieves pressure on return values, but the description does not cover enough of the operation surface to be complete.

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?

Schema description coverage is 100%, so the baseline is 3; the description adds genuine meaning for draft_reply_all by naming accepted parameters and explaining that cc/bcc are added to existing reply-all recipients and other parameters are refused. This is useful beyond the schema, though it covers only one operation's parameter set.

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

Purpose3/5

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

States the domain 'email management' but not a specific verb or scope; the description details only draft_reply_all and groups reply/send/send_draft as transmission operations, leaving the other 19 operations unnamed. An agent can identify it as the mail tool but must read the schema to learn most capabilities.

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?

Provides explicit when-to-use for draft_reply_all versus transmission operations ('never sends it' vs 'reply/send/send_draft are transmission operations'), but gives no guidance for the remaining operations (list, search, move, rules, categories). The when-not guidance is limited to one operation.

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