Skip to main content
Glama
desek

outlook-local-mcp

mail

Read-onlyIdempotent

Retrieve and manage Outlook email messages and folders. Search, filter, and read message details using Microsoft Graph.

Instructions

Mail operations for Microsoft Outlook via Microsoft Graph. By default only read verbs are registered. Additional read verbs (get_conversation, list_attachments, get_attachment) are registered when MailEnabled is configured, and write verbs (create_draft, create_reply_draft, create_forward_draft, update_draft, delete_draft) are registered when MailManageEnabled is configured. The verbs listed below are those active in the current configuration.

Set the required operation parameter to one of the verbs below. Each line names the verb, what it does, and the parameters that verb requires. Optional parameters are omitted here; call operation="help" for the full parameter reference.

  • help: show detailed documentation for all verbs or a single named verb. No required parameters.

  • list_folders: list mail folders (Inbox, Sent, Drafts, etc.) with unread and total counts. No required parameters.

  • list_messages: list messages in a folder or across all folders; filter by date, sender, thread. No required parameters.

  • get_message: get full message details by ID; bodyPreview by default, full body via output=raw. Requires: message_id.

  • search_messages: full-text KQL search across messages; ranked by relevance, not chronologically. Requires: query.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fromNoSender email address to filter by (e.g. alice@contoso.com).
queryNoKQL search string (e.g. subject:"Design Review" from:alice@contoso.com).
outputNoOutput mode: 'text' (default), 'summary', or 'raw'.
accountNoAccount label or UPN to use. Omit to auto-select the default account.
is_readNoFilter by read/unread state. Omit to include both.
is_draftNoFilter by draft state. Omit to include both.
timezoneNoIANA timezone name for the Prefer: outlook.timezone header.
folder_idNoMail folder ID to list messages from. Omit to list from all folders.
operationYesThe operation to perform. Call with operation="help" for full documentation.
importanceNoFilter by message importance.
message_idNoThe unique identifier of the message to retrieve.
provenanceNoFilter to messages created by this MCP server (requires provenance tagging).
flag_statusNoFilter by follow-up flag status.
max_resultsNoMaximum number of folders to return (default 25).
end_datetimeNoEnd of date range (ISO 8601). Filters by receivedDateTime <=.
start_datetimeNoStart of date range (ISO 8601, e.g. 2026-03-12T00:00:00Z). Filters by receivedDateTime >=.
conversation_idNoConversation ID to retrieve all messages in a thread.
has_attachmentsNoFilter by attachment presence. Omit to include both.
Behavior5/5

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

The description discloses that search_messages uses KQL and is ranked by relevance, get_message returns bodyPreview by default, and write verbs are conditionally registered. This adds significant detail beyond the annotations (readOnlyHint, openWorldHint, etc.)

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 well-structured with a general intro, configuration notes, and a clear verb list. However, it is somewhat lengthy and could be tightened, especially the initial paragraphs.

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 tool with 18 parameters, 5 operations, and no output schema, the description provides adequate operation-level detail and links to parameters, though it omits output format specifics (acceptable given no output schema).

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?

With 100% schema coverage, baseline is 3. The description adds value by mapping each verb to its required parameters and noting optional ones omitted, providing operational 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 explicitly states 'Mail operations for Microsoft Outlook via Microsoft Graph' and lists each operation with its specific function, making it clear what the tool does and distinguishing between verbs.

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?

The description explains when read vs write verbs are available based on configuration and advises calling operation='help' for full docs. It does not explicitly state when not to use this tool but provides clear context for its use among siblings.

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

Install Server

Other Tools

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/desek/outlook-local-mcp'

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