ews-meeting-mcp

ews-meeting-mcp is a skill for Claude Code, Codex from ap311036/ews-meeting-mcp. It costs 70 tokens per session (3,215 once invoked), scanned A, original, MIT.

A local connection to company Outlook email and Exchange calendars through an EWS Meeting Agent. Exchange is Microsoft's company email and calendar server, and EWS is its access interface.

In plain words
What is it for?
Use it to search and read Outlook messages, find overlapping free meeting times, schedule or update meetings, cancel meetings safely, and send Jira reports to yourself.
Why use it?
It gives a controlled way to search and read work email, report Jira items to yourself, and manage meetings while keeping email actions read-only and checking calendar setup first.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to search and read Outlook messages, find overlapping free meeting times, schedule or update meetings, cancel meetings safely, and send Jira reports to yourself.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ap311036/ews-meeting-mcp/ews-meeting-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ap311036/ews-meeting-mcp --skill ews-meeting-mcp
Clone the repo
git clone --depth 1 https://github.com/ap311036/ews-meeting-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ews-meeting-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/ap311036/ews-meeting-mcp/ews-meeting-mcp/github.svg)](https://agentmods.dev/skills/ap311036/ews-meeting-mcp/ews-meeting-mcp)
Your own site
<a href="https://agentmods.dev/skills/ap311036/ews-meeting-mcp/ews-meeting-mcp"><img src="https://agentmods.dev/badge/skills/ap311036/ews-meeting-mcp/ews-meeting-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ews-meeting-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/ap311036/ews-meeting-mcp/ews-meeting-mcp"><img src="https://agentmods.dev/badge/skills/ap311036/ews-meeting-mcp/ews-meeting-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.03215
Opus 5.5 $0.00028 $0.01286
Sonnet 5.5 $0.00014 $0.00643
Haiku 4.5 $0.00007 $0.00321

Measured 1mo ago against content hash 03e2f9f03efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ews-meeting-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ews-meeting-mcp/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EWS Meeting Agent

Use the ews-meeting-mcp MCP tools to read company Outlook mail, send self-only Jira reports, and schedule meetings through an on-prem Exchange/EWS calendar.

Workflow

  1. For company Outlook mail, call ews_setup_check, then ews_search_emails with the narrowest known filters. Present the returned metadata, use the exact selected id and optional changekey with ews_read_email, and summarize the returned message. These tools are read-only: they do not mark messages as read, move messages, delete messages, or change labels.
  2. At the start of a scheduling session, call ews_setup_check. If it returns ready: false, show its user_message as-is, or show setup_command verbatim in a fenced bash block, and stop. Do not ask the user to paste a password into chat or MCP config; do not ask for attendee emails or continue with EWS tools until the user says they fixed setup. Then call ews_setup_check again before continuing. If the user asks how to set up an Outlook-style meeting signature, call ews_signature_setup_guide and show the returned sample_html, recommended_path, and setup_command; this helper does not require EWS credentials.
  3. For the Thursday Jira weekly-report automation, after it assembles the previous and current report, call ews_send_email_to_self with subject, body, body_format, and a stable, non-secret idempotency_key. It has no recipient, to, cc, or bcc argument; it sends only to the configured EWS_EMAIL through EWS CreateItem followed by SendItem. Never substitute Gmail or to: me. Reuse the same idempotency key for retries; treat duplicate_confirmation, confirmation_in_progress, and unknown delivery as stop conditions until Sent Items and the audit log are inspected.
  4. Parse the user's request into attendees, candidate rooms, date range, duration, subject, body, location, and optional show_as. For a personal appointment with exact times and no invitees/room, use attendees: [] and rooms: [], skip attendee/room discovery and slot selection, and proceed to preview. For Taiwan/local office scheduling, pass datetime arguments with an explicit local offset such as +08:00. Z is accepted by the tool but means UTC, not local time.
  5. If any attendee is not a complete email address, call ews_resolve_attendees first. Do not ask the user to provide full attendee email addresses before trying company directory resolution.
  6. Use exactly resolved emails for scheduling. If a name has zero matches or multiple matches, ask the user to clarify or choose from the returned candidates before continuing. Prefer the host's interactive multiple-choice UI or clickable choice controls when available; otherwise show a short numbered list of candidates. For ambiguous matches, show candidate names and emails as choices; do not ask the user to type the full email manually.
  7. If the user did not mention rooms, call ews_list_rooms with the attendee count if known, then ask whether a meeting room is needed using the returned options. Prefer the host's interactive multiple-choice UI or clickable choice controls when available; include "no meeting room" and "auto-pick any room with enough capacity" choices. The default source: "auto" tries Exchange room-list discovery and falls back to configured policy rooms; offer the user a choice among the returned room values or "no specific room"; do not rely on a hand-written room list.
  8. If the user wants a room but does not choose a specific room, call ews_suggest_slots with require_room: true and no rooms; the tool uses dynamic Exchange rooms when available, then falls back to configured rooms, and filters rooms with known capacity below the attendee count. P means persons.
  9. If the user chooses specific rooms, pass the selected room values or emails in rooms when calling ews_suggest_slots.
  10. Show suggested slots with their available_rooms. When asking the user to pick a slot or room, prefer the host's interactive multiple-choice UI or clickable choice controls when available; otherwise show a short numbered list. Omit workday_start, workday_end, and avoid to use local policy defaults.
  11. When the user picks a slot and room, call ews_create_meeting_preview with the selected room in rooms.
  12. For recurring meeting requests, pass a structured recurrence object to preview and confirmed create calls. Weekly Monday/Wednesday uses {"type":"weekly","interval":1,"weekdays":["MO","WE"],"range":{"type":"numbered","count":10}}. Every business day until 2026-07-26 uses {"type":"weekly","interval":1,"weekdays":["MO","TU","WE","TH","FR"],"range":{"type":"end_date","end_date":"2026-07-26"}}. Business days mean Monday through Friday only. If the user gives weekdays but no end date, occurrence count, or explicit no-end choice, ask for one before previewing.
  13. Show the exact preview: attendees, rooms, start/end with timezone offsets, show_as, confirmed_will_send_invites, subject, body, location, signature status, recurrence if present, and confirmation_id.
  14. Only after the user explicitly confirms, call ews_create_meeting_confirmed with confirm: true and the exact confirmation_id returned by preview.
  15. After a successful confirmed create, call ews_verify_meeting with the returned item id and changekey when available, then report the organizer item status and room response_status. Treat unknown room response as pending/unknown, not as failure.

Read the full file on GitHub · 81 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed · +2 lines 03e2f9f03efe
  2. 2mo ago First seen · 79 lines · 70 tokens per session scan A 95eb8b9ee12d

Subscribe to this mod's changes

ews-meeting-mcp is a skill published in the GitHub repository ap311036/ews-meeting-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 3,215 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

rowboat-spaces

How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.

rowboatlabs/rowboat · 60 tokens

Cortex

LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…

danielmiessler/LifeOS · 184 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens