A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Omnifocus Mcp Enhanced is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
15
downloads a day
local
runs on your machine
578
downloads in 30d
What it does
🚀 NEW: Native Custom Perspective Access! Enhanced MCP server with OmniFocus custom perspective support, hierarchical task display, AI-optimized tool selection, and comprehensive task management
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user omnifocus-mcp-enhanced '--' npx -y omnifocus-mcp-enhanced
# 2 — ask your agent for something these tools do
# dump_database, add_omnifocus_task, add_project and 23 more
Omnifocus Mcp Enhanced costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JQAll 1 server
jqlts11 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Omnifocus Mcp Enhanced as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user omnifocus-mcp-enhanced '--' npx -y omnifocus-mcp-enhancedReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
26 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Gets the current state of your OmniFocus database
No parameter schema on file.
Add a new task to OmniFocus
No parameter schema on file.
Add a new project to OmniFocus
No parameter schema on file.
Remove a task or project from OmniFocus
No parameter schema on file.
Edit a task or project in OmniFocus
No parameter schema on file.
Move an existing task to a project, parent task, or inbox
No parameter schema on file.
Move a confirmed set of tasks to projects, parent tasks, or Inbox. The complete batch is validated before any change and every destination is verified afterward.
No parameter schema on file.
Mark tasks complete or incomplete by stable ID. Accepts up to 100 items with optional completion dates. Preflights every ID, verifies every result, and restores previous states on failure. Repeating tasks generate new instances when completed.
No parameter schema on file.
Edit fields and tags on up to 100 tasks or projects by stable ID. Each item names one object with taskId or projectId and carries only the fields it changes; an omitted field is untouched and an explicit null clears it. Dates accept an absolute value or a signed shift such as "+1w". Projects also…
No parameter schema on file.
Add multiple tasks or projects to OmniFocus in a single operation
No parameter schema on file.
Remove a user-confirmed set of tasks or projects by stable ID. The complete batch is validated before deletion and every ID is verified absent afterward.
No parameter schema on file.
Create one user-confirmed project tree with stable folder/tag IDs. The complete outline is preflighted, created in one OmniFocus request, and read back for verification.
No parameter schema on file.
Get information about a specific task by ID or name
No parameter schema on file.
Read a task attachment reported by get_task_by_id. Images are returned as MCP image content when possible.
No parameter schema on file.
Read tasks from inbox, flagged, forecast, tag, or custom perspective. Use source to select the view; source-specific parameters are strictly validated.
No parameter schema on file.
Set, update, or clear the repeat rule on a task. Supports ICS rule strings, schedule type, anchor date, catch-up, end date, and repetition count.
No parameter schema on file.
List, search, add, edit, or remove OmniFocus tags. This mixed-operation tool is conservatively marked destructive: list/search are read-only, add/edit mutate, and remove deletes the selected tag plus child tags but keeps tasks.
No parameter schema on file.
Advanced task filtering by status, dates, projects, tags, search, and more, with optional subtask-tree expansion
No parameter schema on file.
List OmniFocus projects or projects due for review. Use view=all (default) for status/folder filters, or view=due_for_review for overdue review work.
No parameter schema on file.
Mark a user-confirmed set of active or on-hold projects reviewed. The complete batch is validated first and review dates are verified afterward.
No parameter schema on file.
List, inspect, and edit OmniFocus custom perspectives and their filter rules. Use this to explain why a perspective shows what it shows, or to change its rules. Perspectives are saved views, not tags. list/get are read-only; update rewrites rules in place. Creating and deleting are not supported…
No parameter schema on file.
List, get, add, edit, or remove OmniFocus folders. This mixed-operation tool is conservatively marked destructive: list/get are read-only, add/edit mutate, and remove permanently deletes contained projects and tasks.
No parameter schema on file.
Append text to a task or project note without overwriting the existing note. Useful for logging progress or adding context.
No parameter schema on file.
Count tasks matching filters without returning the full list. Fast 'how many' queries that return a total plus a breakdown by status. Uses the same filters as filter_tasks.
No parameter schema on file.
Duplicate an existing task, optionally with its subtasks, and optionally with a new name. Useful for template-based workflows.
No parameter schema on file.
List, add, or remove task notifications. This mixed-operation tool is conservatively marked destructive: list is read-only, add mutates, and remove deletes one or all notifications.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Omnifocus Mcp Enhanced or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 2.2.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings2 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest82671c9ce8964a5070ccf753f7a11d94a82fceeb6188d912235dfaab44b2a54a
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (26 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| dump_database | sensitive-source | sensitive-source: keyword "dump" |
| add_omnifocus_task | no tags | |
| add_project | no tags | |
| remove_item | no tags | |
| edit_item | no tags | |
| move_task | no tags | |
| batch_move_tasks | no tags | |
| batch_complete_tasks | no tags | |
| batch_edit_items | no tags | |
| batch_add_items | no tags | |
| batch_remove_items | no tags | |
| create_project_from_outline | no tags | |
| get_task_by_id | no tags | |
| read_task_attachment | no tags | |
| get_tasks | no tags | |
| set_repetition_rule | no tags | |
| manage_tags | no tags | |
| filter_tasks | no tags | |
| get_projects | no tags | |
| mark_projects_reviewed | no tags | |
| manage_perspectives | no tags | |
| manage_folders | no tags | |
| append_to_note | no tags | |
| count_tasks | no tags | |
| duplicate_task | no tags | |
| manage_task_notifications | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest82671c9ce8964a50
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.2.0. Pin a release below and the command asks for exactly that one.
2.2.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Omnifocus Mcp Enhanced can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.