A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Parabol 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
tool-list score
21
tools declared
remote
at its publisher
—
calls last 7d
What it does
Start Parabol retrospectives, standups and sprint poker; read teams/meetings/tasks; create tasks.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http parabol-mcp https://parabol.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# get_viewer, list_teams, get_team and 18 more
Parabol costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 334 servers
usefulapi334 servers
24 categories
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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http parabol-mcp https://parabol.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
21 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.
Fetch the authenticated Parabol user (the token owner): id, preferredName, email, tier, and the team ids (tms) they belong to. Parabol GraphQL: query { viewer { ... } }. Requires the USERS_READ scope. Start here to discover your identity and team ids.
No parameter schema on file.
List the teams the viewer belongs to, with each team's id, name, orgId, tier, and team lead. Parabol GraphQL: viewer.teams. Requires the TEAMS_READ scope.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| includeArchived | boolean | no | Include archived teams (default false). |
Fetch one team by id: metadata, its team members (with each member's user), active meetings, and organization. Parabol GraphQL: viewer.team(teamId). Requires TEAMS_READ (+ MEETINGS_READ for activeMeetings, ORGS_READ for organization).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id. |
List the members of a team, each with role flags (isLead, isOrgAdmin) and the underlying user (preferredName, email). Parabol GraphQL: viewer.team(teamId).teamMembers. Requires TEAMS_READ.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id. |
| sortBy | string | no | Optional field to sort members by (e.g. 'preferredName'). |
List the organizations the viewer belongs to: id, name, tier, billingTier. Parabol GraphQL: viewer.organizations. Requires ORGS_READ.
No parameter schema on file.
Fetch one organization by id, including its teams. Parabol GraphQL: viewer.organization(orgId). Requires ORGS_READ (+ TEAMS_READ for teams).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| orgId | string | yes | The organization id. |
List the users in an organization (Relay connection): each org-user's role, joinedAt, tier, and underlying user (preferredName, email). Paginate with first + after (pass the last edge's cursor). Parabol GraphQL: viewer.organization(orgId).organizationUsers. Requires ORGS_READ + USERS_READ.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| orgId | string | yes | The organization id. |
| first | integer | no | Max org-users to return (page size). |
| after | string | no | Cursor for the next page (the cursor of the last edge from a prior call). |
List past/ongoing meetings for one or more teams (Relay connection), newest first. teamIds is required. meetingTypes defaults to all four (retrospective, action, poker, teamPrompt). before bounds the window (defaults to now); paginate older with after. Parabol GraphQL: viewer.meetings. Requires MEETINGS_READ.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamIds | array | yes | Team ids to fetch meetings for (required). |
| meetingTypes | array | no | Meeting types to include (MeetingTypeEnum). Defaults to all four. |
| first | integer | no | Max meetings to return (default 20). |
| after | string | no | DateTime cursor — return meetings before this ISO timestamp (older page). |
| before | string | no | DateTime upper bound (ISO). Defaults to now. |
Fetch one meeting by id with its phases and stages. For a retrospective it also returns the reflection groups and reflections plus vote/topic/task/comment counts. Uses __typename so you can tell meeting types apart. Parabol GraphQL: viewer.meeting(meetingId). Requires MEETINGS_READ.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| meetingId | string | yes | The meeting id. |
List a team's currently-active (in-progress) meetings. Parabol GraphQL: viewer.team(teamId).activeMeetings. Requires TEAMS_READ + MEETINGS_READ.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id. |
List the viewer's tasks (Relay connection), optionally filtered by team, user, status, archived state, or a text query. Paginate with first + the after DateTime cursor. Parabol GraphQL: viewer.tasks. Requires TASKS_READ.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| first | integer | no | Max tasks to return (default 20). |
| after | string | no | DateTime cursor for the next (older) page (the last edge's cursor). |
| teamIds | array | no | Filter to these team ids. |
| userIds | array | no | Filter to tasks assigned to these user ids. |
| statusFilters | array | no | Filter by task status (TaskStatusEnum: active, stuck, done, future). |
| archived | boolean | no | Include archived tasks (default false). |
| includeUnassigned | boolean | no | Include unassigned tasks (default false). |
| filterQuery | string | no | Free-text filter on task content. |
Escape hatch: run an arbitrary Parabol GraphQL QUERY (read-only) against action.parabol.co/graphql with optional variables. Mutations are REJECTED — use the dedicated write tools or parabol_graphql for those. Useful for fields not covered by the curated read tools. Requires the matching read scope(s) on your token.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | A GraphQL query document (must be a query, not a mutation). |
| variables | object | no | Variables object for the query. |
MUTATES Parabol data: create a task on a team. Required: teamId and status (active|stuck|done|future). Provide plaintextContent for the task text (and/or content, which is a stringified TipTap/ProseMirror JSON document). Optionally assign to a userId or link to a meetingId/discussionId. Parabol GraphQL: createTask(newTask, area). Requires TASKS_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id to create the task on (required). |
| status | string | no | Task status (TaskStatusEnum). Defaults to 'active'. |
| plaintextContent | string | no | Plain-text task content. |
| content | string | no | Rich-text content as a stringified TipTap/ProseMirror JSON document. |
| userId | string | no | Assign the task to this user id. |
| meetingId | string | no | Link the task to this meeting id. |
| discussionId | string | no | Link the task to this discussion id (meeting thread). |
| sortOrder | number | no | Sort order (Float). |
| area | string | no | Optional AreaEnum context for the task (e.g. 'teamDash', 'meeting'). |
| fields | object | no | Additional documented GraphQL input fields to send verbatim in this mutation's input (merged OVER the typed fields above). |
MUTATES Parabol data: update an existing task. Required: id. Optionally change content (stringified TipTap JSON), status, assignee (userId), or sortOrder. Only included fields change. Parabol GraphQL: updateTask(updatedTask, area). Requires TASKS_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The task id (required). |
| content | string | no | New rich-text content as a stringified TipTap/ProseMirror JSON document. |
| status | string | no | New status (TaskStatusEnum). |
| userId | string | no | Reassign the task to this user id. |
| sortOrder | number | no | New sort order (Float). |
| area | string | no | Optional AreaEnum context. |
| fields | object | no | Additional documented GraphQL input fields to send verbatim in this mutation's input (merged OVER the typed fields above). |
MUTATES Parabol data: add a reflection card to a running retrospective's reflect phase. Required: meetingId, promptId (the reflect-prompt/column), sortOrder (Float). content (optional) is a stringified TipTap/ProseMirror JSON document (<=2000 chars). Parabol GraphQL: createReflection(input). Requires MEETINGS_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| meetingId | string | yes | The retrospective meeting id (required). |
| promptId | string | yes | The reflect-prompt (column) id (required). |
| sortOrder | number | no | Sort order within the column (Float). Defaults to 0. |
| content | string | no | Reflection text as a stringified TipTap/ProseMirror JSON document. |
| fields | object | no | Additional documented GraphQL input fields to send verbatim in this mutation's input (merged OVER the typed fields above). |
MUTATES Parabol data: add a comment to a meeting discussion thread. Required: content (stringified TipTap/ProseMirror JSON document), discussionId, threadSortOrder (Int). Optionally isAnonymous or threadParentId (to reply). Parabol GraphQL: addComment(comment) → union. Requires COMMENTS_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | Comment body as a stringified TipTap/ProseMirror JSON document (required). |
| discussionId | string | yes | The discussion (meeting thread) id (required). |
| threadSortOrder | integer | no | Position within the thread (Int). Defaults to 0. |
| isAnonymous | boolean | no | Post the comment anonymously. |
| threadParentId | string | no | Parent comment id, to post a threaded reply. |
| fields | object | no | Additional documented GraphQL input fields to send verbatim in this mutation's input (merged OVER the typed fields above). |
MUTATES Parabol data: start a new retrospective meeting for a team (returns the new meetingId). Required: teamId. Optionally name it. Parabol GraphQL: startRetrospective → union. Requires MEETINGS_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id to run the retro for (required). |
| name | string | no | Optional meeting name. |
MUTATES Parabol data: start a new Check-in (Action) meeting for a team (returns the new meetingId). Required: teamId. Optionally name it. Parabol GraphQL: startCheckIn → union. Requires MEETINGS_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id (required). |
| name | string | no | Optional meeting name. |
MUTATES Parabol data: start a new async Standup (Team Prompt) meeting for a team. Required: teamId. Optionally name it (default 'Standup'). Parabol GraphQL: startTeamPrompt → union. Requires MEETINGS_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id (required). |
| name | string | no | Optional meeting name (default 'Standup'). |
MUTATES Parabol data: send team invitations by email. Required: teamId and invitees (an array of email addresses). Optionally scope to a meetingId. Parabol GraphQL: inviteToTeam(teamId, invitees). Requires TEAMS_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id to invite into (required). |
| invitees | array | yes | Email addresses to invite (required). |
| meetingId | string | no | Optionally associate the invitation with a meeting id. |
MUTATES Parabol data (potentially): escape hatch to run an arbitrary Parabol GraphQL operation — including any mutation — against action.parabol.co/graphql with optional variables. Use for operations not covered by the curated tools. Your token must carry the scope the operation requires. Prefer parabol_query for read-only calls.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | A GraphQL query or mutation document. |
| variables | object | no | Variables object for the operation. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Parabol 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: —
ATool-list grade · score 93 / 100
Release 1.11.1 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
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
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest9927d54fa56063886f0c7c81ce94b32ad4e05626c57d96c657f38c2f1f61aa98
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_viewer | untrusted-input | untrusted-input: keyword "fetch" |
| list_teams | no tags | |
| get_team | untrusted-input | untrusted-input: keyword "fetch" |
| list_team_members | no tags | |
| list_organizations | no tags | |
| get_organization | untrusted-input | untrusted-input: keyword "fetch" |
| list_organization_users | no tags | |
| list_meetings | no tags | |
| get_meeting | untrusted-input | untrusted-input: keyword "fetch" |
| list_active_meetings | no tags | |
| list_tasks | no tags | |
| parabol_query | no tags | |
| create_task | state-write | state-write: declares destructiveHint: true |
| update_task | state-write | state-write: declares destructiveHint: true |
| create_reflection | state-write | state-write: declares destructiveHint: true |
| add_comment | state-write | state-write: declares destructiveHint: true |
| start_retrospective | state-write | state-write: declares destructiveHint: true |
| start_checkin | state-write | state-write: declares destructiveHint: true |
| start_team_prompt | state-write | state-write: declares destructiveHint: true |
| invite_to_team | state-write | state-write: declares destructiveHint: true |
| parabol_graphql | state-write | state-write: declares destructiveHint: true |
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 digest9927d54fa5606388
Scanned2026-10-20
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.11.1.
1.11.1
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 Parabol 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.