A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
B2match (unofficial) 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.
94/100
trust score
11
downloads a day
local
runs on your machine
739
downloads in 30d
What it does
Unofficial read-only B2match events: agenda, participants, meetings, schedule, conversations
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user b2match-unofficial-mcp '--' npx -y b2match-mcp
# 2 — ask your agent for something these tools do
# auth_status, list_my_events, get_event and 20 more
B2match (unofficial) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
BAAll 2 servers
barzoj2 servers
2 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. This one runs on your machine: your client starts B2match (unofficial) 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 b2match-unofficial-mcp '--' npx -y b2match-mcpReconnect, 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
23 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Show whether a local B2match token is available and, when valid, who it belongs to. Never returns the token. Call this first when an authenticated tool (my_*, list_my_events, conversations, notifications) reports a login error; public tools work without a token.
No parameter schema on file.
List events the logged-in viewer has joined, with ids/slugs usable as the event argument elsewhere. Requires login; use get_event for any single public event instead.
No parameter schema on file.
Fetch public event metadata, dates, registration window, login methods, and navigation menu paths. Start here to resolve an event before calling the other event tools; use list_my_events to find events you joined. Works without login.
No parameter schema on file.
Fetch the logged-in viewer's own participant status, activation, permissions, organisation pages, and opportunities for one event. Use get_participant for someone else's public profile.
No parameter schema on file.
List public participants as a compact summary. Set detail=true for the fuller record; use get_participant for one profile.
No parameter schema on file.
Fetch one participant's full public profile without sending B2match's profile-view tracking mutation. Use list_participants to search or find ids; use my_participation for your own status.
No parameter schema on file.
List organisation pages (participations) of an event, paginated. Use get_organisation for one page, list_participants for people. Resolves the menu path automatically; pass path to override.
No parameter schema on file.
Fetch one organisation page (a participation: organisation details plus its representatives). Use list_organisations to find participation ids; use get_participant for a single person. Resolves the menu path automatically; pass path to override.
No parameter schema on file.
List published marketplace opportunities (offers/requests) of an event, paginated. Use get_opportunity for one entry's full details. Resolves the menu path automatically; pass path to override.
No parameter schema on file.
Fetch a marketplace opportunity. Use the id or url from list_opportunities (published marketplace ids differ from opportunity ids on my_participation). Resolves the marketplace menu path automatically; pass path to override.
No parameter schema on file.
Fetch the event agenda: sessions and networking blocks with times. Use get_session for one session's details and my_schedule for your personal schedule. Resolves the menu path automatically; pass path to override.
No parameter schema on file.
Fetch one agenda session with its details and a first page of attendees. Provide session_id, or path to a session URL; path alone is enough. Use list_session_attendees to page through attendees only, get_agenda to find sessions.
No parameter schema on file.
Page through the attendees of one agenda session. Returns only the attendee list with a cursor, not the session details; use get_session for those. Provide session_id or path (from get_agenda).
No parameter schema on file.
List the speakers shown on the event's speakers page, paginated. Use list_participants for all registered participants. Resolves the menu path automatically; pass path to override.
No parameter schema on file.
Fetch the logged-in viewer's personal event schedule (booked sessions and meetings). Use get_agenda for the full public agenda and my_meetings for meeting requests by status. The PDF agenda URL is omitted unless include_pdf_link is true.
No parameter schema on file.
Fetch the logged-in viewer's meetings and meeting requests, optionally one status bucket. Unfiltered responses include a compact availability summary (merged free ranges per day) unless detail=true. Use my_schedule for the overall timetable and find_meeting_slots to find free times with others.
No parameter schema on file.
Fetch the logged-in viewer's own meeting availability. Default is merged free ranges per day; set detail=true for the full timeslot grid. Use find_meeting_slots for slots shared with specific participants.
No parameter schema on file.
Find free meeting slots shared by the logged-in viewer and selected participants on one day. Read-only: does not book or request a meeting. Use my_availability for your own free time only.
No parameter schema on file.
Fetch B2match's recommended and newest participants for the logged-in viewer to meet. Use list_participants to search all participants and find_meeting_slots to check shared free time.
No parameter schema on file.
List the logged-in viewer's conversations with last-message previews, paginated. Does not mark conversations as read; prefer it over get_conversation unless full message history is needed.
No parameter schema on file.
Fetch conversation messages. B2match marks that conversation as read when messagesV2 is fetched, even though this client never sends MarkConversationAsSeen. Disabled unless …=1 and acknowledge_marks_read is true. Use list_conversations for last-message previews. Unknown ids return a not-found error.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | string | yes | Conversation UUID from list_conversations. |
| acknowledge_marks_read | boolean | no | Required with B2MATCH_ALLOW_SIDE_EFFECT_READS=1; fetching messages marks the conversation as read. |
Returns unread/unseen notification counters by default. Fetching the notification list resets B2match's unseen counter (unseen goes to 0) even though this client never sends ReadNotification. The unread counter is unchanged. The full list requires …=1 and acknowledge_marks_seen=true.
No parameter schema on file.
Run a raw B2match GraphQL query. Disabled unless B2MATCH_ALLOW_RAW=1. Rejects mutations, subscriptions, and queries that select messagesV2 or the notifications list unless …=1.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | GraphQL query document; only query operations are allowed. |
| variables | object | no | GraphQL variables object. |
| require_auth | boolean | no | true sends the stored token and fails if none is available. |
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 B2match (unofficial) 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 94 / 100
Release 0.2.2 · scanned 28 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 score94
Findings3 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest756ed6fcf7857faae112f99d664d8d2ed293da22c146f2f26474953e9a3dd0c1
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 (23 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>".
1 of the 23 recovered tools are registered only when process.env.B2MATCH_ALLOW_RAW === "1" holds (dist/server.js:286) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 22.
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.
22 tools are registered unconditionally · 1 more only when process.env.B2MATCH_ALLOW_RAW === "1" holds (dist/server.js:286) — typically when a key or option is configured. All 23 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| auth_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_my_events | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_event | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| my_participation | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| list_participants | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_participant | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| list_organisations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_organisation | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| list_opportunities | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_opportunity | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| get_agenda | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| get_session | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| list_session_attendees | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_speakers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| my_schedule | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| my_meetings | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| my_availability | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| find_meeting_slots | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| meeting_recommendations | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| list_conversations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_conversation | untrusted-inputexternal-sink | untrusted-input: keyword "fetch"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_notifications | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| graphql_read conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest756ed6fcf7857faa
Scanned2026-10-28
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 0.2.2. Pin a release below and the command asks for exactly that one.
0.2.2
25 Oct 2026
latestNo release note was published with this version.
0.2.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 B2match (unofficial) 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.