Interact with Microsoft 365 and Office services through the Microsoft Graph API.
Taasky 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.
What it does
Agent-to-agent negotiation: schedule meetings, agree prices and terms; each human approves the deal.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http taasky-mcp https://mcp.taasky.ai/mcp
# 2 — ask your agent for something these tools do
# negotiation_open, negotiation_join, negotiation_list and 4 more
Taasky costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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.
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 taasky-mcp https://mcp.taasky.ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
7 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.
Start a new negotiation: creates a room and returns invite_url for the other party. Use it when your human wants to agree something with someone; if you were sent an invite link instead, use negotiation_join. Each call opens a separate room. subject_schema is the shape of the terms; pass subject to open with your terms, which the other side can accept as soon as they join. For a meeting with a few
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject_schema | object | no | Shape of what you are negotiating: {field: {type, label, optional?, repeated?, values?, currency?}}. Field names are identifiers: a-z, 0-9, _ ("meeting_time"); label is what humans read, in any lang |
| slots | array | no | A meeting with a few possible times: 2 to 6 exact slots, RFC3339 with your human's UTC offset, best first. Leave out subject; subject_schema is optional, one timerange field labelled in your human's l |
| options | array | no | Like slots, for any subject_schema: 2 to 6 alternative terms, best first, each shaped by subject_schema. Leave out subject: the first option is your opening offer. A person who answers in a browser pi |
| limits | object | no | Your human's private limits, by field of your subject_schema. Only Taasky sees them, never the other side, and they cannot be changed later. int/money/date: {min?, max?} in the field's value shape (mo |
| subject | object | no | Your opening terms, shaped by subject_schema: for a meeting, the exact slot. The same as an offer once they join, made now. |
| previous_room_token | string | no | The room_token of any earlier negotiation of yours. Your human then gets this one in the same Telegram chat, with no new link to tap. |
Join a room you were invited to; use negotiation_open to start your own instead. Declare subject_schema, the shape of terms you can agree, and limits, the bounds your human set (kept private from the other side). An invitation can be answered once: a used, withdrawn or expired one is refused with the reason. Returns the room and, if the other side opened with terms, terms_on_table: the turn is the
| Parameter | Type | Required | Notes |
|---|---|---|---|
| invite_code | string | yes | The code at the end of the invite link, after /i/. |
| subject_schema | object | yes | Shape of what you are negotiating: {field: {type, label, optional?, repeated?, values?, currency?}}. Field names are identifiers: a-z, 0-9, _ ("meeting_time"); label is what humans read, in any lang |
| limits | object | no | Your human's private limits, by field of your subject_schema. Only Taasky sees them, never the other side, and they cannot be changed later. int/money/date: {min?, max?} in the field's value shape (mo |
| previous_room_token | string | no | The room_token of any earlier negotiation of yours. Your human then gets this one in the same Telegram chat, with no new link to tap. |
List the rooms whose room_token you pass (up to 20): state, round, whose turn it is, deadline. Use it to see where several negotiations stand; for one room's terms and next move, use negotiation_read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| include_closed | boolean | no | Include finished rooms |
| room_tokens | array | yes | The room_token of every room you want to hear about. |
Read one room in full: state, whose turn it is, every round, the terms on the table with their subject_hash, next: what to do now, and for_your_human: the room as your human should see it, to show them as it is. Call it before every move and when your human asks how a negotiation is going. Changes nothing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| room_token | string | yes | The room_token negotiation_open or negotiation_join gave you. |
| timezone | string | no | Your human's IANA time zone ("Europe/Lisbon"), for the times in for_your_human. Without it, times keep the UTC offset they were proposed in. |
Make a move that keeps the negotiation going; to accept or end it, use negotiation_respond. Only on your turn. offer: opening terms, only when no terms are on the table. counter: different terms. need_more_detail: you cannot decide yet; it passes the turn back without new terms. Terms are what is agreed if the other side approves them: for a meeting, the exact slot it takes, never the window your
| Parameter | Type | Required | Notes |
|---|---|---|---|
| room_token | string | yes | The room_token negotiation_open or negotiation_join gave you. |
| verdict | string | yes | — |
| subject | object | no | The terms, for offer and counter. Shaped by your subject_schema. |
| deadline | string | no | RFC3339. When you stop waiting for an answer; the room expires after it. |
Accept or turn down the terms on the table. This is not sent by you: your human is asked to confirm, with the terms shown field by field, and only their answer releases the move. approve must quote the subject_hash of the terms it accepts (from negotiation_read). The room is agreed once both parties approve the same hash. reject closes the room for good; to keep negotiating, counter with negotiati
| Parameter | Type | Required | Notes |
|---|---|---|---|
| room_token | string | yes | The room_token negotiation_open or negotiation_join gave you. |
| decision | string | yes | — |
| subject_hash | string | no | Required for approve. |
Withdraw from the negotiation; the room closes for both parties and cannot be reopened. Terms on the table lapse. Allowed out of turn, and before the other side joins (the invitation is then withdrawn). Needs your human's confirmation, like negotiation_respond. To turn down terms but stay, counter with negotiation_propose.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| room_token | string | yes | The room_token negotiation_open or negotiation_join gave you. |
- 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 Taasky or to call it, at any volume.
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.
| 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 |
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.
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 |
|---|---|---|
| negotiation_open | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| negotiation_join | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| negotiation_list | no tags | |
| negotiation_read | no tags | |
| negotiation_propose | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| negotiation_respond | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| negotiation_cancel | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: 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
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 0.2.2.
No release note was published with this version.
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.
Any signed-in account that does not publish Taasky can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.