RU
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Nothing to run from here
Pi Durateam 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.
92/100
trust score
10
downloads a day
local
runs on your machine
596
downloads in 30d
What it does
Pi agent teams on any provider: parallel delegates, forks, MCP tools; runs built to finish.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user pi-durateam-mcp '--' npx -y pi-durateam
# 2 — ask your agent for something these tools do
# status, steer, wait and 15 more
Pi Durateam costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NYAll 2 servers
Nyarlathoteppppp2 servers
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 Pi Durateam 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 pi-durateam-mcp '--' npx -y pi-durateamReconnect, 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
18 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.
Check a background pi session. Returns state, turn count, tools used, latest text, and any
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
| verbose | boolean | no | Include the full tool trace and notice history |
Redirect a running pi agent mid-task. The message lands after its current tool call finishes,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
| message | string | yes | — |
Wait for delegates without polling in a loop. until: "progress" (default) returns after a new
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | One session; returns its status snapshot |
| sessionIds | array | no | Several sessions; returns a summary of each |
| until | string | no | Default progress for sessionId, settled for sessionIds |
| timeoutMs | integer | no | Default … for settled/all_settled, … for progress; max … |
| afterTurns | integer | no | Prior snapshot's turn count |
| afterToolCalls | integer | no | Prior snapshot's toolCallCount |
| verbose | boolean | no | Single session: include the full snapshot, tool results and call ids |
Answer a pending Pi extension UI question. Get requestId from questions[].id in status or wait.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
| requestId | string | yes | — |
| value | yes | Chosen option, text, or boolean for a confirm |
Send another prompt to a delegate that has already finished, keeping everything it read
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
| prompt | string | yes | The next turn for this delegate |
| maxTurns | integer | no | Fresh turn quota for this run; omitted keeps the remaining budget |
| maxToolCalls | integer | no | Fresh own-tool-call quota for this run; omitted keeps the remaining budget |
| attachments | array | no | Absolute paths of text files appended to this prompt, as on spawn |
| saveTo | string | no | Absolute file path for this run's final text, as on spawn |
Stop a running pi session. Partial output stays readable via status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
List pi sessions held by this server, running and finished, plus finished durable sessions
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cwd | string | no | Absolute project directory; includes loaded and stored sessions for this cwd |
| state | string | no | Filter by state: starting, running, done, aborted, error |
| verbose | boolean | no | Include full text and tool calls |
Drop a finished session from the review history, freeing its id for reuse.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
Hand a Pi session over between Claude/Codex windows. save (when the user asks to hand over): record
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| cwd | string | yes | Absolute path of the repository. save: the session's own cwd, exactly as it was spawned with |
| name | string | no | Optional label to keep several handoffs per repository; read defaults to the newest |
| sessionId | string | no | save: the Pi session to hand over |
| goal | string | no | save: what the work is for |
| completed | string | no | save: what is done, including results a new window needs |
| next | string | no | save: the next step |
Optional setup diagnostics: reports model availability, provider authentication, permissions and budgets.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| models | string | no | Substring to filter the model list, e.g. "deepseek" |
| cwd | string | no | Repository you intend to delegate in; picks up its project-local pi model scope |
List models this delegate may use from pi's available providers after model filters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filter | string | no | — |
| cwd | string | no | Picks up a project-local pi model scope |
| offset | integer | no | First matching model index to return |
| limit | integer | no | Page size, default …, at most 200 |
Delegate a task to a pi agent running in the background. Returns a sessionId immediately, so
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resources | no | Explicit instruction/skill files; omitted loads none. Forks inherit the selection; {} clears it. Does not grant tools. | |
| coordinator | no | Opt-in memory-only orchestration of caller-planned read-only children. Omitted prompt gives a concise synthesis with disagreements, failed coverage and original report references; omitted tools select | |
| prompt | string | no | The task for the pi agent. Required for ordinary delegates; omit with coordinator for the default dispatch/wait/synthesis workflow. A supplied prompt replaces that default. |
| forkFrom | string | no | Start a new task from a settled session's history; budgets are fresh. Omitted cwd/model/tools inherit and are revalidated, except coordinator defaults its omitted tools to codemode. |
| attachments | array | no | — |
| saveTo | string | no | Absolute file path: when the run finishes, its final text is written there and results show savedTo instead |
| model | string | no | Omit for the configured default. Use "provider/modelId" from the models tool to choose another. |
| fallbackModels | array | no | — |
| thinking | string | no | Explicit pi thinking level. Omit to use pi's configured/default level. |
| cwd | string | no | Absolute working directory. Required unless forkFrom supplies the parent cwd. |
| id | string | no | — |
| label | string | no | Free-text note shown in sessions, e.g. what this delegate is for; never sent to the delegate |
| tools | array | no | — |
| nativeMcp | boolean | no | Enable Pi native MCP independently of third-party extensions. Requires explicit mcpServers and authorized exact tool names, including codemode/tool_search if used. |
| mcpServers | array | no | Names from Pi mcp.json to connect. Required with nativeMcp; other servers are not loaded. |
| extensions | boolean | no | Load pi extensions for this delegate. Off by default; they add startup cost and can misbehave. |
| durable | boolean | no | — |
| retentionDays | integer | no | — |
| maxTurns | integer | no | Turn quota shared with follow_up unless explicitly renewed there; server ceiling …. |
| maxDurationMs | integer | no | Wall-clock deadline in milliseconds; server ceiling …. |
Fan out several delegates in one call. Each task inherits the batch-level model, cwd, tools
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tasks | array | yes | 1 to … delegates to start |
| prompt | string | no | Shared instructions for every task, e.g. one review sent to several models; a task's own prompt is added after it. Coordinator tasks keep their default synthesis. |
| resources | yes | Default resource selection for batch tasks; each task can replace it, including {} to clear. | |
| coordinator | no | A coordinator plan, exactly as spawn's coordinator (see spawn for its fields); checked the same way. | |
| forkFrom | string | no | Default settled parent session for this batch |
| attachments | array | no | Default for every task in this batch. Absolute paths of text files appended to the prompt, read by this server, e.g. a diff you wrote to your scratchpad; they may lie outside cwd. At most 20, 256 KiB |
| saveDir | string | no | Absolute directory: each finished task's final text is written to <sessionId>.md there |
| model | string | no | Default model for every task in this batch |
| fallbackModels | array | no | Default for every task in this batch. Models to continue on, in this session, when a provider error outlasts Pi's own retries: patterns such as "xai/*" or exact refs, tried in order; models of the fai |
| thinking | string | no | Default thinking level for every task in this batch; omit to use pi settings |
| cwd | string | no | Default working directory for every task in this batch |
| tools | array | no | Default tool allowlist for every task in this batch |
| extensions | boolean | no | Default extensions setting for every task in this batch |
| durable | boolean | no | Default for every task in this batch. Default false: memory only, nothing written, gone when this MCP process exits; right for short, cheap, re-runnable work such as reviews, searches and model compar |
| nativeMcp | boolean | no | Default native MCP setting for this batch |
| mcpServers | array | no | Default native MCP server selection for this batch |
| maxTurns | integer | no | Default turn budget; server ceiling … |
| maxDurationMs | integer | no | Default wall-clock deadline; server ceiling … ms |
| maxToolCalls | integer | no | Default cap on each delegate's own tool calls |
| retentionDays | integer | no | Default for every task in this batch. Durable only: days to keep it on disk after it finishes (default …, max …). Set it longer when the user wants to come back to this session later. |
Delegate a task to a pi agent and wait for the final answer. Blocks until done.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coordinator | no | A coordinator plan, exactly as spawn's coordinator (see spawn for its fields); checked the same way. | |
| verbose | boolean | no | Include configuration and the full tool trace with ids and results |
Launch caller-approved tasks by zero-based taskIndexes (omit for all unlaunched). Started tasks run once; startup failures can be retried.
No parameter schema on file.
Wait for all selected children, or all launched children when sessionIds is omitted; until:"settled" returns as soon as any one settles, so a larger plan can start its next task in the freed slot. timeoutMs: max 55000, default 30000 when omitted. Returns compact per-child state, questions, errors…
No parameter schema on file.
Get one launched child's full report, state and follow-up readiness (without renewing quotas), including questions, failures and save diagnostics. store() reports within the SDK's storage limits; print only the conclusions/references the caller needs. Original savedTo files remain independent of…
No parameter schema on file.
Ask a finished child launched by this coordinator a targeted question, preserving its history/model/tools.
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 Pi Durateam 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 92 / 100
Release 0.7.12 · 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 score99
Client score92
Findings5 threat · 2 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestbdc4a74590f00222304dcf43b9fc379cadc852c68088304978cc0fd82b184981
Score vectorthreat 99 → client 92
| 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 (14 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 |
|---|---|---|
| status | no tags | |
| steer | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| wait | no tags | |
| answer | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| follow_up | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| abort | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| sessions | no tags | |
| forget | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| handoff | state-write | state-write: declares readOnlyHint: false |
| init | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| models | no tags | |
| spawn | code-execexternal-sink | code-exec: keyword "spawn" in tool name; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| spawn_batch | code-execexternal-sink | code-exec: keyword "spawn" in tool name; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| run | 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
Integrityfirst-seen
Surface digestbdc4a74590f00222
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 0.7.12. Pin a release below and the command asks for exactly that one.
0.7.12
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 Pi Durateam 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.