de en es ja ko ru zh

pi-subagent

Name: pi-subagent
Author: guyiicn

by guyiicn

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

pi-subagent

Turn the Pi CLI (@earendil-works/pi-coding-agent) into a programmierbaren Coding-Sub-Agenten, dem jeder MCP-Host (ZCode, Claude Code, Cursor, …) Aufgaben delegieren, Sitzungen verfolgen und Prozesse beenden kann.

pi-subagent ist ein schlanker MCP-Server, der pi -p --mode json in 7 strukturierte Tools kapselt: Aufgaben delegieren, Ergebnisse abholen, Planungsentscheidungen treffen, benannte Sitzungen verwalten und Läufe abbrechen. Prozessisoliert, vollständig sitzungsbasiert, Sync/Async-Dualmodus.

Warum

Pi ist ein minimaler Terminal-Coding-Agent. Anstatt Pi Methodik beizubringen, behandelt dieses Projekt Pi als delegierbaren Arbeiter: Ein Host-Agent (ZCode / Claude Code) entscheidet, wann er delegiert, startet eine eigenständige Aufgabe und holt das Ergebnis ab. Ein Pi-Prozess = ein isolierter Sub-Agenten-Lauf.

Prozessisolation — jede Delegation startet einen pi -p-Kindprozess. Ein Pi-Absturz betrifft nur diesen Lauf.
Vollständig sitzungsbasiert — jede Aufgabe ist an eine benannte Sitzung gebunden (z. B. feat-auth); nachfolgende Aufrufe setzen automatisch fort.
Sync / Async — Standard ist async (vermeidet Timeouts bei Host-Tool-Aufrufen); Ergebnisse mit pi_status per Long-Poll abholen.
Planbar — pi_plan ist eine reine 5-stufige Entscheidungsfunktion (reject / capacity / reuse / modify / mode), vollständig unit-getestet.
Universelles MCP — jeder Standard-MCP-Client kann es laden.

Related MCP server: pi-delegate-mcp

Architektur

┌─────────────────────────────────────────────────────────────┐
│  MCP Host (ZCode / Claude Code / Pi / Cursor …)              │
└───────────────────────────┬─────────────────────────────────┘
                            │ MCP (JSON-RPC over stdio)
                            ▼
┌─────────────────────────────────────────────────────────────┐
│  pi-subagent-server  (Node/TS)                                │
│  ┌────────────┐  ┌──────────────┐  ┌────────────────────┐   │
│  │ Tool layer │  │ Session      │  │ Pi runner          │   │
│  │ (7 tools)  │─▶│ registry     │─▶│ (spawn pi -p)      │   │
│  │ + plan()   │  │ + persist    │  │ parse agent_end    │   │
│  └─────┬──────┘  │ + _snapshot  │  │ + tool_execution   │   │
│        │         └──────────────┘  └─────────┬──────────┘   │
│        │                           ┌────────▼─────────┐     │
│        └───────────────────────────│ Run registry     │     │
│           (kill)                   │ + process-table  │     │
│                                   └──────────────────┘     │
└─────────────────────────────────────────────────────────────┘
                            │ child_process.spawn({ cwd })
                            ▼
                   ┌─────────────────────┐
                   │  pi CLI (0.77+)     │
                   └─────────────────────┘

Drei Schichten mit klaren Grenzen: Tool-Schicht (MCP-Schema + plan()-reine Funktion) / Sitzungsregister (Zustand + Persistenz + Redaktion) / Runner (pi starten, NDJSON parsen, Prozesstabelle).

Tools

Tool	Zweck
`pi_plan`	Entscheiden: soll delegiert werden, sync/async, wie viele Sitzungen
`pi_delegate`	Eine Aufgabe auslösen (Standard async; neue Sitzungen warten auf Handshake)
`pi_status`	Ergebnis eines Laufs abholen (Long-Poll)
`pi_session_list`	Sitzungen auflisten (`cwd` weglassen für die vollständige Menge, die `pi_plan` benötigt)
`pi_session_snapshot`	Eine Sitzung inspizieren
`pi_session_fork`	Eine Sitzung abzweigen, um einen anderen Pfad zu testen
`pi_kill`	Einen Lauf abbrechen
`pi_task_create`	Eine mehrstufige Aufgabe erstellen (Host schreibt zuerst `_plan-draft.md`)
`pi_task_plan`	Eine Domänenprüfung des Plans auslösen (Ergebnis über `pi_status` abholen, Urteil automatisch geparst)
`pi_task_stage_run`	Eine Stufe ausführen: sync (auf Ergebnis warten) oder async (gibt runId zurück)
`pi_task_stage_collect`	Ergebnis eines async-Stufenlaufs abholen; automatisch bewerten und erneut auslösen (max. 3), sonst manuell
`pi_task_list`	Aufgaben auflisten (nach taskId / Status filtern)

Review-Schleife: Nach pi_task_plan das Ergebnis mit pi_status(runId) abholen. Wenn der Lauf endet, erkennt der Server, dass es sich um einen Review-Lauf handelt, parst _plan-reviewed.md und speichert planVerdict / planReviewedPath in der Aufgabe. Stufen-Prompts enthalten automatisch den überprüften Plan und die Ausgabedateien bestandener Abhängigkeitsstufen.

Async-Stufen: Übergeben Sie mode: "async" an pi_task_stage_run, um einen Tool-Aufruf nicht für den gesamten Lauf zu blockieren (empfohlen, wenn der MCP-Host ein kurzes Tool-Timeout erzwingt). Ergebnis mit pi_task_stage_collect(taskId, stageId) abholen. Fehlgeschlagene Versuche werden unter einem neuen Sitzungsnamen erneut ausgelöst, um eine Kontamination des Verlaufs zu vermeiden; nach 3 Fehlversuchen wechselt die Stufe auf manual mit einem Entscheidungsfeld (retry_with_new_hint wird über promptHintOverride unterstützt).

Neustart-Wiederherstellung: Ein erneutes Ausführen von pi_task_create mit derselben taskId führt zu einer Zusammenführung statt zu einem Konflikt. Stufen, deren Ausgabedatei bereits existiert und die Validierung besteht, werden automatisch als passed markiert, sodass unterbrochene Aufgaben ohne manuelle Bearbeitung von tasks.json fortgesetzt werden.

Sitzungsmodell

Jede Sitzung hat einen menschenlesbaren Namen + Pi's UUID + cwd + goal.
Der erste pi_delegate-Aufruf erstellt die Sitzung (goal erforderlich); spätere Aufrufe setzen automatisch fort.
Das Register wird in ~/.pi-subagent/registry.json gespeichert (atomarer Schreibvorgang; beim Neustart werden unterbrochene running-Datensätze zu error korrigiert).
Parallelitätslimit: 4 laufende Läufe; eine einzelne Sitzung wird nie parallel ausgeführt.
Aufgaben werden in ~/.pi-subagent/tasks.json gespeichert (atomarer Schreibvorgang; laufende Stufen werden beim Neustart zu failed(interrupted_by_restart) korrigiert).

Installation

git clone <this-repo> && cd pi-subagent
npm install

Voraussetzung: Die pi-CLI ist installiert (npm i -g @earendil-works/pi-coding-agent) und im PATH.

MCP-Host konfigurieren

Fügen Sie zu Ihrer MCP-Client-Konfiguration hinzu:

{
  "mcpServers": {
    "pi-subagent": {
      "command": "npx",
      "args": ["tsx", "/abs/path/to/pi-subagent/src/server.ts"]
    }
  }
}

Optionale Umgebungsvariablen:

PI_SUBAGENT_REGISTRY — Pfad zum Register (Standard ~/.pi-subagent/registry.json)
PI_BIN — überschreibt die pi-Ausführungsdatei (für Tests verwendet)

Test

npm test           # full suite (140 tests)
npm run test:fast  # dot reporter

Tests verwenden ein Fake-pi (test/fixtures/fake-pi.sh) und decken ab: async/sync, Timeout, Kill, Sitzungserstellungsfehler, Multi-Waiter, Fortschrittslimit, Planungsregeln (tabellengetrieben + 100-Iteration-Property-Tests), Registerpersistenz, Redaktion usw.

Projektstruktur

src/
├── types.ts                 # all shared types + error codes
├── errors.ts                # ToolError helpers
├── runner/                  # parse.ts, argv.ts, spawn.ts, process-table.ts
├── registry/                # session.ts, run.ts, persist.ts, redact.ts
├── scheduler/               # keywords.ts, plan.ts (5-stage pure function)
├── tools/                   # delegate, status, plan-tool, session, kill
└── server.ts                # MCP entry (stdio)
skills/pi-subagent/          # SKILL.md + delegation-patterns (strategy layer)
test/                        # fixtures/ + *.test.ts
docs/                        # design.md (spec) + implementation-plan.md

Design & Prozess

Dieses Projekt durchlief vor der Implementierung ein kollaboratives Design + 4 Runden externer Überprüfung. Die Spezifikation und der Plan sind unter docs/ eingecheckt:

docs/design.md — vollständige Design-Spezifikation (Architektur, Tool-Verträge, Fehlerbehandlung, Planungsregeln, Teststrategie). Jeder Vertrag ist auf eine Review-Notiz (R1–R4) zurückführbar.
docs/implementation-plan.md — 19 TDD-Aufgaben (fehlschlagenden Test schreiben → implementieren → bestehen → committen).

Wichtige Designentscheidungen, alle gestützt auf echte Untersuchung der pi -p-Ausgabe und externe Überprüfung:

cwd ≠ Sitzungsspeicher — spawn({ cwd }) steuert das Arbeitsverzeichnis; Pi's Sitzungsdateien verwenden ihren Standardort (verschmutzt das Projekt nicht).
Async-Standard + Handshake — neue Sitzungen warten auf Pi's session-Ereignis, bevor sie zurückkehren (mit einem sessionStartTimeoutMs), sodass der Host immer eine echte piSessionId erhält.
Mehrstufen-Planer — plan() ist reject → capacity → reuse → modify → mode, wobei Modifikatoren stapeln statt zuerst zu treffen (eine Lektion aus Runde 1 der Überprüfung).
Fortschritts-Redaktion — Tool-Ergebnisse werden gekürzt und von Tokens/Schlüsseln bereinigt, bevor sie gespeichert werden.

Status

Funktionierende Implementierung, 140 bestandene Tests. Noch nicht auf npm veröffentlicht — aus dem Quellcode über tsx ausführen.

Lizenz

MIT

Available Tools

7 tools

pi_delegateC

委派任务给 Pi 子代理（默认 async）

Name	Required	Description	Default
`cwd`	No
`goal`	No
`mode`	No
`prompt`	Yes
`session`	Yes
`constraints`	No
`runTimeoutMs`	No
`allowUnknownTools`	No

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits but only mentions 'default async'. It does not explain side effects, how results are returned, or whether the tool is idempotent. Critical details are missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, but it is overly terse for a tool with 8 parameters. While front-loaded, it lacks structure and does not fully utilize the space to convey necessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (8 parameters, nested objects, no output schema, no annotations), the description is severely incomplete. It fails to cover usage patterns, return values, or async/sync behavior beyond the default.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain any of the 8 parameters, not even the required 'prompt' and 'session'. The enum for 'mode' is mentioned only implicitly as 'default async' but no details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool delegates tasks to a Pi sub-agent with a default async mode. However, it does not differentiate from sibling tools like pi_plan or pi_session_fork, which could have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor are there any preconditions or exclusions mentioned. The description is too brief to inform decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

pi_killC

中止 run

Name	Required	Description	Default
`runId`	Yes

TDQS

C2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must fully disclose behavior, but it only states '中止 run' without detailing side effects, reversibility, or required permissions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely short but at the expense of clarity; it fails to provide necessary information, making it underspecified rather than appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A kill operation with one parameter is simple, but the description omits return values, error cases, and prerequisites, rendering it incomplete for reliable agent invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter 'runId' has no description in the schema or in the text, leaving its purpose and format entirely unspecified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description '中止 run' conveys the action (abort) and resource (run), but is in Chinese and does not differentiate from siblings like pi_delegate or pi_plan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance provided on when to use this tool versus alternatives, nor any context about prerequisites or typical scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

pi_planC

调度决策：该不该委派、sync/async、开几个 session

Name	Required	Description	Default
`cwd`	Yes
`task`	Yes
`fanout`	No
`estComplexity`	No
`preferredMode`	No

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; the description does not disclose side effects, authorization needs, or whether the tool is read-only or modifies state. The term '决策' implies decision-making but no details on consequences.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise (one line). It is front-loaded with the core idea, but at the cost of missing important details. It could be slightly expanded without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters, no output schema, and no annotations, the description is insufficient. It does not explain return values, parameter usage, or behavioral traits, making it hard for an agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

0% schema description coverage; the description does not explain parameter semantics beyond their names (e.g., fanout, estComplexity). Field names give some clues but are insufficient for proper invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description '调度决策：该不该委派、sync/async、开几个 session' indicates it is for scheduling decisions, but it is vague. It mentions delegation and session management, aligning with sibling tools like pi_delegate and pi_session_fork, but does not clearly state the tool's specific action or output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description does not mention prerequisites, when to delegate or not, or how this relates to other tools like pi_delegate or pi_session_fork.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

pi_session_forkD

派生 session

Name	Required	Description	Default
`to`	Yes
`from`	Yes

TDQS

D1.5/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description is too minimal to disclose behavioral traits like destructiveness, permissions, or lifecycle impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely brief but at the expense of completeness. Not a model of efficiency; it omits essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with two required parameters and no output schema or annotations, the description provides zero contextual completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%; description fails to explain what 'from' and 'to' represent, leaving all parameters underspecified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description is a single Japanese phrase '派生 session' meaning 'fork session'. It suggests duplication but lacks a clear verb-resource structure or differentiation from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to fork vs using siblings like pi_session_list or pi_session_snapshot. No context provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

pi_session_listA

列 session（不传 cwd 取全量，供 pi_plan 用）

Name	Required	Description	Default
`cwd`	No

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full transparency burden. It implies a read-only operation ('list') and explains cwd filtering behavior, but does not disclose potential side effects, auth requirements, or other safety guarantees. Adequate but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the action, and contains no superfluous information. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one optional param, no output schema), the description covers purpose, parameter behavior, and intended usage context. It does not explain return format, but for a list operation this is acceptable. Slightly more detail would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains that omitting cwd returns all sessions, adding meaningful semantics beyond the bare schema. This provides sufficient guidance for a single optional parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'list' and resource 'session', with additional detail on behavior when cwd is omitted. It also specifies use for pi_plan, distinguishing it from sibling tools like pi_session_fork or pi_session_snapshot.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on when to use the tool (for pi_plan) and the effect of omitting cwd. It does not explicitly state when not to use it or mention alternatives, but the guidance is clear enough for an AI agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

pi_session_snapshotC

取 session 详情

Name	Required	Description	Default
`session`	Yes

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. The description implies a read operation but does not explicitly state it is non-destructive or disclose any behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise but under-specified. A single phrase with no additional structure or front-loading of key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity (1 param, no nested objects, no output schema), the description is incomplete. No information on return value, behavior, or context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%. The parameter 'session' lacks any description in both schema and tool description, leaving its meaning ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description '取 session 详情' clearly indicates fetching session details. It distinguishes from siblings like pi_session_list (listing) and pi_session_fork (forking) but does not specify the snapshot aspect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus siblings. No context on prerequisites or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

pi_statusC

取 run 结果（long-poll）

Name	Required	Description	Default
`runId`	Yes
`waitTimeoutMs`	No

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions 'long-poll' implying blocking behavior, but does not disclose idempotency, destructiveness, authentication needs, or error handling. The transparency is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short (one phrase), which is concise but lacks structure. It front-loads the core purpose but does not provide enough detail to be fully helpful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has two parameters and no output schema, the description is insufficient. It omits details on return format, long-poll behavior nuances, timeout semantics, and relationship to sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explain any parameters. 'runId' and 'waitTimeoutMs' remain undocumented in meaning. The description adds no value beyond the schema's structural definition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb '取' (get) and resource 'run result' with 'long-poll' qualifier. However, it does not distinguish this tool from siblings like pi_kill or pi_plan, which are distinct actions but no explicit differentiation is provided.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. It does not mention prerequisites, context, or conditions for use. The description is purely functional.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

7 tool updatesv0.1.0Jul 1, 2026
- First observedpi_delegate
- First observedpi_kill
- First observedpi_plan
- First observedpi_session_fork
- First observedpi_session_list
- First observedpi_session_snapshot
- First observedpi_status

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.8/5.0

Scored 2026-07-01 07:25 across 7 tools

Disambiguation5/5

Each tool targets a distinct operation: delegation, kill, planning, session management, and status. No overlap in purpose.

Naming Consistency4/5

All tools share the 'pi_' prefix, but the structure varies: some are verbs (pi_delegate, pi_kill), others are noun_verb (pi_session_fork). Overall readable and consistent prefix helps.

Tool Count5/5

7 tools is appropriate for a subagent manager covering delegation, planning, session lifecycle, and status retrieval.

Completeness4/5

Core operations are covered, though missing explicit session creation or update tools. Forking may serve creation, and kill provides termination.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

Related MCP Connectors

ReasonOAuth
io.github.reason-machines
Start and manage Reason cloud coding agents, projects and sessions from any MCP client.
Coding Agents Agent Orchestration Autonomous Agents
1
https://mcp.reasonmachines.com/mcp
Node CommandOAuth
io.github.huseyincig
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.
File Systems Shell Access Browser Automation
1
https://mcp.nodecommand.app/mcp
Roamer MCPOAuth
com.mathismeadows
Hosted MCP server and Agent Skills for specs, engineering threads, and project memory.
Agent Orchestration Developer Tools Project Management
1
https://roamer-mcp.mathismeadows.com/mcp
AI.TV MCP ServerOAuth
tv.ai
Remote MCP server for AI.TV creators — delegate account operations to your AI agent over MCP.
Entertainment & Media AI & Machine Learning
2
https://api.ai.tv/mcp

Related MCP Servers

pokeclaw
Coding Agents Code Execution Command Line
madebydia
A
license
Not graded
quality
D
maintenance
Enables MCP clients to spawn and control Codex CLI and Claude Code sessions on the host machine, with session management and filesystem access.
Updated 5 months ago (2026-06-08 12:59 UTC)
4
MIT
pi-delegate-mcp
Coding Agents Code Analysis Autonomous Agents
sotola122
A
license
Not graded
quality
B
maintenance
Delegates bounded coding tasks from MCP clients to the Pi Coding Agent over stdio. Supports review, verification, implementation, and batch operations with long-running task polling.
Updated 2 months ago (2026-08-19 02:08 UTC)
MIT
pi-agent-mcp
Coding Agents Agent Orchestration Autonomous Agents
a809384377
F
license
Not graded
quality
B
maintenance
Enables MCP hosts like Claude Code and Codex to spawn, manage, and interact with persistent, reusable Pi coding-agent sessions, supporting task dispatch, status checks, and session lifecycle control.
Updated 2 months ago (2026-08-22 06:12 UTC)
2 npm
-
agentmux
Autonomous Agents Agent Orchestration Developer Tools
seaweedsoup98
A
license
B
quality
B
maintenance
Enables any MCP host to delegate work to multiple coding-agent CLIs such as Codex, Claude Code, and Antigravity as subagents, preserving native sessions and supporting team-based supervision and agent-to-agent messaging.
Updated a month ago (2026-09-22 04:11 UTC)
17
13 npm
Apache 2.0