de en es ja ko ru zh

mcp-delegate

Name: mcp-delegate
Author: hessenpepper

by hessenpepper

Overview Schema Source Related Servers Discussions Admin

Python

Local

mcp-delegate

Ein MCP-Server, der Claude Code (als Orchestrator) ein Tool gibt, um eine Aufgabe an eine separate, vollwertige agentische Schleife zu delegieren, die auf einem anderen Modell läuft (lokal per Ollama oder remote per OpenRouter), mit eigenem Tool-Zugriff (Dateien, Bash usw.) und das Ergebnis am Ende zurückgibt – funktional äquivalent zu einem nativen Subagenten, aber modellunabhängig.

Siehe mcp-subagent-delegation-plan.md für den vollständigen Build-Plan, aufgeteilt in separate Commits/Checkpoints.

Status

Phase 1, 2, 3 and 4 abgeschlossen.

delegate_task – einmalige Chat-Completion gegen einen konfigurierten OpenAI-kompatiblen Endpunkt (Ollama, LM Studio, vLLM, OpenRouter, ...).
delegate_agentic_task – gibt dem delegierten Modell eine eigene Tool-Schleife (read_file, write_file, run_bash), die auf ein vom Aufrufer angegebenes Arbeitsverzeichnis beschränkt ist und läuft, bis es keine Tools mehr aufruft, max_iterations erreicht oder timeout_seconds überschreitet.
list_recent_delegations – zeigt an, was früher ausgeführte Delegationen (mit einem der beiden Tools) tatsächlich getan haben, ohne in Logs zu stöbern oder irgendetwas erneut auszuführen.
get_delegation_transcript – vollständiges Nachrichten-/Tool-Aufruf-Transkript für eine einzelne Delegation, wenn sie mit capture_transcript=True ausgeführt wurde (z. B. für Modellvergleichs-/Evaluierungs-Läufe).

Abweichung vom ursprünglichen Plan: Phase 2 sah vor, agent-loop als Subprozess zu kapseln. agent-loop unterstützt nur Linux/macOS/WSL, und dieser Server muss auf Windows nativ laufen. Deshalb haben wir die In-Process-Schleife gebaut, die in der Alternative von Phase 3 beschrieben wurde – gleiche Tool-Schnittstelle, keine Subprozess-/ANSI-Bereinigungs-Komplexität, und sie umgeht die AGPL-/Nicht-Kommerzielle-Lizenz von agent-loop komplett. Siehe delegate/agentic.py.

Sicherheitshinweis: working_dir ist vom Aufrufer vorgegeben, keine feste Sandbox – das delegierte Modell erhält unbeobachteten Datei-/Bash-Zugriff auf das Verzeichnis, auf das es zeigt. Datei-Tools (read_file/write_file) sind so eingeschränkt, dass sie innerhalb von working_dir bleiben; run_bash läuft mit diesen Verzeichnis als cwd, aber Shell-Befehle sind nicht vollständig sandboxed und können es verlassen (z. B. mit cd ..). Richte es auf ein Verzeichnis, in dem du damit okay bist, dass ein unbeaufsichtigtes Modell darin lesen, schreiben und Befehle ausführen kann.

Guardrail-Hinweis: Phase 4 des ursprünglichen Plans verlangte zu bestätigen, dass die eigenen Guardrails von agent-loop (Iterationslimit, Wiederholungserkennung) aktiv sind. Da wir agent-loop nicht verwenden, trifft das nicht direkt zu – unsere Schleife hat eigene max_iterations- und timeout_seconds-Grenzen (in Tests bestätigt), aber keine Wiederholungserkennung. Ein Modell, das zwischen zwei Tool-Aufrufen hängen bleibt, läuft bis zum max_iterations-Limit, statt frühzeitig erkannt zu werden. Es lohnt sich, das hinzuzufügen, falls das tatsächlich vorkommt.

Related MCP server: deepseek-subagent-mcp

Einrichtung

uv sync
cp .env.example .env             # fill in DELEGATE_BASE_URL / DELEGATE_API_KEY / DELEGATE_MODEL
cp models.json.example models.json   # optional: named backends, see below

Mehrere Backends

Beide Tools nehmen einen optionalen backend-Parameter entgegen, der base_url/model/api_key aus models.json holt, statt der Standard-Umgebungsvariablen DELEGATE_* – z. B. backend="ollama-local" für einen Aufruf und backend="openrouter-free" für einen anderen in demselben Durchgang, jeweils gleichzeitig. model überschreibt, wenn ebenfalls angegeben, nur die Modellstring innerhalb dieses Backends.

Verweise für einen Schlüssel auf eine Umgebungsvariable, statt sie direkt in models.json zu schreiben:

{
  "openrouter-free": {
    "base_url": "https://openrouter.ai/api/v1",
    "model": "nvidia/nemotron-nano-9b-v2:free",
    "api_key_env": "OPENROUTER_API_KEY"
  }
}

models.json ist gitignored, genau wie .env.

Parallelität

MCP-Tool-Aufrufe laufen bereits auf eigenen Worker-Threads, also laufen parallele Delegationen ohne extra Zusatz parallel. DELEGATE_MAX_CONCURRENCY (Standard 4, siehe .env.example) begrenzt, wie viele Delegationen – über beide Tools, egal welches Backend – gleichzeitig ausgeführt werden, um zu verhindern, dass ein großer Ausgang den lokalen Modellserver oder die Ratenlimits einer bezahlten API überlastet.

Server direkt starten (meistens nützlich, um zu prüfen, dass er ohne Fehler startet – er wartet danach auf stdio auf einen MCP-Client):

uv run server.py

Protokollierung

Jeder delegate_task-/delegate_agentic_task-Aufruf – Erfolg oder Fehler – wird in eine lokale SQLite-Datei delegations.db geloggt (gitignored, wird bei erster Verwendung angelegt): Tool, Backend, Modell, Aufgabentext, Start-/Endzeit, Iterationszahl, Erfolg/Fehler, eine gekürzte Ergebnis-/Fehler-Vorschau und Token-Nutzung, falls das Backend sie liefert. Du kannst sie über list_recent_delegations abfragen oder direkt mit sqlite3 delegations.db "select * from delegations order by id desc limit 20". Logging ist Best-Effort – ein Logging-Fehler bringt einen sonst erfolgreichen Vorgang nicht zu Fall.

Beide Tools hängen ebenfalls eine endgültige [tokens: N prompt / N completion / N total ($cost)]-Zeile an ihren sonstigen Rückgabewert an, wenn das Backend Nutzung meldet, damit der aufrufende Agent sie sofort sehen kann, ohne extra list_recent_delegations aufzurufen.

Kostenverfolgung

pricing.json bildet Modell-String → {input_per_million, output_per_million} USD-Raten ab. Wenn das aufgelöste Modell eines Aufrufs einen Eintrag hat, werden die Kosten aus dem tatsächlichen Token-Verbrauch berechnet, in delegations.db (Spalte cost_usd_) protokolliert und im [tokens: ...]-Suffix angegeben. Ein Modell ohne Eintrag protokolliert cost_usd_ = NULL – unbekannt, nicht als kostenlos angenommen – damit eine fehlender Eintrag nicht stillschweigend zu niedrige Ausgaben meldet. Lokal angehängt Modelle haben deshalb meist keinen Eintrag; wirklich kostenliche freie Modelle (z. B. OpenRouter-Modelle mit :free) erhalten einen expliziten {"input_per_million": 0, "output_per_million": 0}-Eintrag, statt weggelassen zu werden.

Anders als .env/models.json ist pricing.json kein Geheimnis oder umgebungsspezifisch, also wird es direkt committet, statt zu gitignoren. Die Preise ändern sich. Die Datei wurde bei OpenRouter's /api/v1/models am 2026-08-21 abgerufen, für Modelle, die in einem Modellvergleichs-Bake-Off, für das dieser Server erstellt wurde; ruf sie neu ab und aktualisiere sie, wenn du Modelsleistungs ändern willst.

Transkript-Erfassung (Modellvergleichs-/Eval-Läufe)

Beide Tools akzeptieren capture_transcript: bool = False. Wenn aktiviert, wird der vollständige Nachrichtenaustausch – jede Nachricht des Modells, jeder Tool-Aufruf und jedes Tool-Ergebnis, nicht nur die endgültige Antwort – protokolliert, und der Rückgabewert erhält ein Suffix [delegation_id: N]. Abholen kannst du mit mit get_delegation_transcript(delegation_id).

Das gibt es dafür, dieselbe Aufgabe durch mehrere verschiedene Modelle/Backends laufen zu lassen und nicht nur die Endgültige Antwort zu vergleichen, sondern auch wie jede Version dort hingekommen ist (Modell- bzw. `Anruf-Auswahl, fehlerhafte Tool-Aufrufe, Wiederholungen) – etwa für einen BewerVergleichswettbewerb aus, bevor man ein Modell für Produktion auswählt. Standardmäßig deaktiviert, da es zusätzlichen Logging-Overhead gibt, den man bei normaler Delegation sonst nicht benötigt.

Registrieren bei Claude Code

Eine projektspezifische .mcp.json ist bereits eingecheckt (uv run server.py). Starte Claude Code in diesem Verzeichnis neu oder führe claude mcp list aus, um zu bestätigen, dass der delegate-Server übernommen wurde, und bitte dann, delegate_task mit einem trivialen Prompt aufrufen zu lassen, um den Rundweg zu bestätigen.

Tools

delegate_task(prompt, model=None, system_prompt=None, backend=None, capture_transcript=False) -> str – einmalige Chat-Completion gegen das konfigurierte Backend.
delegate_agentic_task(task, working_dir, model=None, max_iterations=20, timeout_seconds=600, backend=None, capture_transcript=False) -> str – mehrstufige Delegation mit read_file/write_file/run_bash-Tools, eingeschränkt auf working_dir. Es gibt nur die endgültige Antwort zurück, nicht das vollständige Transkript, außer wenn capture_transcript=True ist.
list_recent_delegations(limit=20) -> list[dict] – die zuletzt protokollierten Delegationen, neueste zuerst.
get_delegation_transcript(delegation_id) -> list[dict] – vollständiges Transkript zur Delegation, die mit capture_transcript=True geloggt wurde.

delegate_task/delegate_agentic_task geben Fehler (schlechte Konfiguration, nicht erreichbarer Endpoint, Timeout, Iterationslimit) als "Error: ..."-Strings zurück, statt zu werfen, damit ein aufrufender Agent sehen kann, was passiert ist.

Available Tools

4 tools

delegate_agentic_taskA

Delegate a multi-step task to a model with its own tool-use loop (read_file, write_file, run_bash) scoped to working_dir. Runs until the model stops calling tools, hits max_iterations, or exceeds timeout_seconds. Returns only the final answer, not the full transcript.

The delegated model gets unattended file/bash access within working_dir for the duration of the call - point it at a directory you're comfortable it can read, write, and execute commands in.

Args: task: The task instruction to give the delegated model. working_dir: Directory the model's tools are scoped to. model: Override just the model string for this call. max_iterations: Stop after this many tool-call rounds. timeout_seconds: Wall-clock budget for the whole task. backend: Named backend from models.json (base_url/model/api_key) to use instead of the default DELEGATE_* env vars. model, if also given, overrides the model within that backend. capture_transcript: Log every model message and tool call/result for later retrieval via get_delegation_transcript, instead of just the final answer. Off by default; useful when comparing models (e.g. a bake-off) rather than for routine use.

ParametersJSON Schema

Name	Required	Description	Default
`task`	Yes
`model`	No
`backend`	No
`working_dir`	Yes
`max_iterations`	No
`timeout_seconds`	No
`capture_transcript`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It clearly states that the delegated model gets unattended read/write/execute access within working_dir, that only the final answer is returned, that there are termination conditions, and that transcript capture is opt-in. This is comprehensive and honest about side effects and limits.

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?

Despite being long, the description is tightly structured: a core behavior paragraph, a safety warning, then a bulleted Args list. Every sentence earns its place, and the most important info (what it does, termination, permissions) is front-loaded. No fluff or redundancy.

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

Completeness5/5

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

For a complex delegation tool with 7 parameters, no annotations, and a dangerous access profile, the description covers all critical aspects: scope, termination, access level, return value, optional transcript capture, and backend override. The existence of an output schema is acknowledged but not required to detailed since it says returns only the final answer. Nothing an agent needs to invoke it correctly is missing.

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

Parameters5/5

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

Schema coverage is 0%, so the description is the only source of parameter meaning. It explains every parameter in the Args block, including the nuanced interplay between model and backend (backend as a base_url/model/api_key bundle, and that `model` overrides within that backend). This fully compensates for the schema's lack of descriptions.

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 opens with a precise verb and resource: 'Delegate a multi-step task to a model with its own tool-use loop...'. It clearly states the operation's scope (working_dir) and distinguishes itself from tools like get_delegation_transcript by explaining that it returns only the final answer, not the full transcript. This is a specific, unambiguous definition that lets an agent know exactly what it does.

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 explains the conditions under which the delegated model stops (no more tool calls, max_iterations, timeout_seconds) and warns about unattended file/bash access. It also suggests capture_transcript for comparison scenarios, indirectly routing to get_delegation_transcript. However, it does not explicitly contrast with delegate_task or state when to choose this tool over that sibling, leaving some inference to the agent.

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

delegate_taskA

Delegate a single-shot task to a configured OpenAI-compatible model (e.g. local Ollama or OpenRouter) and return its text response verbatim.

Args: prompt: The task/question to send to the delegated model. model: Override just the model string for this call. system_prompt: Optional system prompt to steer the delegated model. backend: Named backend from models.json (base_url/model/api_key) to use instead of the default DELEGATE_* env vars. model, if also given, overrides the model within that backend. capture_transcript: Log the full message exchange for later retrieval via get_delegation_transcript. Off by default; useful when comparing models (e.g. a bake-off) rather than for routine use.

ParametersJSON Schema

Name	Required	Description	Default
`model`	No
`prompt`	Yes
`backend`	No
`system_prompt`	No
`capture_transcript`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.4/5.0

Behavior4/5

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

No annotations are present, so the description carries the behavioral burden. It discloses the side-effect of transcript capture, the verbatim return behavior, and backend/model override semantics. It does not discuss latency, cost, or authentication, but those are not critical for selecting or invoking this tool correctly.

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 organized with a front-loaded summary followed by a clear Args block. Every parameter is explained in one or two lines, and there is no redundant or filler content.

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

Completeness5/5

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

For a single-shot delegation tool, the description covers purpose, parameter semantics, backend resolution, and the return behavior. With an output schema present and sibling context available, no critical invocation detail is missing.

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

Parameters5/5

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

The schema has 0% description coverage, but the description fully documents all five parameters, including the relationship between backend and model, overriding behavior, and the opt-in nature of capture_transcript. This completely compensates for the schema gap.

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 tool 'Delegate a single-shot task to a configured OpenAI-compatible model' and 'return its text response verbatim.' The 'single-shot' qualifier distinguishes it from the sibling delegate_agentic_task, though it does not explicitly name that sibling.

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?

It gives concrete guidance on when to use capture_transcript ('when comparing models, e.g. a bake-off') and when not ('rather than for routine use'), and explains backend selection versus DELEGATE_* env vars. It does not explicitly describe when to choose delegate_task over delegate_agentic_task, but context signals and the 'single-shot' phrasing provide reasonable guidance.

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

get_delegation_transcriptA

Full message transcript (every model message and tool call/result) for one delegation, if it was run with capture_transcript=True. Get the id from list_recent_delegations. Returns an error string if no transcript was captured for that id.

Args: delegation_id: The id field from a list_recent_delegations row.

ParametersJSON Schema

Name	Required	Description	Default
`delegation_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.8/5.0

Behavior4/5

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

No annotations are provided, so the description carries the burden. It discloses the error condition for missing transcripts, which is the key behavioral nuance. It does not explicitly state read-only semantics, but that is reasonably implied for a retrieval tool.

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 concise, with two clear sentences and a brief args section. No redundant or filler content; it efficiently conveys all necessary information.

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

Completeness5/5

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

Given there is an output schema (as indicated in context), the description need not explain return formats. It covers the essential context: the source of the id, the capture condition, and error behavior. This makes it complete for a single-parameter retrieval tool.

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

Parameters5/5

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

The parameter delegation_id is explained beyond the schema: it is the id from a list_recent_delegations row. This provides actionable meaning on how to obtain the correct value, enhancing the bare integer type definition.

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 tool returns the full transcript for a delegation, using a specific verb ('get') and resource ('transcript'). It is distinct from siblings (list_recent_delegations lists, delegate_task delegates), so no ambiguity.

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

Usage Guidelines5/5

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

The description explicitly notes the precondition (capture_transcript=True), the error behavior when no transcript exists, and instructs to obtain the delegation_id from list_recent_delegations. This gives clear when-to-use guidance and differentiates it from alternatives.

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

list_recent_delegationsA

List the most recent delegate_task / delegate_agentic_task calls (backend, model, task, duration, iterations, success, token usage, USD cost if the model has a pricing.json entry, truncated result), most recent first. Answers "what did the delegated model actually do" without re-running anything.

Args: limit: Max number of records to return (default 20).

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations provided, the description carries the full behavioral disclosure burden. It discloses the read-only nature (without re-running), sorting (most recent first), truncation of results, and conditional cost reporting. It does not mention pagination or error behavior, but for a simple read-only listing tool these are minor omissions; the disclosed traits exceed typical descriptions.

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 moderately concise, listing the returned fields in a parenthetical that is useful but slightly dense. The core purpose is stated upfront, and the parameter doc is separated. It could be tightened by moving the field list to a separate line, but it remains efficient and well-organized.

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

Completeness5/5

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

The tool has one optional parameter, no annotations, and an output schema (not provided). The description covers the return semantics (fields, ordering, truncation, cost condition) and the read-only intent. Given the simplicity, nothing essential for correct invocation is missing.

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

Parameters5/5

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 for the single parameter 'limit'. It does so explicitly: 'Max number of records to return (default 20).' This adds full semantic meaning beyond the bare schema field, making the tool usable without additional inference.

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 tool lists recent delegate_task / delegate_agentic_task calls, enumerates the returned fields (backend, model, task, duration, iterations, success, token usage, USD cost, truncated result), and specifies ordering (most recent first). It also states the intended purpose—answering what a delegated model actually did—which distinguishes it from sibling tools that create delegations or fetch full transcripts.

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 implies a clear use case for inspecting prior delegations without re-running them, but it does not explicitly contrast with siblings like get_delegation_transcript or delegate_task. It lacks explicit when-not-to-use guidance, though the mention of 'without re-running anything' strongly suggests a read-only inspection context.

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.

4 tool updatesv0.1.0Aug 23, 2026
- First observeddelegate_agentic_task
- First observeddelegate_task
- First observedget_delegation_transcript
- First observedlist_recent_delegations

Deploy Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.7/5.0

Scored 2026-08-23 00:30 across 4 tools

Disambiguation5/5

Each tool has a distinct purpose: delegate_task for single-turn, delegate_agentic_task for multi-step with tool use, list_recent_delegations for querying history, and get_delegation_transcript for retrieving full logs. No overlap.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern (delegate_task, delegate_agentic_task, list_recent_delegations, get_delegation_transcript), with clear action prefixes.

Tool Count5/5

Four tools precisely cover the core delegation workflow: create a delegation (two variants), list delegations, and inspect a transcript. No unnecessary extras.

Completeness5/5

The tool set covers creating delegations, retrieving summaries, and fetching full transcripts. No update/delete is needed for delegation records, so the surface is complete for its purpose.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

AgentdaOAuth
com.myagentda
Agent-native task management: your AI agent is the interface. Delegate to anyone by email.
Project Management Agent Orchestration Communication
2
AgentSite B
io.github.figgy-ops
Task-first cross-agent collaboration for discussions, review, referrals, and reusable knowledge.
Knowledge & Memory Search
101
handoff-mcp-server A
io.github.josephibra
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Agent Orchestration Autonomous Agents
2
AgentMesh A
io.github.lugdwei
MCP delegation fallback for AI agents to discover capabilities, knowledge, tools, and collaborators.
Agent Orchestration Autonomous Agents Communication
51

Related MCP Servers

handoff-mcp
felkru
A
license
A
quality
C
maintenance
Enables Claude to delegate tasks to external coding agents (Codex or Antigravity) for independent reviews, separate quota usage, and async processing.
Updated 2 months ago (2026-07-21 18:35 UTC)
6
MIT
deepseek-subagent-mcp
Coding Agents Agent Orchestration
gaztrabisme
A
license
A
quality
B
maintenance
Enables AI coding agents like Claude Code or Codex to delegate tasks to a DeepSeek Harness subagent with its own context window, providing tools for task delegation, result waiting, continuation, and supervision with sandboxed execution.
Updated 10 days ago (2026-09-02 12:46 UTC)
6
MIT
DeepSeek Subagent MCP Server
AI & Machine Learning Agent Orchestration
kira4094
A
license
A
quality
B
maintenance
Lets MCP clients like Codex delegate independent sub-tasks to DeepSeek as a sub-agent via a single tool, with optional context, custom system prompts, and configurable model/temperature settings.
Updated 21 days ago (2026-08-23 06:55 UTC)
1
9
MIT
pi-delegate-mcp
Coding Agents Autonomous Agents
howznguyen
A
license
A
quality
B
maintenance
Enables delegating coding tasks to a pi agent as a steerable background worker, allowing mid-run redirection, follow-ups, and keeping the delegate's context isolated from your main conversation.
Updated 18 days ago (2026-08-25 19:30 UTC)
12
12
16
MIT