uipath-orchestrator-mcp-python

MCP日程管理

提供方 Mo3bdlaa

日程管理 stdio · 本地进程 OAuth 授权 社区 / 第三方 Claude DesktopClaudeCline
查看接入方式

An MCP server that exposes UiPath Orchestrator as agent tools, letting AI assistants manage automation jobs, queues, assets, schedules, robots, and audit logs via natural language across cloud, on-prem, and sovereign deployments.

一句话选型结论

按资料字段整理

uipath-orchestrator-mcp-python 属于日程管理类 MCP 服务器,stdio · 本地进程,OAuth 授权,可直接接入 Claude Desktop、Claude、Cline,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类日程管理 传输方式stdio · 本地进程 鉴权OAuth 授权 部署方式本地部署
GitHub 星标 1 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

日程管理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

Local Deployment MCP Server UiPath Orchestrator Python RPA Orchestration AI Agent Integration Robot Management Audit & Monitoring

支持客户端

适用场景

Local DeploymentMCP ServerUiPath Orchestrator

安装与配置

stdio · 本地进程 OAuth 授权
客户端在本机拉起子进程,数据不出本机
python -m uipath_mcp_python.server

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 python,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
日程安排

按空闲时间自动排日程。

提醒与待办

设提醒、管待办清单。

时间协调

在多人之间找共同空档。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cline,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好OAuth 授权对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在日程管理场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
uipath-orchestrator-mcp-python当前 未标注 stdio · 本地进程 本地部署 有 2026-06-01
Todoist MCP Server 79e800d2 35 stdio · 本地进程 支持远程部署 有 2026-05-17
Outlook Calendar MCP 7 stdio · 本地进程 本地部署 有 2026-05-18
MCP Server Apple Events 5 stdio · 本地进程 本地部署 有 2026-05-17
y-cli 未标注 stdio · 本地进程 本地部署 无 2026-10-05
Google Calendar 未标注 HTTP · 远程 支持远程部署 有 2026-05-17

服务器档案

日程管理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Mo3bdlaa上游标注的维护方 Mo3bdlaa
分类日程管理本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式OAuth 授权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · python本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-06-01上游最后核验时间

详细介绍

9.9 KB
来自项目仓库与上游目录的原文,未做删改

uipath-orchestrator-mcp-python

> Python MCP server for UiPath Orchestrator — drive your automations from Claude Desktop and any MCP-aware agent.

What is this?

A Model Context Protocol server that exposes your
UiPath Orchestrator as a set of agent tools. Point Claude Desktop (or Cline, Continue,
or a custom agent) at it and ask, in plain language, to start jobs, inspect failures,
manage queues, and read audit logs — across Cloud, on-prem, and PAT deployments.

It's a typed async Python client (25 tools, Pydantic models, three production auth
strategies) wrapped as a native MCP server — not a REST wrapper, not a bespoke
integration.

Why does it exist?

REST APIs aren't MCP servers — an agent can't discover or call them without glue code.
And the MCP servers that do exist don't cover UiPath Orchestrator, especially on-prem
and sovereign deployments
where most examples stop at SaaS. This fills that gap:
production auth coverage (Cloud OAuth · On-prem · PAT) behind a single MCP surface.

What you can ask the agent

Once it's connected, these are the kinds of prompts you can send:

  • "Schedule the Invoice Processing job to run weekdays at 9 AM in the Finance folder."
  • "List all jobs that failed in the last 24 hours, grouped by process, with the error message for the most common failure."
  • "How many items are pending in the OnboardingEmployees queue, and which robots are configured to process it?"
  • "Run a one-time execution of the Reconciliation process in the AsiaTenant, then notify me when it finishes."
  • "Pull yesterday's audit log entries for any folder permission changes."
  • "Show me the assets defined in the HR folder that look like credentials (don't print their values)."
  • "Give me a health snapshot of the Production folder — job states, queue backlogs, robot availability."

Install (Claude Desktop)

1. Clone and install:```bash
git clone https://github.com/Mo3bdlaa/uipath-orchestrator-mcp-python.git
cd uipath-orchestrator-mcp-python
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e .


**2. Add to your `claude_desktop_config.json`:**```json
{
  "mcpServers": {
    "uipath-orchestrator": {
      "command": "python",
      "args": ["-m", "uipath_mcp_python.server"],
      "env": {
        "UIPATH_URL": "https://cloud.uipath.com/your-org/your-tenant/",
        "UIPATH_AUTH_TYPE": "cloud-oauth",
        "UIPATH_CLIENT_ID": "...",
        "UIPATH_CLIENT_SECRET": "...",
        "UIPATH_TENANT_NAME": "Default"
      }
    }
  }
}

Use the absolute path to your virtualenv's interpreter for command (e.g.
/path/to/uipath-orchestrator-mcp-python/.venv/bin/python) so Claude Desktop launches
the server with the dependencies installed. After pip install -e . you can also use
the uipath-mcp console script instead of python -m uipath_mcp_python.server.

Config file location:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json

Restart Claude Desktop and the uipath-orchestrator tools appear in the 🔌 menu.

Configure auth

Pick the one strategy that matches your deployment. All strategies also need
UIPATH_URL and UIPATH_TENANT_NAME.

Use case UIPATH_AUTH_TYPE Required variables
Cloud (SaaS Orchestrator) cloud-oauth UIPATH_CLIENT_ID, UIPATH_CLIENT_SECRET
On-prem (regulated / sovereign) on-prem UIPATH_USERNAME, UIPATH_PASSWORD
Personal scripts / quick prototyping cloud-pat UIPATH_PAT

On-prem is the deployment most MCP/UiPath examples never cover — and it's the one
that matters for regulated and sovereign environments. It's a first-class strategy here,
not an afterthought.

For local development, copy .env.example → .env and fill in the values instead of
using the env block above.

Tools exposed

The server exposes 25 tools, grouped by Orchestrator domain:

Folders & Infrastructure

Tool Description
list_folders Return Orchestrator folders (organizational units) with pagination.
list_robots Return robots registered in the Orchestrator, optionally scoped to a folder.
list_machines Return host machines known to the Orchestrator.
list_sessions List active robot sessions — which machines are connected and their state.
aggregate_session_states Count robots grouped by connection state (Available, Busy, Disconnected …).
count_entities Total counts of top-level entities (processes, assets, queues, schedules).

Assets

Tool Description
list_assets List assets (credentials, config values) stored in a folder.
get_robot_asset Retrieve a specific asset value that has been assigned to a robot.

Processes & Jobs

Tool Description
list_releases List published process releases, optionally filtered by key.
query_jobs Search for jobs with optional state and process name filters.
inspect_job Retrieve full details for a single job by its numeric ID.
start_process Trigger execution of a published process by name.
cancel_job Request graceful stop (or forced kill) of a running job.

Queues

Tool Description
list_queues List every queue definition in the Orchestrator.
enqueue_item Push a new item into a named queue for robot processing.
query_queue_items Search queue items with optional filters on queue ID and status.

Schedules

Tool Description
list_schedules List scheduled triggers (cron expressions, next run times).

Logs & Audit

Tool Description
query_robot_logs Retrieve robot execution logs with optional filtering.
query_audit_trail Search the audit trail — who changed what and when.

Analytics

Tool Description
get_job_metrics Aggregate job counts by state and compute the overall success rate.
get_queue_metrics Compute per-status breakdown and success rate for a queue.
get_faulted_jobs Fetch recent faulted jobs for failure analysis.
analyze_process Compute success rate and execution statistics for a process.
summarize_folder Build a health snapshot of a folder: job states, queue/robot counts.
get_dashboard High-level dashboard with aggregated metrics.

> The descriptions above mirror the tool docstrings in
> uipath_mcp_python/server.py — that file is the
> source of truth as tools change.
>
> Tools are annotated with MCP hints (readOnlyHint / destructiveHint) so an
> agent host can tell safe reads from state changes. Only start_process,
> enqueue_item, and cancel_job mutate Orchestrator state.

Uniform list responses. Every list/query tool returns the same envelope, so
an agent never has to guess the shape:```json
{ "items": [ / rows / ], "count": 2, "total": 57 }


`count` is the size of the returned page; `total` is the server-side total when
the OData endpoint reports one (otherwise `null`).

## Resources (read-only endpoints)

| URI | Description |
|---|---|
| `orchestrator://folders` | All folders |
| `orchestrator://robots` | All robots |
| `orchestrator://machines` | All machines |
| `orchestrator://queues` | Queue definitions |
| `orchestrator://jobs/recent` | Last 20 jobs |
| `orchestrator://releases` | Published processes |
| `orchestrator://dashboard` | Dashboard metrics |
| `orchestrator://sessions` | Active sessions |
| `orchestrator://assets` | Stored assets |
| `orchestrator://schedules` | Configured schedules |

### Parameterised resource templates

| URI template | Description |
|---|---|
| `orchestrator://folders/{folder_id}/summary` | Robots, queues, releases & job metrics for one folder |
| `orchestrator://queues/{queue_name}/metrics` | Live item-status breakdown & success rate for a queue |

## Reliability & transport

The client is built for unattended agent use:

- **Token refresh** is serialised behind a lock and reused with a 5-minute
  buffer, so concurrent tool calls trigger a single handshake. A `401` triggers
  one transparent refresh-and-retry.
- **Transient failures** — both HTTP `429`/`5xx` responses and transport-level
  errors (connection resets, read/connect timeouts) — are retried with
  exponential backoff and jitter, honouring the `Retry-After` header when present.
- **Timeouts and a bounded connection pool** are configured on the HTTP client;
  error bodies are trimmed before surfacing as a typed `OrchestratorError`.
- **Observability:** retries, token refreshes, and give-ups are logged through
  the `uipath_mcp_python` logger (silent by default — attach a handler / set a
  level in your host app to see them).

Optional tuning via environment variables:

| Variable | Default | Description |
|---|---|---|
| `UIPATH_REQUEST_TIMEOUT` | `30` | Per-request timeout (seconds) |
| `UIPATH_MAX_CONNECTIONS` | `20` | Max simultaneous HTTP connections |
| `UIPATH_FOLDER_ID` | — | Default Organizational Unit ID |
| `UIPATH_DISABLE_SSL_VERIFY` | `0` | Set `1` to skip TLS verification (on-prem self-signed) |

## Project structure```
uipath_mcp_python/
├── schemas.py        # Pydantic models for every Orchestrator entity
├── orchestrator.py   # Async API client with 3 auth strategies
├── settings.py       # Environment-to-config loader
└── server.py         # MCP tool & resource definitions

See examples/ for worked agent interactions, including a multi-step
list-then-schedule flow and an on-prem deployment.

Development```bash

pip install -e ".[dev]"
pytest # unit tests — no live Orchestrator required
ruff check uipath_mcp_python/ tests/
mypy # static type check (config in pyproject.toml)
```

The package ships a py.typed marker, so
downstream projects get full type information when importing
uipath_mcp_python.

License

MIT — free to use, modify, and distribute.


Built by Mohammed Shaker

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
uipath-orchestrator-mcp-python 怎么安装?

在客户端按下面的安装命令接入:python -m uipath_mcp_python.server。装完在客户端配置里引用同一个包或端点。

uipath-orchestrator-mcp-python 怎么在 Claude Desktop、Claude、Cline 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

uipath-orchestrator-mcp-python 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

uipath-orchestrator-mcp-python 需要 API Key 吗?

资料标注需要OAuth 授权认证,使用前准备好对应凭据,并按最小权限配置。

uipath-orchestrator-mcp-python 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cline;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

uipath-orchestrator-mcp-python 能提供哪些能力?

资料显示能力标签包括 Local Deployment、MCP Server、UiPath Orchestrator、Python、RPA Orchestration、AI Agent Integration。具体工具清单以官方文档为准。

uipath-orchestrator-mcp-python 需要什么运行环境?

运行时为 python;属于本地进程,需要在本机装好运行环境。

uipath-orchestrator-mcp-python 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-06-01。