Planfix MCP Server
Enables integration with Planfix CRM and task management system, allowing lead management, contact/company management, task creation/search/commenting, and report generation via the Planfix REST API v2.0.
README
Planfix MCP Server
This MCP server provides integration with the Planfix API, allowing Model Context Protocol (MCP) clients to interact with Planfix CRM and task management system.
Features
- Lead management (create, search, convert to tasks)
- Lead searches can reuse a known
clientIdto skip contact lookups - Contact and company management
- Task management (create, search, comment)
- Report generation and management
- Uses Planfix REST API v2.0 (API docs)
- Authentication via Bearer token
Configuration
The server requires the following environment variables for Planfix API access:
PLANFIX_ACCOUNT– Your Planfix account name (e.g.,yourcompany)PLANFIX_TOKEN– Planfix API token with necessary permissionsPLANFIX_BASE_URL– (optional) Override the REST API base URL. Defaults tohttps://<PLANFIX_ACCOUNT>.planfix.com/rest/. Set this for.ruand other regional installations, e.g.https://yourcompany.planfix.ru/rest/PLANFIX_ACCOUNT_URL– (optional) Override the web origin used for human-facing links (task/contact/user pages). Defaults toPLANFIX_BASE_URLwithout the trailing/rest/PLANFIX_FIELD_ID_EMAIL– Custom field ID for emailPLANFIX_FIELD_ID_PHONE– Custom field ID for phonePLANFIX_FIELD_ID_TELEGRAM– Set any value to use the system Telegram fieldPLANFIX_FIELD_ID_TELEGRAM_CUSTOM– Custom field ID for Telegram when using the custom fieldPLANFIX_FIELD_ID_CLIENT– Custom field ID for clientPLANFIX_FIELD_ID_MANAGER– Custom field ID for managerPLANFIX_FIELD_ID_AGENCY– Custom field ID for agencyPLANFIX_FIELD_ID_LEAD_SOURCE– Custom field ID for lead sourcePLANFIX_FIELD_ID_LEAD_SOURCE_VALUE– Value ID for default lead sourcePLANFIX_FIELD_ID_PIPELINE– Custom field ID for pipelinePLANFIX_FIELD_ID_TAGS– Custom field ID for task tags- Missing tag names will be added automatically to the directory
PLANFIX_FIELD_ID_LEAD_ID– Custom field ID for external lead IDPLANFIX_LEAD_TEMPLATE_ID– ID of the lead task templatePLANFIX_TASK_TITLE_TEMPLATE– Template for the default lead task title (e.g.,{name} - client's task)
config.yml
Custom fields can also be configured via config.yml. The default path is
./data/config.yml. Override it with the --config=/abs/path/config.yml CLI
flag or the PLANFIX_CONFIG environment variable. You can also specify a
different Planfix account when using a custom config:
PLANFIX_CONFIG=/etc/planfix-mcp.yml PLANFIX_ACCOUNT=demo \
npx @popstas/planfix-mcp-server
proxyUrl: "http://localhost:8080"
webhook:
enabled: false
url: "https://example.com/hook"
token: "<token>"
skipPlanfixApi: false
leadTaskFields:
- id: "456"
name: "id сделки"
argName: lead_id
type: number
contactFields:
- id: "123"
name: "Резидентство"
argName: resident
type: enum
values: ["резидент", "нерезидент", "иное"]
userFields:
- id: "789"
name: "Департамент"
argName: department
type: string
proxyUrl routes all Planfix REST API calls (including tool requests) through
the specified HTTP proxy.
Values from config.yml override matching entries from the legacy environment
variables when merged by id. User custom fields from this list are requested
individually by the planfix_search_manager tool so their values are available
in responses. Managers can be searched either by email or by numeric id
through this tool, enabling lookups when only an identifier is available.
Chat API
To create tasks from chat messages, add a chatApi block to config.yml:
chatApi:
useChatApi: true
chatApiToken: "<token>"
providerId: "<id>"
baseUrl: "https://<account>.planfix.com/webchat/api"
chatApiToken– token for Planfix Chat API requests.providerId– identifier of the chat provider configured in Planfix.useChatApi– enable Chat API integration. Whentrue, task creation proceeds as:- A chat is created via Chat API with the initial message.
getTaskretrieves the new task'staskId.- Subsequent updates are made through the REST API.
baseUrl– base URL for Chat API calls. Defaults tohttps://<account>.planfix.com/webchat/api.
Webhook
To post lead task payloads to a webhook before creating or updating a task,
add a webhook block to config.yml:
webhook:
enabled: true
url: "https://example.com/hook"
token: "<token>"
skipPlanfixApi: false
enabled– whether to send the lead task payload to the webhook URL.url– webhook endpoint URL.token– shared secret appended to the JSON payload astoken.skipPlanfixApi– whentrue, the webhook response must includetaskId, and the Planfix REST API call is skipped.
Debug
npx @modelcontextprotocol/inspector node d:/projects/expertizeme/planfix-mcp-server/dist/index.js
Logging
Set LOG_LEVEL=debug to enable detailed cache logs. Logs are written to data/mcp.log.
Clearing Cache
Run npm run cache-clear to remove all cached Planfix API responses stored in data/planfix-cache.sqlite3 and delete the objects cache file data/planfix-cache.yml.
Example MCP Config (NPX)
{
"mcpServers": {
"planfix": {
"command": "npx",
"args": [
"-y",
"@popstas/planfix-mcp-server"
],
"env": {
"PLANFIX_ACCOUNT": "yourcompany",
"PLANFIX_TOKEN": "your-api-token",
"PLANFIX_FIELD_ID_EMAIL": "123",
"PLANFIX_FIELD_ID_PHONE": "124",
"PLANFIX_FIELD_ID_TELEGRAM": "1",
"PLANFIX_FIELD_ID_TELEGRAM_CUSTOM": "125",
"PLANFIX_FIELD_ID_CLIENT": "126",
"PLANFIX_FIELD_ID_MANAGER": "127",
"PLANFIX_FIELD_ID_AGENCY": "128",
"PLANFIX_FIELD_ID_TAGS": "129",
"PLANFIX_FIELD_ID_LEAD_ID": "130",
"PLANFIX_LEAD_TEMPLATE_ID": "42",
"PLANFIX_TASK_TITLE_TEMPLATE": "{name} - работа с клиентом"
}
}
}
}
Usage
Running the Server
Run the server with the required environment variables set. Example (with npx):
PLANFIX_ACCOUNT=yourcompany \
PLANFIX_TOKEN=your-api-token \
PLANFIX_FIELD_ID_EMAIL=123 \
PLANFIX_FIELD_ID_PHONE=124 \
PLANFIX_FIELD_ID_TELEGRAM=1 \
PLANFIX_FIELD_ID_TELEGRAM_CUSTOM=125 \
PLANFIX_FIELD_ID_CLIENT=126 \
PLANFIX_FIELD_ID_MANAGER=127 \
PLANFIX_FIELD_ID_AGENCY=128 \
PLANFIX_FIELD_ID_LEAD_SOURCE=129 \
PLANFIX_FIELD_ID_LEAD_SOURCE_VALUE=130 \
PLANFIX_FIELD_ID_PIPELINE=131 \
PLANFIX_FIELD_ID_LEAD_ID=132 \
PLANFIX_FIELD_ID_TAGS=133 \
PLANFIX_LEAD_TEMPLATE_ID=42 \
PLANFIX_TASK_TITLE_TEMPLATE="{name} - работа с клиентом" \
npx @popstas/planfix-mcp-server
To run the server over Server-Sent Events (SSE), use the planfix-mcp-server-sse command:
PLANFIX_ACCOUNT=yourcompany \
PLANFIX_TOKEN=your-api-token \
planfix-mcp-server-sse
Using the Planfix Client
The Planfix client provides a convenient way to interact with the Planfix API directly from the command line.
Prerequisites
Make sure you have the following environment variables set in your .env file:
PLANFIX_ACCOUNT=your-account
PLANFIX_TOKEN=your-api-token
Basic Commands
-
Test the connection
npm run planfix test -
Make a GET request
npm run planfix get user/current -
Make a POST request with data
npm run planfix post task/ --data '{"name":"Test Task","description":"Test Description"}' -
Search for objects
npm run planfix post object/list --data '{"filters":[{"type":1,"operator":"equal","value":"Продажа"}]}'
Tool Reference
planfix_create_sell_task
- Creates a sell task using textual information about the agency and employee.
- Resolves the client, parent lead task, assignees, and agency IDs automatically based on the provided strings.
- Input fields (all strings):
name: Task title, e.g."Продажа {{ название товара }} на pressfinity.com".agency: Agency/company name (optional).email: Employee email used to locate the Planfix contact.contactName/employeeName: Employee full name (optional).telegram: Employee telegram username (optional).description: Description with the list of ordered products.project: Project name to associate with the sell task (optional).
- Returns
{ taskId, url }.
planfix_create_sell_task_ids
- Creates a sell task when Planfix identifiers are already known.
- Requires numeric
clientIdand optionalleadTaskId,agencyId, andassignees(user IDs). - Accepts
name,description, and optionalprojectstring values.
-
Update an object (PUT request)
npm run planfix put task/123 --data '{"name":"Updated Task Name"}' -
Delete an object
npm run planfix delete task/123
Using in Code
import { planfixClient } from './lib/planfix-client';
// Get current user
const user = await planfixClient.get('user/current');
// Create a new task
const newTask = await planfixClient.post('task/', {
name: 'New Task',
description: 'Task description',
// ... other task properties
});
// Search for objects
const objects = await planfixClient.post('object/list', {
filters: [
{
type: 1,
operator: 'equal',
value: 'Продажа'
}
]
});
Available Tools
Lead Management
leadToTask: Convert a lead to a task by creating/updating contact and tasksearchLeadTask: Search for lead tasks by contact information
Contact Management
searchPlanfixContact: Search contacts by name, phone, email, or TelegramcreatePlanfixContact: Create a new contact in PlanfixupdatePlanfixContact: Update existing contact informationsearchPlanfixCompany: Search for companies by name
Task Management
searchPlanfixTask: Search for tasks by title, client ID and optionaltemplateIdcreateSellTask: Resolve contact/agency IDs and create a sell taskcreateSellTaskIds: Create a sell task when IDs are already knowncreateLeadTask: Create a new lead task. WhenchatApi.useChatApiis enabled, it sends the initial message through the Chat API, gets the resultingtaskIdviagetTask, and then updates the task using the REST API. AcceptsmessageandcontactNamefields.addToLeadTask: Create or update a lead task and update contact details. Whenwebhook.enabledis true, it posts the input payload to the webhook endpoint, optionally skipping the Planfix API ifskipPlanfixApiis set.createTask: Create a task using text fieldscreateComment: Add a comment to a taskgetChildTasks: Retrieve child tasks of a parent task. Userecursiveto fetch all descendant tasks as a flat list; returned tasks includeparent_task_id.updateLeadTask: Update an existing lead task (only empty fields are updated unlessforceUpdateis true)
Directory Management
planfix_search_directory: Search directories by nameplanfix_search_directory_entry: Search directory entry by directory name and entry name
User Management
searchManager: Find a manager by email
Reporting
listReports: List all available reportsrunReport: Generate and retrieve a specific report
References
TODO:
- Add tool
getTaskto retrieve task details - Add tool
getContactto retrieve contact details - Add tool
getManagerto retrieve manager details - Add more comprehensive error handling and logging
- Add input validation for all API endpoints
- Add rate limiting and retry logic for API calls
MIT License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。