Build your own CUSTOM API MCP server

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

This n8n demonstrates how any organisation can quickly and easily build and offer MCP servers to their customers or internal staff to improve productivity. This MCP example uses PayCaptain.com as a...

Best for

HR automation workflows
AI RAG automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.executeworkflowtrigger, n8n-nodes-base.switch, n8n-nodes-base.stickynote, @n8n/n8n-nodes-langchain.mcptrigger, @n8n/n8n-nodes-langchain.toolworkflow, n8n-nodes-base.httprequest, n8n-nodes-base.googlesheets, n8n-nodes-base.filter

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Jimleuk.

Original n8n.io source

1.1 Workflow description

Title: Build your own CUSTOM API MCP server
Workflow name: Build your own CUSTOM API MCP server

This n8n demonstrates how any organisation can quickly and easily build and offer MCP servers to their customers or internal staff to improve productivity.

This MCP example uses PayCaptain.com as an example and shows how to create an MCP server which can search for and update employee data.

How it works

A MCP server trigger is used and connected to 3 custom workflow tools: Search Employee, Get Employee by ID and Update Employee.
Each tool makes calls to the PayCaptain API to perform their respective tasks. Extra care is performed to strip out sensitive data and ensure we're not sharing too much.
The Update Employee too also guards against updating fields which would preferably remain readonly. When you control the MCP server, you can determine behaviour of the tool.
Finally, a Google Sheet node is used to log all operations for later audit. This will add a tiny bit of latency but recommended if sensitive data is being accessed.

How to use

This MCP server allows any compatible MCP client to manage their PayCaptain employee database. You will need to have a PayCaptain account and developer key to use it.
Connect your MCP client by following the n8n guidelines here - https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger/#integrating-with-claude-desktop
Try the following queries in your MCP client:
- "When did Sarah start here employment at the company?"
- "Does Jack work Wednesdays or Fridays?"
- "Please update Tracy's NI number to ABCD123456"

Requirements

PayCaptain Account and Developer Key.
Google Sheets to log actions for later audit.
MCP Client or Agent for usage such as Claude Desktop - https://claude.ai/download

Customising this workflow

Add or remove employee attributes as required for your user case.
If Google Sheets is too slow, consider an API call to a faster service to log calls to the MCP server.
Remember to set the MCP server to require credentials before going to production and sharing this MCP server with others!

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - When Executed by Another Workflow

Type / Role: n8n-nodes-base.executeWorkflowTrigger - executeWorkflowTrigger
Config choices: Version 1.1

Block 2 - Operation

Type / Role: n8n-nodes-base.switch - switch
Config choices: Version 3.2

Block 3 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 4 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 5 - Sticky Note3

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 6 - Paycaptain MCP Server

Type / Role: @n8n/n8n-nodes-langchain.mcpTrigger - mcpTrigger
Config choices: Version 1

Block 7 - Update Employee

Type / Role: @n8n/n8n-nodes-langchain.toolWorkflow - toolWorkflow
Config choices: Version 2.1

Block 8 - Get Employee

Type / Role: @n8n/n8n-nodes-langchain.toolWorkflow - toolWorkflow
Config choices: Version 2.1

Block 9 - Get Employees

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 10 - Search Employees

Type / Role: @n8n/n8n-nodes-langchain.toolWorkflow - toolWorkflow
Config choices: Version 2.1

Block 11 - Log Call

Type / Role: n8n-nodes-base.googleSheets - googleSheets
Config choices: Version 4.5

Block 12 - Filter Matches

Type / Role: n8n-nodes-base.filter - filter
Config choices: Version 2.2

Block 13 - Aggregate Search Results

Type / Role: n8n-nodes-base.aggregate - aggregate
Config choices: Version 1

Block 14 - Get Employees1

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 15 - Filter Matching ID

Type / Role: n8n-nodes-base.filter - filter
Config choices: Version 2.2

Block 16 - Strip Sensitive Fields1

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 17 - Strip Sensitive Fields

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 18 - Update Employee1

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 19 - Valid Fields Only

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 20 - Has Valid Request?

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 21 - Get Error Response

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 22 - Get Success Response

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 23 - Aggregate Get Response

Type / Role: n8n-nodes-base.aggregate - aggregate
Config choices: Version 1

Block 24 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Showing the first 24 of 25 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow	Build your own CUSTOM API MCP server
Complexity	advanced
Nodes	25
Categories	HR, AI RAG
Author	Jimleuk
Published	21 Apr 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/3638/3638.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source HR workflows AI RAG workflows

Frequently asked questions

What does Build your own CUSTOM API MCP server do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your HR, AI RAG use case.

Jimleuk

100 workflows

Nodes

n8n-nodes-base.executeworkflowtrigger n8n-nodes-base.switch n8n-nodes-base.stickynote @n8n/n8n-nodes-langchain.mcptrigger @n8n/n8n-nodes-langchain.toolworkflow n8n-nodes-base.httprequest n8n-nodes-base.googlesheets n8n-nodes-base.filter

Complexity

advanced

Published 21 Apr 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/3638/3638.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Manage employee offboarding with Google Workspace, Slack, HubSpot and Notion

## Quick Overview This workflow receives an HR offboarding webhook, validates and enriches the employee record, suspends the user in Google Workspace, deactivates the user in Slack, looks up the matching HubSpot contact, logs the event to Notion and Google Sheets, and notifies HR/IT via Gmail and Slack. ## How it works 1. Receives a POST webhook from the HR system with employee offboarding details. 2. Parses the payload to normalize key fields (name, email, department, manager, last day) and flags invalid requests. 3. Posts an alert to a Slack IT channel when the record is invalid and stops further processing. 4. Enriches valid records with an offboarding ID, risk level, revocation deadline, and an actions summary. 5. Suspends the employee in Google Workspace via the Admin Directory API, deactivates the user in Slack via the Slack API, searches for the contact in HubSpot, and creates an offboarding entry in a Notion database. 6. Combines the revocation results and appends a compliance log row to a Google Sheets “Offboarding Log” tracker. 7. Emails an offboarding completion summary to the manager and HR using Gmail and posts a completion digest to the Slack IT channel. ## Setup 1. Copy the n8n webhook URL from the HR offboarding webhook trigger and configure your HR system to POST the offboarding payload to it. 2. Provide credentials/tokens for the Google Admin Directory API and Slack API (both used via HTTP requests) and replace the placeholder Bearer tokens in the request headers. 3. Add a HubSpot App Token credential with access to search contacts. 4. Create a Notion database for offboarding logs, add a Notion API integration, and set the Notion database ID and API key in the Notion request. 5. Add Google Sheets OAuth credentials, set your Google Sheet ID, and ensure the “Offboarding Log” sheet contains the columns mapped in the append step. 6. Add a Gmail connection for sending summary emails and set the target Slack channel ID for the invalid-record alert and IT ops digest messages.

View

Send AI interview briefs from resumes with GPT-4o-mini, Google Sheets and Gmail

## Quick Overview This workflow runs every 15 minutes to read candidate rows from Google Sheets, download each resume PDF from Google Drive, extract text, generate an HTML interview brief using OpenAI GPT-4o-mini, email it via Gmail to the interviewer, and mark the row as Processed to avoid duplicates. ## How it works 1. Runs on a schedule trigger every 15 minutes. 2. Reads all candidate rows from the “Candidates” tab in Google Sheets and processes them one at a time. 3. Skips any rows where the Status column is already set to “Processed.” 4. Extracts the Google Drive file ID from the resume link, downloads the PDF, and converts it to plain text. 5. Cleans and truncates the resume text and combines it with the candidate’s name, role, and email details. 6. Sends the resume text and metadata to OpenAI (GPT-4o-mini) to generate a styled HTML interviewer brief. 7. Emails the HTML brief to the interviewer via Gmail and updates the candidate row in Google Sheets to “Processed,” then waits 5 seconds before moving to the next candidate. ## Setup 1. Add Google Sheets OAuth credentials and replace `YOUR_CANDIDATES_SHEET_ID`, then create a “Candidates” sheet with columns Name, Email, Job Role, Resume Drive Link, Interviewer Email, and Status. 2. Add Google Drive OAuth credentials and ensure each resume PDF is accessible to the workflow (for example, shared so the connected account can view it). 3. Add an OpenAI API credential and keep the model set to GPT-4o-mini. 4. Add Gmail OAuth credentials and confirm the sender name and subject line meet your email requirements. 5. Adjust the schedule interval if you want the workflow to check for new candidates more or less frequently.

View

Provision new hire IT accounts with Google Workspace, Slack, and Gmail

## Quick Overview This workflow receives new-hire records via a webhook, validates and normalizes the data, then provisions a Google Workspace account, creates an onboarding task in Google Tasks, notifies the IT team in Slack, emails the hiring manager via Gmail, and logs the run to Google Sheets. ## How it works 1. Receives a new hire payload from the HR system through an HTTP webhook endpoint. 2. Parses the payload, standardizes key fields (name, department, manager, start date), and skips records missing required identity data. 3. If the record is invalid, posts a Slack message to the IT channel for manual review and stops processing. 4. For valid hires, generates a company email address, username, temporary password, ticket title, and a target ready-by date. 5. Creates the new user in the Google Admin Directory (Google Workspace) and opens an IT onboarding checklist as a Google Tasks task. 6. Posts a provisioning summary to the IT Slack channel, emails the manager a day-one checklist via Gmail, and appends the provisioning details to a Google Sheets log. ## Setup 1. Configure your HR system (or source app) to send a POST request to the workflow webhook path `/hr/new-hire` using the production webhook URL. 2. Add Google credentials with access to the Admin SDK Directory API (for user creation), Google Tasks, Gmail, and Google Sheets, and ensure the account has the required admin permissions. 3. Add Slack credentials, set the target channel ID for IT onboarding notifications, and update the channel selection if needed. 4. Update the email domain in the generated address (currently `@yourcompany.com`) and confirm how departments map to Google Workspace org unit paths. 5. Set your Google Sheets document ID and ensure it contains (or can create) a sheet named "Provisioning Log" with matching columns for the appended fields.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Build your own CUSTOM API MCP server

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

This n8n demonstrates how any organisation can quickly and easily build and offer MCP servers to their customers or internal staff to improve productivity.

How it works

How to use

Requirements

Customising this workflow

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - When Executed by Another Workflow

Block 2 - Operation

Block 3 - Sticky Note

Block 4 - Sticky Note1

Block 5 - Sticky Note3

Block 6 - Paycaptain MCP Server

Block 7 - Update Employee

Block 8 - Get Employee

Block 9 - Get Employees

Block 10 - Search Employees

Block 11 - Log Call

Block 12 - Filter Matches

Block 13 - Aggregate Search Results

Block 14 - Get Employees1

Block 15 - Filter Matching ID

Block 16 - Strip Sensitive Fields1

Block 17 - Strip Sensitive Fields

Block 18 - Update Employee1

Block 19 - Valid Fields Only

Block 20 - Has Valid Request?

Block 21 - Get Error Response

Block 22 - Get Success Response

Block 23 - Aggregate Get Response

Block 24 - Sticky Note2

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions