Workflow86 MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Workflow86 MCP Server list my workflows"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Workflow86 MCP Server
This is a fairly standard Node MCP Server implementation against the workflow86.com public API.
Standard Setup
Normal users will only need to follow some fairly standard setup steps:
Create an API Key from the Organization page of workflow86.com
Setup your MCP client
If you are using Cursor your config file will be at
~/.cursor/mcp.jsonClaude on MacOS has a config file at
~/Library/Application\ Support/Claude/claude_desktop_config.jsonFor other tools please follow their setup instructions
Most tools use configuration in the following format:
{ "mcpServers": { "workflow86": { "command": "npx", "args": ["@npm-workflow86/mcp-server"], "env": { "W86_API_KEY": "<API Key for your W86 Organization>" } } } }To use the latest unreleased build specify the canary tag eg.
"args": ["@npm-workflow86/mcp-server@canary"],Check your Node Version
Make sure your system default node version is v22 or greater (20 may also work but your mileage may vary)node -v
Note: The server will start even if W86_API_KEY is not set so MCP clients can discover available tools. However, calling any Workflow86 tool requires an API key (or custom W86_HEADERS). Without it, tool calls will fail with an authorization error.
Optional: set W86_DOMAIN to point at a different API host (defaults to https://api.workflow86.com).
Test Integration
Cursor
Goto Cursor -> Settings -> Cursor Settings -> Tools & Integrations
There should be a workflow86 entry in the MCP Tools section. If something's gone wrong an error message will display here.
Related MCP server: mcp-n8n-builder
Contributor Setup
For other folk that would like to run the server against source for whatever reason setup is a little more involved. If you don't already have the source run:
git clone git@github.com:workflow86oss/mcp-server.gitBuild
npm install && npm run build
Tests and Coverage
Run unit tests:
npm testRun module tests:
npm run moduleTestAnalyze coverage for module tests:
npm run moduleCoverageUses
c8(V8 coverage) so child processes spawned by module tests are includedFirst run
npm installto ensure dev deps (c8) are installedHTML and lcov reports:
coverage/module/(opencoverage/module/index.html)
Run with CLI
This is particularly useful to get at logs easily if things are going wrong or for quick testing:
First setup your Dev API Key (you might like to add this to your shell init script)
export W86_API_KEY=<api key>Then you can invoke commands via jsonrpc like this:
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list-workflows","arguments":{}}}' | node build/server.jsConfigure a MCP Client
To configure a MCP Client to run against your local checkout put this config in the correct place for your desired tool:
{
"mcpServers": {
"workflow86": {
"command": "node",
"args": ["/<absolute-checkout-path>/mcp-server/build/server.js"],
"env": {
"W86_API_KEY": "<API Key for your W86 Client>"
}
}
}
}Regenerate Generated Client Code
src/client contains a typescript client generated from the Public API OpenAPI spec at https://api.workflow86.com/v3/api-docs. To regenerate after API changes:
npm run genclientReferences
Workflow86 homepage: https://www.workflow86.com
MCP Spec: https://modelcontextprotocol.io/specification/2025-06-18
Available Tools
22 toolsadd-columnC
Add a column to an existing table.
Inputs: name (required), type (required), tableId (required).
create-tableB
Create a new Table with the given name and columns
Inputs: columns (required), tableName (required).
delete-columnB
Delete a column from an existing table.
Inputs: tableId (required), columnName (required).
delete-componentB
Delete a component from a draft workflow, removing all links to and from the component.
Inputs: workflowId (required), componentId (required).
get-sessionC
JSON representation of a Workflow Session
Inputs: sessionId (required).
get-tableA
Retrieve detailed information about a specific table including its ID, name, and complete column definitions. Provides the full schema and metadata for the specified table.
Inputs: tableId (required).
get-workflowB
Get comprehensive workflow details including metadata (ID, version, status, name), full workflow description with purpose and use cases, complete component definitions with types and descriptions, placeholder mappings for data flow between components, component connections and relationships, and links to related workflow operations like session management
Inputs: workflowId (required), workflowVersion.
get-workflow-historyA
Retrieve a paginated history of all versions for a specific workflow, including version numbers, timestamps, status changes, and metadata for each version. Useful for tracking workflow evolution and accessing previous versions.
Inputs: workflowId (required), pageNumber.
list-formsA
Get a paginated list of available forms including form names, URLs, associated workflow IDs and names. Returns form metadata with pagination support for easy form discovery and access. Useful for finding forms that users can submit or access.
Inputs: pageNumber.
list-sessionsA
Get a paginated list of all execution sessions for a workflow, including session IDs, status, timestamps, and execution mode. Can filter between production and test runs of draft workflows. Returns user-friendly messages when no sessions exist, with pagination support for workflows with many execution histories.
Inputs: workflowId (required), pageNumber, sessionMode.
list-tablesB
Get a paginated list of all tables for the authenticated client. Returns table summaries including table IDs, names, and pagination controls for browsing through all available tables.
Inputs: pageNumber.
list-tasksA
Get a filtered list of task summaries with comprehensive filter options including text search, workflow filtering, status filtering, date range filtering, and pagination support. Returns task details with names, descriptions, URLs, workflow information, and navigation links for easy task management and tracking.
Inputs: endDate, startDate, workflowId, queryString, +2 more.
list-workflowsA
Get a paginated list of workflow summaries including workflow IDs, names, publication status, draft versions, and navigation links. Returns structured metadata for each workflow with pagination controls and links to detailed workflow information.
Inputs: status, orderBy, pageNumber, orderDirection.
publish-workflowA
Publish an existing workflow DRAFT, making it available for production execution. Adds a comment and description to document the publication. Creates a new published version and increments the draft version number.
Inputs: workflowId (required), comment, description.
rename-columnC
Rename a column in an existing table.
Inputs: tableId (required), newColumnName (required), originalColumnName (required).
rerun-workflowB
A command for rerunning a workflow from an existing session
Inputs: sessionId (required), workflowId (required), componentId (required), projectVersion.
retry-failed-componentA
Restart execution of a failed component and continue the workflow from that point forward. Automatically resumes processing from the specified component using existing session data and placeholder values. Essential for recovering from transient failures or errors without restarting the entire workflow.
Inputs: sessionId (required), componentId (required), threadId.
run-workflowC
A command for starting a workflow
Inputs: workflowId (required), componentId (required), workflowVersion, placeholderValues.
terminate-componentA
Selectively terminate a specific component thread within a workflow session while allowing other components to continue running. Provides granular control over workflow execution by targeting individual components or threads. Useful for stopping problematic components without affecting the entire workflow.
Inputs: sessionId (required), componentId (required), threadId.
terminate-entire-sessionA
Immediately stop and terminate an entire workflow session, ending execution of all active components and preventing any further processing. Useful for canceling long-running workflows or stopping erroneous executions. Returns confirmation of termination status.
Inputs: sessionId (required).
unpublish-workflowA
Unpublish an existing workflow, making it unavailable for normal execution. This changes the status of the currently published version and makes only the draft version available. Useful for taking workflows offline for any reason.
Inputs: workflowId (required).
update-workflow-detailsA
Update workflow name and/or description. Only provided fields will be updated, omitted fields will remain unchanged.
Inputs: workflowId (required), workflowName, workflowDescription.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 22 tools
Each tool targets a distinct operation—workflows, sessions, tasks, forms, tables, and component manipulation—with clear boundaries. Even similar actions like 'terminate-entire-session' and 'terminate-component' are differentiated by scope.
All tool names follow a consistent 'verb_noun' pattern (e.g., list-workflows, create-table, delete-component). No mixing of conventions or ambiguous verbs.
22 tools is slightly above the typical 3-15 range, but the broad domain (workflows, sessions, tables, forms) justifies the number. It is not excessive and each tool serves a clear purpose.
The tool surface has significant gaps: no create/delete workflow, no table delete/update, only list operations for forms and tasks. Essential CRUD operations are missing, limiting agent capabilities.
Maintenance
Related MCP Connectors
Open-source Zapier/n8n alternative as an MCP server: agents build, run and debug your workflows.
Build and run AI workflows, agents, data tables and 1000+ API integrations from any MCP client.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server for CertScore.ai public website risk-signal workflows.
Related MCP Servers
- AlicenseCqualityDmaintenanceA Model Context Protocol (MCP) server for programmatically creating and managing n8n workflows.118MIT
- AlicenseAqualityDmaintenance🪄 MCP server for programmatic creation and management of n8n workflows. Enables AI assistants to build, modify, and manage workflows without direct user intervention through a comprehensive set of tools and resources for interacting with n8n's REST API.1029 npm86MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for n8n workflow automation, enabling management of workflows, executions, credentials, tags, users, and webhooks via an MCP-compatible client.MIT
- AlicenseBqualityDmaintenanceMCP server for managing n8n workflows and executions. Enables listing, activating, deactivating, and executing workflows, as well as monitoring executions and instance health.9MIT