Stack Ai MCP server

Connect Stack Ai to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

What you can do with the Stack Ai MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the create knowledge base tool in Stack Ai
  • Use the delete document tool in Stack Ai
  • Use the get knowledge base tool in Stack Ai
  • Use the browse connection resources tool in Stack Ai
  • Use the manage folder tool in Stack Ai
  • Use the run action tool in Stack Ai

Supported Tools

create_knowledge_base

Create Knowledge Base

Create a new knowledge base. Optionally connect it to an external data source and configure indexing parameters for RAG (Retrieval-Augmented Generation).

delete_document

Delete Document

Delete a file from a user's document bucket associated with a specific flow and node.

get_knowledge_base

Get Knowledge Base

Retrieve details of a specific knowledge base by its ID, including its configuration, connected sources, and indexing parameters.

browse_connection_resources

Browse Connection Resources

Browse or search resources available through a connection. Useful for discovering files, folders, or data in connected external services like SharePoint or Google Drive.

manage_folder

Manage Folder

Create, update, or delete a folder. Use this to organize your projects within the Stack AI platform.

run_action

Run Action

Execute a specific action from a tool provider. Depending on the action, this can search, create, change, or delete data in an external system. Obtain the action ID and expected input schema from your Stack AI action configuration.

list_documents

List Documents

List all files in a user's document bucket for a specific flow and node. Returns the filenames stored in the bucket.

list_conversations

List Conversations

List conversations for a specific user within a project. Returns conversation histories from chat-based deployed flows.

delete_knowledge_base

Delete Knowledge Base

Permanently delete a knowledge base and all its indexed resources.

update_knowledge_base

Update Knowledge Base

Update an existing knowledge base's properties including name, description, and indexing parameters.

list_tool_providers

List Tool Providers

List available tool providers in Stack AI for interacting with external services such as web search, databases, and third-party APIs.

list_user_conversations

List All User Conversations

List all user conversations for a project via the manager interface. Returns conversations across all users, useful for admin/oversight purposes.

get_connection

Get Connection

Retrieve details of a specific connection including its type, status, and configuration. Optionally check the connection's health status.

sync_knowledge_base

Sync Knowledge Base

Synchronize a knowledge base with its connected data sources. Triggers re-indexing of content from the connected sources.

delete_knowledge_base_resource

Delete Knowledge Base Resource

Remove a specific file or resource from a knowledge base.

delete_connection

Delete Connection

Remove a connection from your organization. This will disconnect the associated external service.

get_organization_analytics

Get Organization Analytics

Retrieve analytics summary across all projects in the organization. Returns per-project summaries including total runs, errors, token usage, and user counts.

flow_feedback

Submit Flow Feedback

Submit feedback for a specific flow run. Use this to provide human feedback on AI-generated outputs, useful for evaluation and fine-tuning workflows.

list_folders

List Folders

List and search folders in your organization. Folders are used to organize projects within the Stack AI platform.

list_connections

List Connections

List all connections in your organization. Connections represent integrations with external services like SharePoint, Salesforce, Slack, Google Drive, etc.

get_project_analytics

Get Project Analytics

Retrieve run logs and analytics for a specific flow/project. Returns detailed information about each run including status, latency, token usage, inputs, outputs, and errors. Supports date range filtering and pagination.

manage_conversation

Manage Conversation

Manage a conversation within a project. Rename, archive/unarchive, or delete a conversation.

list_knowledge_base_resources

List Knowledge Base Resources

List files and resources indexed in a knowledge base. Supports cursor-based pagination.

get_storage_analytics

Get Storage Analytics

Retrieve storage usage analytics for the organization, including total storage and per-knowledge-base breakdowns.

list_knowledge_bases

List Knowledge Bases

List all available knowledge bases in your organization. Supports cursor-based pagination for large collections.

run_flow

Run Flow

Execute a deployed Stack AI workflow and retrieve its output. Send inputs to a published flow and receive the AI-generated results. Supports text inputs, URLs, and conversation tracking via user IDs. You can target a specific flow version or use the latest published version.

upload_knowledge_base_resource

Upload Knowledge Base Resource

Upload a file directly into an existing Stack AI knowledge base and start indexing. Returns the provider resource ID. Use list_knowledge_base_resources to read back the resource; acceptance does not mean indexing has finished.

upload_document

Upload Workflow Document

Upload a file to a deployed workflow Files Node for a specific user or conversation. The workflow must already contain the Files Node. Use list_documents to read back the user bucket.

Connect Stack Ai to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Stack Ai in Metorial. In your Metorial portal, enable the Stack Ai MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Stack Ai tools.

Run Stack Ai through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Stack Ai and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Stack Ai tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Stack Ai

Notion

Create, read, update, and archive pages and databases in a Notion workspace. Manage blocks (paragraphs, lists, headings, embeds, etc.) within pages. Query databases with filters and sorts across rich property types including text, numbers, dates, selects, relations, and formulas. Search across pages and databases by title. Add and read comments on pages and blocks. Upload files to pages. Manage workspace users and retrieve user profiles.

Google Sheets

Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Microsoft Outlook

Send, read, reply to, forward, and manage email messages in user mailboxes. Organize messages into folders, apply categories, flags, and importance levels. Manage file and item attachments. Create, update, delete, and respond to calendar events and meetings. Find available meeting times, manage attendees, handle recurrence, and work with shared or delegated calendars. Create, read, update, and delete contacts, organize them into contact folders, and manage contact photos. Manage tasks and task lists via Microsoft To Do, including due dates, reminders, recurrence, and checklist items. Support for Focused Inbox, @-mentions, mail tips, send-on-behalf, and send-as capabilities.

Technical notes for Stack Ai

Run published Stack AI workflows, upload files to workflow Files Nodes or knowledge bases, retrieve run analytics, and use existing knowledge-base, connection, conversation, folder, and action management tools.

Frequently asked questions

Common questions about connecting Stack Ai to AI agents with Metorial.

  1. How many tools does the Stack Ai MCP server have?
    The Stack Ai MCP server exposes 28 tools, including Create Knowledge Base, Delete Document, Get Knowledge Base. Each one is governed and traced through Metorial.
  2. Stack Ai exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Stack Ai MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Stack Ai and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Stack Ai MCP server yourself or use the hosted gateway.

Connect Stack Ai to production AI agents

See how Metorial gives your team governed access to Stack Ai, with tracing and security controls built in.