AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Teable Mcp Server

mcp-ltphat2204-teable-mcp-server · by ltphat2204

MCP server for Teable - Connect AI assistants to your no-code database with natural language queries

No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add mcp-ltphat2204-teable-mcp-server

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-ltphat2204-teable-mcp-server)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Teable Mcp Server? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Teable MCP Server

A Model Context Protocol (MCP) server that connects Teable — the super-fast, open-source, no-code database — to LLMs like Claude, ChatGPT, and others.

This server enables AI agents to seamlessly query records, explore schema structures (spaces, bases, tables, views), and retrieve data from your Teable instance using natural language. It acts as a bridge, empowering your AI to interact with your data dynamically and intelligently.

🌟 What is Teable?

Teable is a next-generation, open-source, no-code database built on Postgres. It combines the ease of use of a spreadsheet with the power of a relational database.

  • Hyper-fast: Handles millions of rows with ease.
  • Open Source: You own your data. Self-hostable.
  • SQL-like: Powerful querying capabilities.
  • Real-time: Collaboration features built-in.
  • API-first: Designed for developers and automation.

✨ Features

This MCP server exposes 27 tools to LLMs, organized into the following categories:

🔍 Read / Query

  • query_teable: Query records from a table with support for filtering, sorting, limiting, and view-scoped results.
  • get_record: Retrieve a single record by its ID.
  • create_record: Create a new record in a table with specified field values.
  • update_record: Update an existing record by ID with specified field values.
  • delete_record: Permanently delete a record (all data will be lost). This operation is irreversible.
  • get_record_history: Access the full change history of a record.
  • list_spaces: List all spaces accessible to the user.
  • list_bases: List all bases within a specific space.
  • list_tables: List all tables within a specific base.
  • list_views: List all views within a table.
  • get_table_fields: Fetch the full schema (field definitions) of a table.

💬 Record Comments

  • get_record_comments: Retrieve all comments on a specific record.
  • comment_on_record: Post a new comment on a record.

🏗 Field Management

  • create_field: Add a new field to a table (supports all field types: singleLineText, number, checkbox, date, singleSelect, multipleSelect, longText, formula, rating, currency, percent, email, url, phoneNumber, attachment).
  • update_field: Rename a field or update its description/options.
  • delete_field: Permanently remove a field and all its data from a table.

📊 Dependency & Impact Analysis

  • get_field_dependency_graph: Retrieve the complete local and cross-table dependency graph of fields in a table, resolving formula references and rollups with dynamic Mermaid flowchart visualization.
  • analyze_field_impact: Recursively analyze the upstream and downstream safety impact of modifying or deleting a specific field, performing base-wide scans to trace local and foreign dependents with an actionable safety recommendation checklist.

📋 Table Management

  • create_table: Create a new table in a base, optionally with initial fields.
  • update_table: Rename a table or update its description.
  • delete_table: Move a table to the trash (recoverable).
  • export_table_data: Export all table data as CSV.

🗑 Table Trash

  • get_table_trash: List all tables currently in the trash for a base.
  • restore_table_from_trash: Restore a trashed table back to the active base.
  • permanently_delete_table: Irreversibly delete a table. Cannot be undone.

👁 View Management

  • create_view: Create a new view (grid, gallery, kanban, calendar, gantt, or form).
  • update_view: Rename a view or update its filter/sort configuration.
  • delete_view: Remove a view from a table.
  • share_view: Enable or disable a public share link for a view.

🛠 Configuration

To use this server, you need a Teable API Key.

  1. Get your API Key:
  • Log in to your Teable account and navigate to Personal Access Token settings.
  • Click Create New Token.
  • Enable the following permission scopes:
  • Read: space, base, table, record, view, field
  • Write/Mutate: record (comments), field, table, view
  • Select the appropriate bases you want the MCP server to access.
  • Save the token - you'll need this for configuration.
  1. Environment Variables:

You can configure the server using specific environment variables.

| Variable | Description | Required | Default | | :--- | :--- | :--- | :--- | | TEABLE_API_KEY | Your Personal Access Token | Yes | - | | TEABLE_BASE_URL | API Endpoint (Change if self-hosting) | Yes | https://app.teable.ai/api |

🚀 Usage

> Note: For Option 1 and Option 2, since we are using the local source code, you must build the project first. > ``bash > npm install && npm run build > ``

Option 1: Using with Claude Desktop (Recommended)

Add the following configuration to your claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "teable": {
      "command": "node",
      "args": [
        "/absolute/path/to/teable-mcp-server/dist/index.js"
      ],
      "env": {
        "TEABLE_API_KEY": "mcp_sk_xxxxxxxxxxxxxx",
        "TEABLE_BASE_URL": "https://app.teable.ai/api"
      }
    }
  }
}

Note: Replace mcp_sk_xxxxxxxxxxxxxx with your actual API key.

Option 2: Using with Cursor

  1. Open Cursor Settings.
  2. Navigate to Features -> MCP.
  3. Click + Add New MCP Server.
  4. Enter a name (e.g., "Teable").
  5. Select Type: command.
  6. Command:

``bash node /absolute/path/to/teable-mcp-server/dist/index.js ``

  1. Add your Environment Variables in the env section:
  • TEABLE_API_KEY: your_api_key
  • TEABLE_BASE_URL: https://app.teable.ai/api

💻 Local Development

  1. Clone the repository:

``bash git clone https://github.com/ltphat2204/teable-mcp-server.git cd teable-mcp-server ``

  1. Install dependencies:

``bash npm install ``

  1. Build the project:

``bash npm run build ``

  1. Debug using MCP Inspector:

``bash export TEABLE_API_KEY=your_api_key export TEABLE_BASE_URL=https://app.teable.ai/api npm run inspector ``

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

📄 License

This project is licensed under the MIT License.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.