nocodb-mcp-connector
Click 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., "@nocodb-mcp-connector list all records in the Projects table"
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.
nocodb-mcp-connector (Python)
An MCP server that exposes a NocoDB base (bases, tables, records, linked records) as tools, so Claude can read/write your NocoDB data the same way it can with the built-in Airtable connector.
Python implementation of this connector. There's also a TypeScript version with the identical tool set — pick whichever fits your stack. This is the primary/maintained one.
Built as a self-serve open-source template: you deploy your own instance with your own NocoDB account and your own auth secret. There's no shared hosted service — each user runs their own copy.
Tools
Same 13 tools as the TypeScript version: list_workspaces, list_bases,
list_tables, get_table_schema, list_records, get_record,
count_records, create_records, update_records, delete_records,
list_linked_records, link_records, unlink_records. Create/update/delete
all accept either a single record or a list for batching.
Related MCP server: Test MCP Server
1. Get a free NocoDB instance
Sign up at https://app.nocodb.com (free plan — 50,000 records, well above Airtable's 1,000-record free cap). Import your Airtable base directly (Base -> Import -> Airtable) or start empty. Get an API token: avatar (bottom left) -> Account Settings -> Tokens -> Create New Token.
2. Local setup
Requires Python 3.10+.
python -m venv .venv
.venv\Scripts\activate # Windows
pip install -e .
cp .env.example .env # fill in NOCODB_BASE_URL / NOCODB_API_TOKEN3. Run locally (stdio, for Claude Desktop/Code)
nocodb-mcp-connectorAdd it to your MCP client config, e.g. claude_desktop_config.json:
{
"mcpServers": {
"nocodb": {
"command": "C:\\path\\to\\nocodb-mcp-connector-py\\.venv\\Scripts\\python.exe",
"args": ["-m", "nocodb_mcp_connector.stdio"],
"env": {
"NOCODB_BASE_URL": "https://app.nocodb.com",
"NOCODB_API_TOKEN": "your-token-here"
}
}
}
}4. Deploy to Render (for claude.ai custom connector)
claude.ai's custom connectors need a public HTTPS URL, so this repo ships an
HTTP entry point (nocodb_mcp_connector.http) alongside the local one — a
stateless Streamable HTTP server, since NocoDB itself holds all the actual
state.
Push this repo to GitHub.
In Render: New -> Blueprint, point it at the repo (
render.yamlis already set up: free plan,pip install -e ., health check on/health).Set the three env vars Render will prompt for:
NOCODB_BASE_URL,NOCODB_API_TOKEN— your NocoDB credentials.MCP_AUTH_TOKEN— a secret you generate yourself (openssl rand -hex 32or similar). This is what stops random people on the internet from hitting your NocoDB data through the public URL — it's checked with a constant-time comparison against theAuthorization: Bearer <token>header on every/mcprequest.
Deploy. Render's free tier sleeps after 15 min idle — expect a ~30-60s cold start on the first request after a gap.
In claude.ai: Settings -> Connectors -> Add custom connector.
URL:
https://<your-app>.onrender.com/mcpAuth: Request headers ->
Authorization: Bearer <the same MCP_AUTH_TOKEN>
/health is intentionally left unauthenticated (Render's health check needs
to reach it) — it only ever returns "ok", no data.
Notes on the MCP SDK version
This was built against mcp 2.0.0 — the high-level server class is
mcp.server.mcpserver.MCPServer (older tutorials referencing FastMCP from
mcp.server.fastmcp predate this rename). If you see import errors after a
pip install --upgrade mcp, check mcp's changelog for further API moves.
Verifying against your instance
The NocoDB v2 API endpoint shapes here mirror the TypeScript version — see its README for the same caveat: verified against documented behavior, not a live Swagger scrape, so double-check against a real base once you have one.
Smoke test
Stdio (requires the MCP initialize handshake before tools/list will
respond — see the TS README for the exact three-line payload):
python -m nocodb_mcp_connector.stdioHTTP, once running (nocodb-mcp-connector-http or python -m nocodb_mcp_connector.http):
curl http://localhost:3000/health
# "ok"
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "Authorization: Bearer $MCP_AUTH_TOKEN" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}}}'Available Tools
13 toolscount_recordsB
Count records in a table, optionally matching a filter.
Inputs: table_id (required), where.
create_recordsB
Create one or more records in a table.
Inputs: records (required), table_id (required).
delete_recordsC
Delete one or more records by Id.
Inputs: ids (required), table_id (required).
get_recordB
Get a single record by its Id.
Inputs: table_id (required), record_id (required).
get_table_schemaA
Get full schema for a table: its fields/columns, types, options (e.g. select choices), and relational (Links) fields with their linkFieldId. Call this before creating/updating records so you know valid field names and link field ids.
Inputs: table_id (required).
link_recordsA
Link one or more existing records to a given record through a relational (Links) field (e.g. attach child records to a parent).
Inputs: table_id (required), record_id (required), link_field_id (required), related_record_ids (required).
list_basesA
List NocoDB bases (projects) visible to this API token. Pass workspace_id on NocoDB Cloud if you have multiple workspaces; omit it for self-hosted OSS instances.
Inputs: workspace_id.
list_linked_recordsB
List the records currently linked to a given record through a relational (Links) field.
Inputs: table_id (required), record_id (required), link_field_id (required), limit, +1 more.
list_recordsA
List records from a table, with optional filtering, sorting, field selection, and pagination.
Inputs: table_id (required), sort, limit, where, +3 more.
list_tablesA
List tables within a NocoDB base, including each table's id, name, and type.
Inputs: base_id (required).
list_workspacesA
List NocoDB workspaces visible to this API token. Only relevant on NocoDB Cloud; self-hosted OSS instances typically don't use workspaces — call list_bases directly instead.
Inputs: no named parameters.
unlink_recordsB
Remove a link between a record and one or more related records through a relational (Links) field.
Inputs: table_id (required), record_id (required), link_field_id (required), related_record_ids (required).
update_recordsB
Update one or more existing records. Each record object must include its Id plus the fields to change.
Inputs: records (required), table_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Each tool targets a distinct resource and action. list_bases vs list_workspaces are clearly separated by workspace vs base, and descriptions clarify usage. list_records vs get_record differ in list vs single retrieval.
All tools use verb_noun snake_case (list_bases, create_records, link_records, etc.) with no mixed conventions or vague verbs. The pattern is immediately predictable.
13 tools is appropriate for a database connector covering base/table discovery, schema introspection, record CRUD, querying, and link management. Each tool earns its place.
Core workflows are well-covered: explore bases/tables/schema, then create/update/delete/query records and manage links. Minor gaps include no create/delete base or table, but these may be outside the connector's scope.
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Hosted Airtable MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Official Airtable MCP server — database and operations layer for agents.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol server that provides tools for programmatically managing Airtable bases, tables, fields, and records through Claude Desktop or other MCP clients.12291 npm75MIT
- FlicenseNot gradedqualityDmaintenanceA dual-transport MCP server that exposes your API as tools to LLM clients, supporting both stdio transport for local clients like Claude Desktop and HTTP/SSE transport for remote clients like OpenAI's Responses API.-
- AlicenseNot gradedqualityDmaintenanceRemote MCP server that auto-generates tools from NocoBase OpenAPI specs to enable full CRUD operations on collections across multiple instances. Supports streamable HTTP transport and API key authentication for secure, natural language interaction with NocoBase deployments.MIT
- AlicenseAqualityDmaintenanceAn MCP server that enables AI assistants to interact with NocoBase instances for managing collections, UI schemas, flow models, and running API operations. It provides both hand-crafted tools and dynamically generated tools from NocoBase's OpenAPI specification.2311 npmMIT