No install? Use cloud.anythingmcp.com directly.
Sign in, install the Coda in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Coda, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Coda + ChatGPT
Drive Coda (docs + tables + formulas) from any AI agent: docs, tables, rows, columns, formulas, packs, controls. 13 tools, Bearer token auth.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
CODA_API_TOKEN
Paso 1 — Obtener credenciales
io/developers/apis/v1).
Setup:
- Sign in to https://coda.io → top-right avatar → Account → API settings → Generate API token.
- Name the token. Copy it. Set
CODA_API_TOKEN.
Authentication: Authorization: Bearer ${CODA_API_TOKEN}.
Resource hierarchy: Doc → Section (Page) → Table → Row → Cell. Coda's twist: tables are first-class with structured columns and types; rows are addressable individually; columns can hold formulas.
Doc IDs look like dXXXXXXXXXX (10-char prefix d). Visible in the doc URL.
Table IDs look like grid-XXXXX. Discover via coda_list_tables(docId).
…(continued in the in-app connector instructions)
Paso 2 — Instalar el adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Paso 3 — Añadir el conector en ChatGPT
ChatGPT soporta servidores MCP a través de la función Connectors (planes Plus / Pro / Team / Enterprise). El plan gratuito no admite conectores personalizados.
- Abre ChatGPT → Settings → Connectors (o pulsa el icono 🔧 en el composer → Manage connectors).
- Pulsa "Add custom connector".
- Rellena:
- Name:
Coda - MCP server URL:
https://cloud.anythingmcp.com/mcp - Authentication: Bearer token → pega tu MCP API key (de AnythingMCP → Profile → MCP API Keys → New Key)
- Name:
- Pulsa Connect para autorizar.
Herramientas disponibles
| Tool | What it does |
|---|---|
coda_whoami | Return the user the token belongs to |
coda_list_docs | List docs the user can access |
coda_get_doc | Fetch a single doc by ID |
coda_list_tables | List tables in a doc |
coda_list_columns | List columns in a table |
coda_list_rows | List rows in a table or view |
coda_get_row | Fetch a single row by ID |
coda_insert_rows | Insert (or upsert with keyColumns) rows into a table |
coda_update_row | Update a specific row by ID |
coda_delete_row | Delete a single row by ID |
coda_delete_rows | Bulk-delete rows by IDs (more efficient than per-row) |
coda_get_formula_result | Evaluate a named formula on a doc |
coda_get_mutation_status | Check the status of an async mutation (insert/update/delete) by its requestId returned from those calls |
FAQ
¿Funciona el plan gratuito de ChatGPT con los Connectors MCP personalizados? No — se necesita Plus, Pro, Team o Enterprise.