Nutshell vs Twenty API + MCP

Nutshell

The REST reference is served as Markdown with an OpenAPI fragment per operation, and the hosted MCP server uses OAuth with PKCE and can only read. No rate limit numbers, error format or API changelog were found in the reviewed documentation, and API keys carry no scopes.

Twenty API + MCP

Six MCP meta-tools by default with schemas loaded on demand, and ?mode=direct for clients that load lazily. No status page found.

Nutshell

1. Authenticate REST calls with HTTP Basic, a Nutshell user's email as username and the API key as password, against https://app.nutshell.com/rest
2. Use IDs in the <number>-<type> form, such as 3-accounts, and send updates as JSON Patch with content-type: application/json-patch+json
3. Page lists with page[limit] and page[page], which is 0-based, and call /accounts/list/fields or the lead and contact equivalents for valid filter keys
4. Use the REST API for writes. The MCP server only reads, and OAuth tokens need the read scope
5. Filter webhook events yourself, because every webhook receives all events and subscriptions are created in Setup, not through the API

Twenty API + MCP

1. Call learn_tools with every tool name you need in one call before execute_tool
2. Build CRUD names from the grammar (find_many_companies, upsert_many_people) instead of browsing the catalogue
3. Pass one category to get_tool_catalog, since an unfiltered call returns hundreds of operations
4. Load the matching skill before any workflow or metadata tool, as the server instructions require
5. Batch up to 60 records a call to stay inside 100 requests a minute