Nutshell vs Pipedrive 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.

Pipedrive API + MCP

Hosted MCP server on every plan, with actions recorded in the change log. MCP tool list not published, and the server is labelled beta.

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

Pipedrive API + MCP

1. Use v2 endpoints, which cost fewer tokens than v1
2. Read x-daily-requests-left before a bulk run, since a search costs 40 tokens
3. Send the token in the x-api-token header, never as api_token in the URL
4. Keep under 10 search requests per 2 seconds on every plan
5. Ask the user to load all Pipedrive tools in the client if an expected tool is missing