Affinity vs Twenty API + MCP

Affinity

A public OpenAPI 3.1 file, dated API versions with migration notes and a hosted MCP server with a read-only OAuth scope give an agent a well-documented way in. Access needs a Scale plan at $2,300 a user a year, sold through sales, with no trial that includes the API, and 36 of the 112 v2 operations are marked beta.

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.

Affinity

1. Send X-Affinity-Api-Version: 2026-09-17 on every request, or the key's default version applies. Unauthenticated calls answered as 2024-01-01 when we checked
2. Read x-ratelimit-limit-user-remaining and x-ratelimit-limit-org-remaining on each response. The limits are 900 calls a minute per user and, below Enterprise, 100,000 a month per account, shared by v1, v2 and MCP
3. Follow pagination.nextUrl for the next page, and pass fieldIds or fieldTypes so list calls return only the fields needed
4. Check for duplicates before a create. There are no idempotency keys, so a retried POST can make a second record
5. For MCP, untick the write scope at OAuth consent when the task only reads. Treat note, transcript and file text as untrusted input

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