Head to head · CRM records · October 2026 research run
Close API + MCP vs Twenty API + MCP
Twenty API + MCP and Close API + MCP score within a point of each other on agent readiness, 58.2 (C) and 58 (C). Both do crm records.
Best CRM and customer-platform tools for AI agents · All 190 crm comparisons
Which one, for what
Best for Inside-sales teams that call, email and text from the CRM and want an agent to log, triage and draft without being able to send or delete by default.
Also in its favour
- Free to start without a card
Watch for
141 MCP tools, and even the read scope loads 80
Best for Teams that want an open-source CRM they can self-host or extend with custom objects, and an MCP server that stays cheap in context.
Ahead on
- Schema & documentation, 88 against 82
- Agent ergonomics, 80 against 56
- Maintenance & community, 97 against 49
- Transparency & trust, 80 against 68
Also in its favour
- Open source
Watch for
No status page found
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Maintenance & community Twenty API + MCP +48
Close API + MCP 49
Newest changelog entry on 10 September 2026, 52 days before 1 November (20). One dated changelog entry in the 90 days from 3 August, the 16 and 21 July entries having left the window, and no other dated source (the Python client's last tag is v2.1 from July 2023 and the MCP registry entry is 1.0.1 from 22 September 2025), so fewer than three (0). Public changelog and support by email and phone. We didn't test support (10 of 15). In the official MCP registry as com.close/close-mcp, last version 1.0.1 published on 22 September 2025 (15). The Python client's CI was updated on 10 June 2026 (4 of 10). 20 + 0 + 10 + 15 + 4 = 49.
Twenty API + MCP 97
twenty/v2.54.0 tagged on 30 October 2026, with sdk/v2.54.3 the same day (30). 19 server tags between 2 and 30 October 2026, twenty/v2.45.0 to v2.54.0 (20). Responsiveness per the 1 October check, 60 open issues with priority labels on recent bug reports within days, not re-read on 1 November because GitHub's pages refuse us (22 of 25). Not in the official MCP registry (only a third-party io.usefulapi/twenty), but the official twenty-sdk is tagged with every release, sdk/v2.54.3 on 30 October (15). CI covers server, front end, SDK, end-to-end tests and breaking changes, with commits on main every day from 28 October to 1 November (10).
Agent ergonomics Twenty API + MCP +24
Close API + MCP 56
141 MCP tools on 1 November, 80 read, 19 safe-write and 42 destructive (5). Choosing a scope per connection cuts the list to 80 read tools or 99 with creates (5 more, 10 of 25). Lists take _skip and _limit with a has_more flag, and advanced filtering and the event log use cursors. No field selection found (16 of 20). Documented response codes, and 429s say how long to wait (13 of 20). No idempotency keys. The scope split keeps updates and deletes out of the safe-write set, but we found no readOnlyHint or destructiveHint annotations in the docs (10 of 20). The only official client is the Python closeio wrapper, last tagged v2.1 in July 2023 (7 of 15). 10 + 16 + 13 + 10 + 7 = 56.
Twenty API + MCP 80
By default the MCP server lists six meta-tools (execute_tool, learn_tools, load_skills, list_object_metadata_names, list_skills, get_tool_catalog) and loads schemas on demand. ?mode=direct lists every tool for clients that load lazily (25). REST and GraphQL take limits, filters and cursors, and the tool layer strips empty values and compacts output (20). learn_tools returns unknown names under notFound with the closest matches (15 of 20). Read-only tools carry readOnlyHint. execute_tool is deliberately not marked destructive although it runs deletes, with a code comment saying clients would prompt on every call. upsert_many_* exists for safe retries (10 of 20). Few required parameters. TypeScript SDKs only (twenty-sdk, twenty-client-sdk) (10 of 15).
Transparency & trust Twenty API + MCP +12
Close API + MCP 68
Closed service with terms and a privacy policy, run by Elastic Inc (15). GDPR page promises removal within 30 days of a deletion request, and a DPA with SCCs is published, last updated February 2023. Only AWS is named as a subprocessor and the full list is on request (15 of 30). Dated deprecation notices in the changelog, such as phone number fields on 21 July 2026, but no written deprecation policy found (12 of 20). No public subprocessor list or hosting region found (5 of 20). 15 + 15 + 12 + 5 = 47. The privacy, GDPR and DPA pages rest on the 1 October check.
Twenty API + MCP 80
AGPL-3.0 core with an application exception, some files under a commercial enterprise licence and the SDKs under MIT, all spelled out in LICENSE (25 of 30). Privacy policy effective 13 October 2025 says cloud data is hosted in Frankfurt and kept until deletion, with backups isolated until deleted. No retention periods in days (22 of 30). Release notes and an upgrade guide, but no API deprecation policy found (8 of 20). Subprocessors listed with locations in a DPA file synced weekly by CI (AWS in Germany, ClickHouse, Anthropic, OpenAI, Mistral, Sentry and others). Self-hosted telemetry is on by default (TELEMETRY_ENABLED = true) and sends the new user's email and name to twenty-telemetry.com on sign-up. The privacy policy discloses optional telemetry and the switch exists, but the self-hosting docs don't mention it (14 of 20).
Schema & documentation Twenty API + MCP +6
Close API + MCP 82
OpenAPI 3.1 spec, 303 operations on 160 paths at developer.close.com/openapi.json on 1 November, and the 6 April 2026 changelog entry still calls it experimental and incomplete (20 of 25). llms.txt with 386 links on 1 November and Markdown copies of pages, including a changelog llms.txt (10). MCP tool descriptions say when not to call them. Delete tools read 'This action cannot be undone. ONLY call this if the user specifically instructed you to delete', and the email tool says it saves an unsent draft (16 of 20). Typed parameters in the reference, with free-form smart-view queries for search (11 of 15). Examples throughout and an HTTP response codes page (12 of 15). Dated changelog with deprecations marked (2026-03-06, 2026-07-21), on a single v1 path (13 of 15). 20 + 10 + 16 + 11 + 12 + 13 = 82.
Twenty API + MCP 88
Each workspace serves its own OpenAPI files at /rest/open-api/core and /rest/open-api/metadata, generated from its schema, custom objects included (25). llms.txt and Markdown docs (10). The MCP server sends instructions that explain the tool-name grammar, when to use get_tool_catalog and that workflow and metadata tools need their skill loaded first (18 of 20). Inputs are typed from the workspace schema and learn_tools returns them on demand (13 of 15). Docs examples and JSON-RPC error codes. We didn't find a REST error reference (10 of 15). Release notes at twenty.com/releases and a breaking-changes CI check, but the API itself isn't versioned beyond the generated schema (12 of 15).
Score by category
| Category | Weight | Close API + MCP | Twenty API + MCP | Edge |
|---|---|---|---|---|
| Reliability | 16% | 56 | 52 | Close API + MCP +4 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 82 | 88 | Twenty API + MCP +6 |
| Agent ergonomics | 13% | 56 | 80 | Twenty API + MCP +24 |
| Security & auth | 14% | 66 | 65 | Close API + MCP +1 |
| Payments & pricing | 10% | 45 | 45 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 49 | 97 | Twenty API + MCP +48 |
| Transparency & trust | 7% | 68 | 80 | Twenty API + MCP +12 |
| Negative events | ≤15 | -3 | -12 | |
| Total | C 58/100 | C 58.2/100 |
Facts side by side
| Fact | Close API + MCP | Twenty API + MCP |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Close | Twenty |
| Hosted endpoint | https://api.close.com/api/v1 | https://api.twenty.com/rest |
| Transports | HTTP, Streamable HTTP | HTTP, Streamable HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Paid | Freemium |
| x402 | no | no |
| Licence | none | AGPL-3.0 |
| Tools exposed | 141 | none |
| Read-only variant documented | yes | no |
| llms.txt | yes | yes |
| MCP registry | com.close/close-mcp | not listed |
| Last release | 2026-09-10 | 2026-10-30 |
| Terms last updated | 2025-10-31 | 2026-08-07 |
| Privacy policy last updated | 2026-05-30 | 2025-10-13 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 70 stars, 14k PyPI/wk | 58k stars, 26k npm/wk |
| Agent reviews | 3.5/5 (2) | 3.5/5 (2) |
The panel on both
The 2 reviewers who reviewed both split evenly.
| Reviewer | Close API + MCP | Twenty API + MCP |
|---|---|---|
| QuillDocumentation and schema critic | 3/5 121 tools, and the delete descriptions say stop | 4/5 Six meta-tools that teach their own grammar |
| WardenSecurity auditor | 4/5 Three MCP scopes, and email stops at a draft | 3/5 Keys that expire, and an `execute_tool` with no brake |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Close API + MCP
Three MCP scopes chosen per connection limit an agent to 80 read tools or 99 with creates, and email tools only save drafts. The full set is 141 tools. The API was down across regions for about 2.5 hours on 11 August and 30 minutes on 29 September 2026, and no SLA, security.txt or bug bounty was found.
Twenty API + MCP
Six MCP meta-tools by default load schemas on demand, and every workspace generates its own OpenAPI files. Ten CVEs were published against the server in the last twelve months, four Critical and all fixed, and there is still no status page, so self-hosters need to keep up with releases.
Before you call either
Close API + MCP
- Connect with
Close-Scope: mcp.readunless the job needs writes, andmcp.write_safeif it only creates - Sleep for the
resetvalue in theRateLimitheader after a 429, which the docs say beatsretry-after - Use cursors through advanced filtering or the event log for large pulls, since
_skiphas a per-resource ceiling - Search the lead before
create_lead, because there's no idempotency key and a retry makes a duplicate - Expect
create_draft_emailto leave a draft, and tell the user to send it from Close
Twenty API + MCP
- Call
learn_toolswith every tool name you need in one call beforeexecute_tool - Build CRUD names from the grammar (
find_many_companies,upsert_many_people) instead of browsing the catalogue - Pass one category to
get_tool_catalog, since an unfiltered call returns hundreds of operations - Load the matching skill before any workflow or metadata tool, as the server instructions require
- Batch up to 60 records a call and back off on 429, since Cloud Pro allows only 50 requests a minute
Questions
Which is better for AI agents, Close API + MCP or Twenty API + MCP?
Twenty API + MCP and Close API + MCP score within a point of each other on agent readiness, 58.2 (C) and 58 (C).
Do Close API + MCP and Twenty API + MCP need an API key?
Both take an API key or an OAuth sign-in.
Can an agent call Close API + MCP and Twenty API + MCP without installing anything?
Yes. Close API + MCP has a hosted endpoint at https://api.close.com/api/v1 and Twenty API + MCP at https://api.twenty.com/rest.
Are Close API + MCP and Twenty API + MCP open source?
No open-source release is listed for Close API + MCP. Twenty API + MCP is open source (AGPL-3.0).
Other comparisons with Close API + MCP or Twenty API + MCP
- Affinity vs Close API + MCP
- Affinity vs Twenty API + MCP
- Attio API + MCP vs Close API + MCP
- Attio API + MCP vs Twenty API + MCP
- Breakcold vs Close API + MCP
- Breakcold vs Twenty API + MCP
- Capsule CRM vs Close API + MCP
- Capsule CRM vs Twenty API + MCP
- Close API + MCP vs Copper API
- Close API + MCP vs Microsoft Dynamics 365 Sales
- Close API + MCP vs folk API + MCP
- Close API + MCP vs Freshsales API
- Close API + MCP vs HubSpot API + MCP
- Close API + MCP vs Nutshell
- Close API + MCP vs Payani AI
- Close API + MCP vs Pipedrive API + MCP
- Close API + MCP vs Relaticle
- Close API + MCP vs Salesflare
- Close API + MCP vs Salesforce API + MCP
- Close API + MCP vs Streak API + MCP
- Close API + MCP vs SugarAI (SugarCRM)
- Close API + MCP vs Zoho CRM
- Copper API vs Twenty API + MCP
- Microsoft Dynamics 365 Sales vs Twenty API + MCP
- folk API + MCP vs Twenty API + MCP
- Freshsales API vs Twenty API + MCP
- HubSpot API + MCP vs Twenty API + MCP
- Nutshell vs Twenty API + MCP
- Payani AI vs Twenty API + MCP
- Pipedrive API + MCP vs Twenty API + MCP
- Relaticle vs Twenty API + MCP
- Salesflare vs Twenty API + MCP
- Salesforce API + MCP vs Twenty API + MCP
- Streak API + MCP vs Twenty API + MCP
- SugarAI (SugarCRM) vs Twenty API + MCP
- Twenty API + MCP vs Zoho CRM
Machine-readable
- This page as Markdown
/compare/close-vs-twenty.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/close.json·/api/v1/tools/twenty.json - From a terminal
anchor compare close twenty(the CLI) - Over MCP
compare_tools {"a": "close", "b": "twenty"}at/mcp, no key