Close

Limits

• The scope you grant is the real boundary. Tool descriptions telling the model to confirm before deleting are guidance to the model, not enforcement by the server. Grant mcp.read unless you need writes.
• No SSE. Close states it does not currently support SSE and asks affected teams to email support. Streamable HTTP only.
• n8n is read-only. Close's own n8n instructions carry a note that n8n supports only the mcp.read scope at this time.
• The directory listing understates the surface by 56 tools. A client or page sized on the 52-name snapshot will not know the connector reaches notes, tasks, comments, calls, meeting transcripts, custom objects or voice agents.
• perform_search is listed but undocumented. It appears in the directory snapshot and in no Close documentation we could find.
• Rate limits are per endpoint group, not published as one number. Close enforces limits per organization across all API keys, with a lower per-key limit — the organization limit is currently 3× the per-key limit. A 429 carries a RateLimit header with limit, remaining and reset; Close tells callers to sleep for the rate_reset value. Close publishes no MCP-specific figure, so the applicable numbers depend on which endpoint group a tool hits.
• Custom roles need the Scale plan. All plans include four predefined roles (Admin, Super User, User, Restricted User), but creating or editing roles is Scale-only. If you want a Close role narrower than Restricted User to back an MCP connection, that is a plan gate.
• We did not read the live tools and never called one. Our only contact with the server was an anonymous handshake that returned HTTP 401. Every statement above about tool behaviour comes from Close's documentation or Anthropic's directory listing, each dated below.

Frequently asked questions

Sources

• Close MCP server help article (retrieved 2026-08-18 via the .md variant Close serves). The documentation URL in Anthropic's directory, https://help.close.com/v1/docs/en/mcp-server, HTTP 308-redirects here; this is the current canonical path. Source for the endpoint, the three-scope header model, the client setup steps, the paid-Claude-plan requirement, the n8n read-only note and the two FAQ answers about SSE and the tool list. · retrieved 2026-08-18
• Close MCP Tools reference (retrieved 2026-08-18 via .md, ~29KB). The scope-to-tool mapping: 107 tools under three explicit scope headings, with Close's own description of each. Source for every per-tool behaviour claim on this page, including delete_lead, enrich_field and schedule_voice_agent_call. · retrieved 2026-08-18
• Close MCP server developer page (retrieved 2026-08-18 via .md). Source for the DCR statement, the per-scope one-line definitions, the multi-organization workaround and the third FAQ answer. · retrieved 2026-08-18
• Anonymous MCP initialize against https://mcp.close.com/mcp — HTTP 401 with WWW-Authenticate: Bearer error="invalid_token", error_description="Authentication required", resource_metadata="https://mcp.close.com/.well-known/oauth-protected-resource", retrieved 2026-08-18. This challenge is what establishes the OAuth posture. We never authenticated and never called a tool. · retrieved 2026-08-18
• Close's RFC 9728 protected-resource descriptor — — HTTP 200, retrieved 2026-08-18. Publishes scopes_supported of mcp.read, mcp.write_destructive, mcp.write_safe and offline_access, and names https://api.close.com/ as the authorization server. The /mcp-suffixed path returns the identical document. · retrieved 2026-08-18
• Authorization-server metadata — — HTTP 200, retrieved 2026-08-18. Advertises a registration_endpoint (dynamic client registration), code_challenge_methods_supported of S256 (PKCE), and the authorization_code and refresh_token grants. It publishes no scopes_supported field, so the scope claim on this page rests on the protected-resource descriptor, which RFC 9728 makes authoritative for this resource. · retrieved 2026-08-18
• Close API rate limits (retrieved 2026-08-18 via .md). Source for per-endpoint-group enforcement, the per-organization limit being 3× the per-key limit, the RateLimit header fields and the rate_reset guidance. · retrieved 2026-08-18
• Roles & Permissions — and (both retrieved 2026-08-18 via .md). Source for the four predefined roles, the Scale-plan gate on custom roles, and the list of higher-risk actions — bulk import, bulk email, export, merge, delete leads — that we then checked against both tool lists. · retrieved 2026-08-18
• API Keys & OAuth (retrieved 2026-08-18 via .md). Source for creating a key at Settings → Developer → API Keys, the one-time display, and the one-key-per-integration recommendation. · retrieved 2026-08-18
• Anthropic Connectors Directory entry — — the 55 listed entries (52 tools plus 3 scope markers), partner tier, endpoint, transport and category above are read from our committed directory snapshot dated 2026-08-16. The directory page itself blocks automated fetches, so we did not retrieve it directly. · retrieved 2026-08-16
• help.close.com/robots.txt and developer.close.com/robots.txt — both retrieved 2026-08-18, both Allow: / with only /api/fern-docs/ disallowed. developer.close.com additionally carries Content-Signal: ai-train=yes, search=yes, ai-input=yes — an explicit opt-in to AI synthesis, which is the basis on which this page restates Close's documentation. Both hosts publish an llms.txt index and serve clean Markdown by appending .md to any page URL. · retrieved 2026-08-18
• Close support — <mailto:support@close.com> · Security and privacy (retrieved 2026-08-18). Anthropic's directory files this URL as the connector's privacy_policy. The page's own title is "Close CRM Security & Privacy" and it covers SOC 2 Type 2, GDPR and encryption while *linking* to the privacy policy rather than being it — so it is a combined security-and-privacy overview, not the policy document itself. · retrieved 2026-08-18