mailfloss

Update connection settings

update_settings

Destructive

Partially update a connection's cleaning settings — manual_mode, autofloss, decay_protection, aggressiveness, per-check gates (PATCH /v1/integrations/{type}/connections/{id}). CHANGES THE ACCOUNT and can change which subscribers get removed. Omitted fields are left unchanged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "<type>",
      "id": "<id>"
    },
    "name": "update_settings"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Connection id.
`type`	Yes	ESP slug, e.g. `klaviyo`, `mailchimp`, `brevo`.
`action`	No	Set the auto-action mailfloss takes on invalid emails for this connection: `delete` (remove), `unsubscribe`, `do_nothing` (scan only), or `update_custom_fields` (auto-update the contact’s custom fields). The first three are not plan-gated; `update_custom_fields` is the "Auto-Update Attributes" feature and returns 403 unless the plan includes it (Pro) or the Auto-Update Attributes add-on is active. Returns 422 for ESPs that cannot perform the chosen action (e.g. `delete` on ConvertKit / MailerLite / Klaviyo / Moosend / Remarkety / Attentive; `unsubscribe` on ClickFunnels). The auto-action and Manual Mode are INDEPENDENT settings (as in the dashboard): setting an action leaves `manual_mode` unchanged, and the two may be sent together. The read shape additionally exposes `update_tags` (dashboard-only, not writable). Reads back as `settings.action`.
`checks`	No	Partial set of the 12 floss check gates to update. Each is optional; omitted gates keep their current value. Editing ANY gate switches the connection to `custom` aggressiveness. Unknown gate names are rejected.
`autofloss`	No	Toggle Autofloss (scheduled daily auto-import + clean) for this connection. Paid-plan feature: returns 403 on the free tier, and 422 for integrations that do not support Autofloss (e.g. beehiiv, clickfunnels). The resulting state reads back as `settings.autofloss`; Instafloss is the separate `settings.instafloss` flag.
`manual_mode`	No	Toggle Manual Mode for this connection. When enabled, addresses that fail verification are held for you to review/action in the dashboard instead of being auto-removed. Mode-independent — does not change the aggressiveness preset.
`aggressiveness`	No	Set the aggressiveness preset. "normal"/"aggressive" cascade canonical values to all 12 gates; "custom" detaches from a preset without changing gate values. Mutually exclusive with `checks` in one request.
`decay_protection`	No	Toggle Decay Protection (periodic re-verification of aging contacts) for this connection. Paid-plan feature: returns 403 on the free tier. Enabling resets any custom decay scheduling to the default. Reads back as `settings.decay_protection`.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds the concrete consequence that the tool CHANGES THE ACCOUNT and can alter which subscribers get removed, plus partial-update semantics. It does not cover error behavior (403/422) in the prose, but that is documented in the schema fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero waste: the verb and target are front-loaded, the field list signals scope, and the destructive consequence follows immediately. Nothing is redundant with the schema descriptions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, nested-object mutation with no output schema, the description plus rich schema and destructive annotation give an agent what it needs to call correctly. A small gap remains: it doesn't mention the mutual exclusivity or gate/preset interaction that the schema documents, but the schema carries that burden.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains each parameter in depth, including plan gating and ESP restrictions. The description only enumerates the top-level field names (manual_mode, autofloss, decay_protection, aggressiveness, per-check gates), adding little beyond what structured data provides; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Partially update a connection's cleaning settings'), names the exact fields touched, and includes the endpoint path. It is clearly distinguishable from siblings like get_connection or disconnect_integration.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Partially update' and 'Omitted fields are left unchanged' imply the patch-style usage, and the warning about which subscribers get removed hints at stakes. However, it never states when to choose this over a sibling (e.g., disconnect_integration for turning things off) or any preconditions/alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All mailfloss tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?