Skip to main content
Glama
thenavidm

Flodesk MCP Server

by thenavidm

Save one private subscriber page

save_subscriber_page
Destructive

Writes one requested page of Flodesk subscribers to a new JSON file with 0600 permissions, using filters for status, segment, account, and page; no overwrite or all-pages export.

Instructions

Confirmed one-page GET saved only to an exclusive new0600 JSON file. No CSV/cohort export, all-pages loop, overwrite, automatic upload or browser preview.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoThe page number. Defaults to 1.
statusNoOptional. The subscriber's status. `active`: The subscriber is currently active to receive marketing emails. `unsubscribed`: The subscriber has opted out of marketing emails. `unconfirmed`: The subscriber is pending for double opt-in confirmation. `bounced`: The subscriber's address is undeliverable due to a hard bounce. `complained`: The subscriber marked an email as spam. `cleaned`: The subscriber was cleaned, learn more [here](https://help.flodesk.com/en/articles/4747969#how_can_i_find_out_which_email_addresses_have_been_cleaned). `archived`: The subscriber was archived.
accountNoExact configured private account profile label; not a tenant or provider account ID.
confirmNoExplicit approval for this exact requested ordered batch.
per_pageNoThe number of records to be returned on each page. Defaults to 20. Maximum 100.
segment_idNoOptional. The segment's id. When included, returns only subscribers who were added to the given segment.
output_fileYesAbsolute new file in an existing private directory. Restrict Windows ACLs separately.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this writes to disk. The description adds that only one page is fetched and no overwrite/upload/preview occurs, which is useful. However, it doesn't explain the 'confirm' approval flow or what happens on existing files beyond 'no overwrite'.

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

Conciseness4/5

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

Two short sentences, front-loaded with the core action and scoped by exclusions. The wording is dense but not padded; no sentence is wasted.

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

Completeness3/5

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

For a 7-parameter write tool with no output schema, the description covers scope but omits return format, error behavior, and the meaning of the critical 'confirm' gate. It is adequate but leaves gaps an agent would need to infer.

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 coverage is 100%, so every parameter is already documented in the schema. The description adds no parameter-level syntax or behavior beyond the schema, which is the expected baseline when structured fields do the heavy lifting.

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

Purpose4/5

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

The description states a specific verb and resource: a confirmed GET that saves one page to a private JSON file. It distinguishes itself from export/batch siblings, though the phrasing is compressed and slightly cryptic.

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?

It implies a narrow use case via exclusions ('No CSV/cohort export, all-pages loop, overwrite'), but it never states when to choose this over sibling tools like list_subscribers or preview_subscriber_batch. Usage context is implied rather than explicit.

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