Skip to main content
Glama
thenavidm

substack-mcp

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

List and filter subscribers

list_subscribers
Read-onlyIdempotent

Retrieve and filter Substack subscribers using any column, with free-text search, sorting, and paging; use the total count to size segments before export.

Instructions

List subscribers, with the same filtering the Subscribers dashboard offers: 48 columns, free-text search, sorting and paging.

Returns {count, returned, limit, offset, subscribers}. count is the total matching the filters regardless of limit, so calling with limit: 1 is a cheap way to size a segment before pulling it.

Note: Substack takes the fields it returns from the publication's saved Display settings and ignores a per-request column list. Engagement columns can be filtered on here but are usually not present in the records that come back. Use export_subscribers to read their values.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoHow many to return. 1 to 100, default 25.
offsetNoSkip this many, for paging.
searchNoFree text matched against subscriber name and email.
filtersNoConditions, combined with AND. There is no OR and no nesting: anything needing OR has to be issued as separate calls. Operators by column type: - Int: is, is_not, gt, gte, lt, lte - String: is, is_not, is_any_of, contains, starts_with, ends_with, includes_none - DateTime: is_on, is_after, is_on_or_after, is_before, is_on_or_before - Array (tag_ids, emails_enabled): includes_any, includes_all, includes_none - subscription_type and group_membership: is, is_not, is_any_of Columns: user_name (String, "Name"); user_email_address (String, "Email"); country (String, "Country"); state (String, "State/Province"); group_membership (group_membership, "Group membership"); subscription_type (subscription_type, "Type"); subscription_created_at (DateTime, "Start date"); subscription_expires_at (DateTime, "Expiration date"); first_payment_at (DateTime, "First paid date"); last_subscribed_at (DateTime, "Paid upgrade date"); unsubscribed_at (DateTime, "Cancel date"); subscription_interval (String, "Subscription interval"); stripe_plan_name (String, "Stripe plan"); free_attribution (String, "Subscription source (free)"); paid_attribution (String, "Subscription source (paid)"); is_subscribed (Int, "Can see paid content"); bestseller_tier (Int, "Bestseller"); total_revenue_generated (Int, "Revenue"); num_subs_gifted (Int, "Subscriptions gifted"); bundle_id (Int, "Bundle"); is_bundle_parent (Int, "Bundle origin"); num_emails_received (Int, "Emails received (6mo)"); num_emails_dropped (Int, "Emails dropped (6mo)"); num_email_opens (Int, "Emails opened (6mo)"); num_email_opens_last_7d (Int, "Emails opened (7d)"); num_email_opens_last_30d (Int, "Emails opened (30d)"); num_unique_email_posts_seen (Int, "Unique emails seen (6mo)"); num_unique_email_posts_seen_last_7d (Int, "Unique emails seen (7d)"); num_unique_email_posts_seen_last_30d (Int, "Unique emails seen (30d)"); last_opened_at (DateTime, "Last email open"); links_clicked (Int, "Links clicked"); last_clicked_at (DateTime, "Last clicked at"); emails_enabled (Array, "Sections"); num_web_post_views (Int, "Post views"); num_web_post_views_last_7d (Int, "Post views (7d)"); num_web_post_views_last_30d (Int, "Post views (30d)"); num_unique_web_posts_seen (Int, "Unique posts seen"); num_unique_web_posts_seen_last_7d (Int, "Unique posts seen (7d)"); num_unique_web_posts_seen_last_30d (Int, "Unique posts seen (30d)"); num_comments (Int, "Comments"); num_comments_last_7d (Int, "Comments (7d)"); num_comments_last_30d (Int, "Comments (30d)"); num_shares (Int, "Shares"); num_shares_last_7d (Int, "Shares (7d)"); num_shares_last_30d (Int, "Shares (30d)"); days_active_last_30d (Int, "Days active (30d)"); activity_rating (Int, "Activity"); tag_ids (Array, "Tags")
sort_byNoAny column name to sort by.
publicationNoWhich connected publication to act on, matched loosely against its hostname (for example 'example.substack.com' or just 'example'). Defaults to the first connected publication.
sort_directionNodesc

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv3.0.1
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / filters / items / additionalProperties
      Removed value: -false
  2. First observedv2.1.1

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description is free to add high-value behavior: the exact return shape, that count is pre-limit, and the important gotcha that Substack ignores a per-request column list and returns records per saved Display settings, meaning engagement columns can be filtered but usually aren't returned. That is genuinely non-obvious behavioral context.

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?

Front-loads purpose, then return shape, then the sizing tip, then the caveat. Every sentence carries distinct information; there is no repetition of schema or annotation content and no filler.

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

Completeness5/5

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

With no output schema, the description supplies the return object shape and the count-vs-limit semantics itself, and it flags the Display-settings caveat that would otherwise silently mislead an agent. For a read-only, 7-param, non-required-param list tool, nothing essential is missing.

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

Parameters4/5

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

Schema coverage is 86% (baseline 3), and the description adds real meaning on top: it explains that limit interacts with the pre-limit count and that filtering on engagement columns works even though those columns are typically absent from results. It doesn't add syntax detail for sort/offset beyond what the schema states.

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 ('List subscribers') plus the scope ('the same filtering the Subscribers dashboard offers: 48 columns, free-text search, sorting and paging'). It also distinguishes itself from export_subscribers by assigning that tool the engagement-value reading job, so an agent can route between them without opening schemas.

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

Usage Guidelines4/5

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

Gives a concrete usage tip ('limit: 1' to cheaply size a segment) and names an explicit alternative ('Use export_subscribers to read their values'). It stops short of stating when NOT to use this tool (e.g. versus get_subscriber_count or list_subscriptions), so it is clear context without full exclusion guidance.

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

Deploy Server

Other Tools