substack-saved-mcp

Overview Schema Source Related Servers Discussions Admin

sync_saved_posts

Sync saved Substack posts into a local SQLite cache for offline reading, search, and bookmarking. Use incremental updates by default or force a full refresh to reconcile posts no longer saved.

Instructions

Trigger incremental or full resync of saved posts from Substack account into local SQLite cache.

Incremental (default) stops early once it reaches already-cached posts, so older posts' reading progress isn't refreshed. force=True fetches the whole list, refreshes every post, and soft-deletes local posts no longer saved on Substack. Returns a SyncRun whose status is 'success', 'partial' (the fetch was truncated, e.g. by rate limiting, and reconciliation was skipped), 'auth_required' (run 'substack-saved-mcp login'), or 'failed'. Requires an active authenticated Substack session and can take minutes on large accounts.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`force`	No

Output Schema

TableJSON Schema

Name	Required	Default
`id`	No
`entity`	No	post
`status`	Yes
`sync_mode`	No	incremental
`started_at`	Yes
`completed_at`	No
`error_message`	No
`fetched_count`	No
`upserted_count`	No
`reconciled_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.3.0Aug 19, 2026
- addedOutput schema / properties / entity
```
Added value: +{
+  "default": "post",
+  "type": "string"
+}
```
First observedv0.1.0Aug 2, 2026

TDQS

A4.7/5.0

Behavior5/5

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

No annotations exist, so the description carries the full burden and does so well: it discloses the soft-delete of posts no longer saved on Substack under force, the auth prerequisite plus remediation ('substack-saved-mcp login'), the rate-limiting/truncation behavior reflected in 'partial', and that runs can take minutes. These are exactly the behavioral traits an agent needs and none are derivable from structured fields.

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?

The core action is front-loaded in the first sentence, followed by mode behavior, return statuses, and prerequisites in a logical order. It is on the longer side and the status enumeration is verbose, but nearly every sentence earns its place given the mutation semantics.

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?

Even though an output schema exists (so return values need not be documented), the description still names the SyncRun status values and their meanings, which helps the agent interpret partial/auth failures. Combined with the covered prerequisites and side effects, nothing essential for correct invocation is missing.

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

Parameters5/5

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

Schema coverage is 0% and the single parameter has no schema description, so the description must compensate. It fully explains both values of force: default incremental stops early and leaves older reading progress stale, while force fetches the whole list, refreshes every post, and soft-deletes removed ones. That is richer meaning than the schema's bare boolean-plus-default.

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 (resync/sync) and resource (saved posts from Substack into local SQLite cache). The resource is precise enough to distinguish it from the sibling sync_saved_notes and from the read-oriented list_saved_posts. An agent can identify the operation without opening the schema.

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?

Explicitly frames the two modes and when to pick each: incremental is the default that stops at already-cached posts, force=True refreshes everything. It does not, however, contrast usage against sibling tools (e.g. when to sync vs. read), so it stops short of the alternative-routing that a 5 requires.

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

Deploy Server