Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search Substack publication posts

substack_publication_posts_search
Read-onlyIdempotent

Search posts inside a Substack publication using a query, then paginate results to find relevant articles and topics without browsing the publication manually.

Instructions

Search the posts inside a Substack publication. Requires publication and query. Returns a list (use page when paginated).

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": {
      "publication": "<publication>",
      "query": "<query>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "substack_publication_posts_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, 0 to 20; ten results a page.
queryYesRequired. Text to search for inside the publication.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
publicationYesRequired. A publication: its numeric id (`89120`), its Substack subdomain (`astralcodexten`), its host (`www.astralcodexten.com`) or its URL. A numeric id is refused with a 400 on the routes that need a subdomain, host or URL.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered without description help. The description's remaining behavioral content - that a list is returned and page should be used when paginated - largely restates the schema's page field (0-20, ten results a page). It adds nothing on ranking, result limits, or why page caps at 20.

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 scope, with no filler. The parenthetical about page is slightly redundant with the schema but harmless.

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 read-only search tool with no output schema, the description covers what is needed to call it but leaves search semantics (matching behavior, ordering, empty-result handling) unstated. Given six parameters including required context, llm_model, and conversation_id that are only explained in the schema, the description is minimally adequate rather than complete.

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%, and the schema already explains publication formats, query length, page range, and the analytics/context parameters in detail. The description only repeats the two required fields, adding no syntax or format detail beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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?

States a specific verb (search) and a scoped resource (posts inside a Substack publication), which separates it from broad search tools such as substack_search_top. It does not name any sibling explicitly, so the differentiation is implicit in the phrase 'inside a Substack publication'.

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?

The phrase 'inside a Substack publication' implies the when-to-use case (searching within one known publication rather than site-wide), but no alternative is named and no exclusion is stated. An agent must infer that substack_publication_posts_list is for unfiltered listing and the top-level search tools are for cross-publication search.

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