Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search Stack Overflow questions

stack_overflow_questions_search
Read-onlyIdempotent

Search Stack Overflow questions and answers by keywords, tags, author, or answer count to find relevant snippets and filter technical discussions.

Instructions

Search Stack Overflow questions and answers by words, title, body, tag, author or answer count, with snippets. Optional inputs: site, q, title, body, tagged and 14 more. Returns a list (use cursor 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": {
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "stack_overflow_questions_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoFree text to find in titles, bodies and tags.
bodyNoText that must be in the question body.
modeNo`full` (default) returns questions. `excerpt` returns the questions and answers that match, each with a highlighted snippet.
siteNoStack Exchange site, by its API name (`askubuntu`, `serverfault`, `math`, `ru.stackoverflow`). Default: `stackoverflow`. The sites endpoint lists them all.
sortNoOrder: `relevance` (default), `creation` (the only one that pages without a ceiling), `activity` or `votes`. Ties can repeat or skip rows.
userNoOnly questions asked by this user id.
limitNoUp to this many rows per page, 1 to 100. Default: 30. A page can hold fewer than `limit` rows where rows share a creation second or a block of 100 rows ends. Follow `page.nextCursor` until `hasMore` is false.
orderNoDirection of the sort: `desc` (default) or `asc`.
titleNoText that must be in the title.
closedNo`true` for closed questions, `false` for open ones.
cursorNoCursor from `page.nextCursor` of the previous response. It only works with the same filters.
taggedNoOnly questions that carry all of these tags, comma-separated, up to 5.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
includeNo`body` adds the question text (HTML and Markdown) to each row in `full` mode. Default: none.
acceptedNo`true` for questions with an accepted answer, `false` for those without.
viewsMinNoOnly questions with at least this many views.
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.
notTaggedNoLeave out questions that carry any of these tags, comma-separated, up to 5.
answersMinNoOnly questions with at least this many answers.
createdAfterNoOnly questions asked at or after this time, as an ISO 8601 date or time (such as `2026-01-31`) or epoch seconds. A time with no zone is UTC.
createdBeforeNoOnly questions asked before this time, as an ISO 8601 date or time (such as `2026-01-31`) or epoch seconds. A time with no zone is UTC.
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

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds that results come back as a list with snippets and that pagination uses a cursor, but it says nothing about rate limits, quota costs, or what 'excerpt' mode actually changes in the payload.

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?

Three short sentences with the capability stated first and the pagination note last. The 'and 14 more' clause is low-value filler but does not bloat the definition meaningfully.

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 a 22-parameter search tool with no output schema, the description establishes scope, the optional-parameter-heavy shape, the list return and cursor pagination, which is enough for correct invocation since the schema carries the rest. It is slightly thin on the full-vs-excerpt mode distinction, which materially affects results.

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 every one of the 22 parameters is already documented with examples, enums and defaults. The description spends its words on a partial enumeration ('site, q, title, body, tagged and 14 more') that adds no semantics beyond the schema, so the baseline of 3 is appropriate.

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 and resource ('Search Stack Overflow questions and answers') and enumerates the searchable surfaces (words, title, body, tag, author, answer count) plus the snippet behavior. That scope implicitly separates it from the narrower title-only sibling, though it never names an alternative explicitly.

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?

Describes the tool as a multi-field search and notes the cursor for pagination, which implies when to reach for it over a plain listing. It stops short of explicit when-not guidance relative to stack_overflow_questions_title_search or stack_overflow_questions_list, leaving that inference to the agent.

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