Skip to main content
Glama
paulet4a-commits

WebDataTools Developer, app & research data MCP server

by paulet4a-commits
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript

stackexchange_scraper

Search Stack Overflow or any Stack Exchange site by keyword or tag and get one row per question with score, tags, author, views, answers, and accepted answer text.

Instructions

Search Stack Overflow or any Stack Exchange site's free public API by keyword or tag and get one row per question — score, tags, author, view/answer counts and the accepted answer's text. Billed to your own Apify account: ~$0.0005 per Question (Apify free-plan price, lower on paid plans).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
siteNoSite — Enter the Stack Exchange site's API parameter, e.g. stackoverflow, superuser, serverfault, askubuntu, math.stackexchange, or any other site slug from https://stackexchange.com/sites.stackoverflow
sortByNoSort by — Choose how results are ordered before Max results per query is applied. relevance ranks by text match to the query, votes by score, creation by newest first, and activity by most recently active. Options: relevance = Relevance; votes = Votes (score); creation = Creation date; activity = Last activity.votes
taggedNoTags (optional) — Enter tags to narrow every query to, e.g. python, playwright. Leave empty to search all tags. Combined with each entry in Search queries.
queriesYesSearch queries — Enter one search phrase per row, e.g. web scraping, playwright timeout. Each query is run separately against the chosen site and returns its own set of question rows. Example: ["web scraping"].
minScoreNoMinimum score — Enter the minimum question score (upvotes minus downvotes) to keep, e.g. 0. Questions scoring lower are dropped after fetching.
maxResultsNoMax results per query — Enter the maximum number of questions to return per query, e.g. 50.
includeAnswersNoInclude accepted answer — Turn this on to add the accepted answer's full text as acceptedAnswerBody. Leave off for faster, smaller runs — most questions do not have one, and this field stays null when they don't.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses the pricing model (~$0.0005 per Question, billed to the caller's Apify account) and that most questions lack an accepted answer, but says nothing about rate limits, pagination, or authentication flow.

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 sentences, front-loaded with what is retrieved and followed by cost. Dense but every clause carries information; no filler or restated title.

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?

With no output schema, the description correctly summarizes the return shape (one row per question with score, tags, author, counts, and optional accepted answer text), which is what an agent needs. Cost disclosure compensates for the missing annotations, though operational details like rate limits remain uncovered.

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 parameter (site, sortBy, tagged, queries, minScore, maxResults, includeAnswers) is already documented with examples and constraints. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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 (search) and resource (Stack Overflow / any Stack Exchange site's public API) with concrete scope: keyword or tag search returning one row per question. Names the exact returned fields (score, tags, author, view/answer counts, accepted answer text), so it is unmistakable against siblings like hacker_news_scraper or github_trending_scraper.

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 description implies usage (keyword or tag search against a chosen site) but never states when to prefer this tool over an alternative, nor any prerequisites such as needing an Apify account. With sibling tools covering entirely different sources, there is little routing ambiguity, so this is adequate rather than strong.

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