Skip to main content
Glama
paulet4a-commits

webdatatools-leads-mcp

by paulet4a-commits
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

yc_companies_scraper

Scrape Y Combinator company directory by batch, industry, status, or hiring status to collect company profiles and founder details in one row per company.

Instructions

Y Combinator company directory scraper — batch, industry, hiring status, one-liner, description and founder names/titles/LinkedIn/Twitter for every YC-funded startup, one row per company. Billed to your own Apify account: ~$0.002 per result (Apify free-plan price, lower on paid plans).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoMode — Pick "Browse companies" to list/filter the directory by batch, industry, status or hiring status, or "Search by keyword" to additionally match the query text against each company's name and description. Options: companies = Browse companies; search = Search by keyword.companies
queryNoSearch text — Enter keywords to match against the company name, one-liner and description, e.g. "AI agents". Only used when mode is "Search by keyword", or as an extra filter on top of the other fields in "Browse companies" mode. Leave empty to skip text search.
batchesNoBatches — Enter YC batch codes to keep, e.g. W25, S25, F26. Leave empty to include every batch. Codes are case-insensitive and matched exactly against the company's batch field.
isHiringNoIs hiring — Turn on to keep only companies currently marked as hiring on YC's directory, or leave this switch off (unset) to include both hiring and non-hiring companies. There is no third state for "only non-hiring" — untoggled means "do not filter".
statusesNoCompany statuses — Select which company statuses to keep. Leave empty to include every status (most companies are Active). Options: Active = Active; Acquired = Acquired; Public = Public; Inactive = Inactive.
industriesNoIndustries — Enter industry names to keep, e.g. B2B, Fintech, Healthcare. A company matches if it has at least one of the listed industries. Leave empty to include every industry.
maxCompaniesNoMax companies — Enter the maximum number of matching companies to return, e.g. 200. This is also the billed unit — the run stops as soon as it collects this many matches or runs out of companies to check.
includeFoundersNoInclude founders — Keep this on to fetch each matched company's public YC profile page and extract founder name, title, LinkedIn and Twitter/X links. Turning it off skips one extra request per company and returns founders as null, which is much faster for large runs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses billing to the user's own Apify account (~$0.002 per result), explains that maxCompanies is the billed unit, and notes that includeFounders triggers an extra profile request and can return null for speed. It does not cover authentication setup or rate limits, which keeps it from a 5.

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?

Two sentences, front-loaded with the purpose and output fields, followed by the cost model. Every phrase earns its place, and there is no redundant filler.

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?

No output schema exists, so the description usefully summarizes the return shape as 'one row per company' and lists the included fields; it also covers non-obvious cost behavior. It lacks details on auth/rate limits, but it is complete enough for selection given the rich input schema.

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 the schema already fully documents all 8 parameters with defaults, enums, and constraints. The description adds no parameter-level syntax or behavior beyond what the schema provides, making the baseline 3 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?

The description states a specific verb and resource: 'Y Combinator company directory scraper,' and enumerates the returned fields (batch, industry, hiring status, one-liner, description, founder details), so the agent knows exactly what it does and returns. It does not explicitly differentiate itself from siblings such as company_360 or hiring_signals, so it falls short of a 5.

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

Usage Guidelines2/5

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

It offers no when-to-use or when-not-to-use guidance relative to alternatives, and does not name or exclude any sibling tool. The mode and query options are parameter-level, not routing guidance, so an agent must infer its place in the toolset entirely from the resource name.

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