Leyline Sorcery
← Catalogue
appseed

TinyFish

Search, fetch, and browser automation for agents. Free Search and Fetch; metered browser runs. Leyline uses it as intake evidence crawl, not as a locked vendor.

MCP declaredAPI declaredCost freemiumLicence proprietary

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Plan with TinyFishOpen homepageRead docs

[ Observed sample ]

Frequency in Leyline's observed sample

The count is distinct observed stacks. It is not a Score input.

This component is not in Leyline's observed sample.

Record cmp_tinyfish

Open ranks

[ Score explain ]

Why the Score is 23

How Score works

Score v2 uses only observed signals. The displayed contribution is weight × value × 100. Missing factors are insufficient evidence.

Score factor

GitHub health

18% weight. A licence is declared. Documentation is available.

Value 0.30 · 5.4 points

18% weight × 0.30 value

5.4 points

A licence is declared. Documentation is available.

Score factor

Agent use

16% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Score factor

Human notes

14% weight. 1 stored human notes (component-record).

Value 0.09 · 1.2 points

14% weight × 0.09 value

1.2 points

1 stored human notes (component-record).

Score factor

Composability

16% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Score factor

Checklist

10% weight. An MCP surface is declared. An API is declared. Cost is freemium. 3 of 3 checklist fields are complete.

Value 1.00 · 10.0 points

10% weight × 1.00 value

10.0 points

An MCP surface is declared. An API is declared. Cost is freemium. 3 of 3 checklist fields are complete.

Score factor

Evidence quality

14% weight. 4 sources cover 3 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.

Value 0.49 · 6.8 points

14% weight × 0.49 value

6.8 points

4 sources cover 3 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.

Score factor

Benchmarks

12% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Total23.45 → 23 after rounding

Agent use: insufficient evidence

Composability: insufficient evidence

Benchmarks: insufficient evidence

[ Claims ]

Publisher-asserted record

Claims are what the publisher declares. Score uses observed signals, not these assertions, except for checklist fields derived from interfaces. MCP, API, cost, and license claims are marked verified, unverified, or contradicted from intake evidence.

Kind
app
Interfaces

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Functions

Function

Crawl

walk the public web

Crawl Browse Crawl

Function

Extract

pull a fact or field out

Extract Browse Extract

Function

Browser

operate a live page

Browser Browse Browser

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Observe

watch a system

Observe Browse Observe
Tags
Subject

subject

Automation

The tool runs or schedules multi-step workflows that call other tools.

Automation Browse Automation
Audience

audience

Agents

The product is built for software agents to call, not only for interactive humans.

Agents Browse Agents

[ Capability slices ]

Compose the useful parts.

extract

Extract

Search, fetch, and browser automation for agents. Free Search and Fetch; metered browser runs. Leyline uses it as intake evidence crawl, not as a locked vendor.

freemiumCompose with this
connect

Connect

Search, fetch, and browser automation for agents. Free Search and Fetch; metered browser runs. Leyline uses it as intake evidence crawl, not as a locked vendor.

freemiumCompose with this
observe

Observe

Search, fetch, and browser automation for agents. Free Search and Fetch; metered browser runs. Leyline uses it as intake evidence crawl, not as a locked vendor.

freemiumCompose with this

HTTP Search/Fetch plus MCP. Easy to plug as an evidence plane without owning the rest of a stack. Browser slice is optional and metered.

[ Relations ]

Derived alternatives and shared slots

  • Alternative to
    Firecrawl Shared functions connect, crawl, extract, search. Same kind and overlapping capability.
  • Fills the same slot as
    Context.dev Shared functions connect, crawl, extract, search. Can fill the same function slot.
  • Fills the same slot as
    VUDA (Visual UI Debug Agent) Shared functions browser, connect, crawl, extract, search. Can fill the same function slot.
  • Alternative to
    Exa Shared functions connect, crawl, extract, search. Same kind and overlapping capability.
  • Alternative to
    Browserbase Shared functions browser, connect, observe. Same kind and overlapping capability.
  • Alternative to
    cloro Shared functions extract, observe, search. Same kind and overlapping capability.
  • Alternative to
    Search1API Shared functions crawl, extract, search. Same kind and overlapping capability.
  • Fills the same slot as
    Playwright Shared functions browser, extract, observe. Can fill the same function slot.

[ Signals ]

Observed evidence and source claims

Signals carry source, method, and observedAt. Source review dates and evidence basis are shown separately. Unobserved metrics stay insufficient evidence.

TinyFish brings live web Search, clean Fetch, and Web Agent to ChatGPT, so your agent can find it, read it, and act on it.

Source: x.com

TinyFish brings live web Search, clean Fetch, and Web Agent to ChatGPT, so your agent can find it, read it, and act on it.

Source: x.com

TinyFish brings live web Search, clean Fetch, and Web Agent to Claude and Cowork, so your agent can find it, read it, and act on it.

Source: x.com
Suggest a correction

Propose a change with a public source. Corrections wait for review before the card changes.

[ Notes ]

humanNamed in Leyline concept as a crawl example beside Aside and Firecrawl — examples, not vendor lock.