Trawlia

co.trawliaPublished by trawlia.cov0.1.0Updated Oct 24, 2026

Web search and page extraction for agents, returned as readable text rather than raw JSON.

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Lets an assistant run live web searches and pull readable text from pages it already has URLs for.

What you can do
Trawlia exposes two tools: trawlia_search returns ranked, deduplicated results from the live web, with options for search depth, news topic, result count, domain filters and time range; trawlia_extract fetches URLs you supply and returns their readable content with navigation, cookie banners and newsletter modals stripped. Results come back as readable text rather than raw JSON, and unreadable pages or unavailable sources are reported explicitly. Errors are plain sentences indicating whether a retry is worthwhile.
When to use it
Useful when an assistant needs current web information or the text of specific pages, such as research, fact-checking or summarising articles. It is not a crawler: there is no site-walking or long-running job to poll, so it is the wrong choice for crawling a whole site.
Requirements
Runs locally over stdio, typically via npx trawlia-mcp, so Node.js is needed. A Trawlia API key is required in the TRAWLIA_API_KEY environment variable; a free key gives 100 credits a month. TRAWLIA_BASE_URL is optional and defaults to the hosted API. Network access to the Trawlia API is required.
Before you install
TRAWLIA_API_KEY is a secret and is passed in the environment. Operations spend credits: basic search 1, advanced search 2, extraction 1 per 5 URLs, charged before the work and refunded on hard failure. Queries and URLs are sent to the Trawlia API, a third party. Omitting max_results can return 20 to 60 results into the model's context.

Installation

In SourceWeft

  1. Open Trawlia in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

trawlia-mcp

Trawlia as an MCP server: news search, web search and page extraction, as two tools any MCP client can call.

Get a free key at trawlia.co/signup - 1,000 credits a month, no card.

Claude Code

bash
claude mcp add trawlia --env TRAWLIA_API_KEY=twl_... -- npx -y trawlia-mcp

Claude Desktop, Cursor, and anything else reading a JSON config

json
{  "mcpServers": {    "trawlia": {      "command": "npx",      "args": ["-y", "trawlia-mcp"],      "env": { "TRAWLIA_API_KEY": "twl_..." }    }  }}

The tools

trawlia_search

Ranked, deduplicated results from the live web.

ArgumentDefaultNotes
queryrequiredNatural language, not keywords.
search_depthbasicbasic is 1 credit and returns snippets. advanced is 2 and returns full page text.
topicgeneralnews reaches news indexes and returns publication dates.
max_resultsallTop N of the ranked list. Left out, every result found is returned, typically 20 to 60. These go into your context, so set it when the task is narrow.
include_domains / exclude_domains-Host filters. Subdomains are included.
time_range-day, week, month, year.

trawlia_extract

Fetches URLs you already have and returns their readable content, with navigation, cookie banners and newsletter modals removed. 1 credit per 5 URLs, so pass the whole list at once.

What the model sees

Results come back as readable text rather than raw JSON, and carry two things a plain response would lose:

  • When a page could not be read, the result says so and why, instead of presenting a snippet as though it were the article.
  • A coverage line when a source was unavailable, so the model can weigh a thin result set properly rather than reporting it as a confident nothing.

Errors are readable sentences that say whether retrying is worth it. Running out of credits says so and says not to retry; a rate limit says how long to wait.

Costs

OperationCredits
Basic search1
Advanced search2
Extraction1 per 5 URLs

Charged before the work and refunded on hard failure. Full price list at trawlia.co/pricing.

Not available

Search and extraction, and nothing else. There is no crawler and no long-running job to poll. If your agent needs to walk a whole site, this is the wrong server for it.

Checking it works

bash
TRAWLIA_API_KEY=twl_... node smoke.mjs

Spends a few credits against the real API and prints what a client sees: the tool list, a rendered search, a rejected parameter, and an extraction. Not in CI, because it costs money and depends on the live web.

Environment

VariableRequiredNotes
TRAWLIA_API_KEYyesA search-scoped key is enough and is what you should deploy.
TRAWLIA_BASE_URLnoDefaults to https://api.trawlia.co. For pointing at a local server.

Source: README.md at commit 4ff57a1

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts