Grounder

io.github.rozetypPublished by GitHub account rozetypv0.4.1Updated Oct 24, 2026

Web grounding for local & cloud LLMs: search, fetch, token-capped evidence packs, and research.

The publisher's own server: Grounder - Licensed Meta Grounding Service

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Gives an assistant live web grounding: search, page fetching, cited evidence packs, and open-ended research via a hosted service.

What you can do
Grounder is a thin stdio client for a hosted web-grounding service, exposing four tools. web_search returns organic results with people-also-ask, related searches, and a knowledge graph; fetch returns one page as clean markdown capped to a token budget plus the final URL after redirects; deep_search reads across the pages a search surfaces and ranks them into a token-capped, cited evidence pack with an optional grounded answer; research plans, reads primary sources, and reasons to a grounded conclusion for open questions. Results are token-capped so they fit small context windows.
When to use it
Use it when an assistant needs current web information beyond its training cutoff, especially with a small local model whose context window would overflow on raw pages. It suits quick lookups, cited evidence gathering, and open-ended research questions with no ready-made answer.
Requirements
Runs locally as a Python package (uvx grounder-mcp or pip install grounder-mcp) over stdio and needs network access to the hosted service. The GROUNDER_API_KEY environment variable is optional: without it the server uses a shared demo key, and a free key from the provider raises the limit to 1,500 pages per month. Desktop MCP clients only.
Before you install
The optional GROUNDER_API_KEY is a secret and should be supplied through the environment, not committed to config files shared with others. Queries and fetched page content are sent to the third-party hosted service; the README states query content is not stored. Paid tiers exist (Starter and Pro) if the free page allowance is exceeded, so check usage limits before relying on it.

Installation

In SourceWeft

  1. Open Grounder 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

Grounder MCP

Live web grounding for local and cloud LLMs, as four MCP tools. Every model is frozen at its training cutoff; Grounder gives yours the current web - ranked results, real page content, and a cited evidence pack sized to your context window.

A thin stdio client for the hosted service at https://grounder.dev - no browser, no scraper, nothing heavy runs locally. It runs with no signup on a shared demo key; add your own free key (1,500 pages/month, no card) at grounder.dev for real use.

Install

bash
uvx grounder-mcp          # or: pip install grounder-mcp

Configure

Claude Desktop, Cursor, LM Studio, Continue.dev, or any MCP client. The key is optional - omit it to try Grounder on the shared demo key, or add your own free key from grounder.dev:

json
{  "mcpServers": {    "grounder": {      "command": "uvx",      "args": ["grounder-mcp"],      "env": { "GROUNDER_API_KEY": "gnd_live_your_key" }    }  }}

The four tools

ToolWhat it does
web_searchGoogle organic results plus people-also-ask, related searches, and the knowledge graph. The top snippet often already holds the answer.
fetchOne page as clean markdown, capped to your token budget, plus the final URL after redirects.
deep_searchOne search, read across the pages it surfaces, ranked into a token-capped, cited evidence pack. Optional grounded answer.
researchInvestigates an open question with no ready-made answer: it plans, reads primary sources, notices what is missing, goes back for it, and reasons to a grounded conclusion.

Why use it

  • It fits a small context window. Results come back token-capped, so they slot into an 8-32k local model instead of overflowing it. A few raw pages can be 20,000+ tokens (we measured 22,759 for one query) - enough to make a small model return nothing. You get the relevant passages, not whole pages.
  • The live page, not a cached copy. fetch reads the actual current page; any caching is short, timestamped, and force-refreshable.
  • Flat monthly price, billed in pages. You only pay for pages actually delivered. No per-call metering.
  • No query content stored. Ever.

Pricing

Free: 1,500 pages/month, no card. Starter $9/mo, Pro $19/mo. Full table at https://grounder.dev/pricing.

Source: README.md at commit 124bf0c

Tools

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

Version history

1
  1. v0.4.1LatestSep 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

Other Grounder integrations

Grounder - Licensed Meta Grounding Service

net.grounderOfficial publisher

Remote MCP web search service that runs one query across 10 providers and returns deduplicated results with licensed sources flagged.

Streamable HTTPWeb executableAuth
Web Search & ScrapingCredential requiredOct 27, 2026