Graunt

com.grauntPublished by graunt.comOfficial publisherv1.1.0Updated Oct 31, 2026

The agent-native marketplace for AI data: search listings and read their price and rights.

VerifiedStreamable HTTPWeb executableData & AnalyticsBusiness & CommerceMedia & Design

Overview

AI-generated overview

Graunt is a remote MCP server that lets an assistant search a marketplace of AI data packets and read their price, rights and files.

What you can do
  • Search the public catalog for data packets by keyword and get their ids, titles and public URLs
  • Read one packet's description, price, account requirement, seller-declared rights and URL, plus files for free packets that need no account
  • Search and read raw listing rows as Graunt's API returns them, paginated
  • Read manifests for a listing: agent commerce details, sha256-stamped asset manifest, and per-asset bundle inventory with file roles, formats, sizes and hashes
  • Read machine-readable metadata on Graunt's capabilities and the source types its Refinery accepts
  • Estimate how many hours of video meet a given spec and in which categories
When to use it
Useful when someone needs to find, evaluate or cite AI training or reference data from a marketplace, check licensing and rights before reuse, or gauge available video footage against a specification. It is read-only catalog access, not a purchase or download tool for paid data.
Requirements
A remote streamable HTTP endpoint at api.graunt.com; no package, environment variable or header is declared. Reading a person's owned packets requires the separate library connector and a sign-in with their Graunt account.
Before you install
Rights are seller-declared, so verify training, redistribution and citation terms before relying on a packet. Paid packets and those needing an account return no files; obtaining them happens at the packet's URL on graunt.com, outside this connection. Download links for free packet files are short-lived.

Installation

In SourceWeft

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

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.graunt%2Fmarketplace/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "graunt": {
      "type": "http",
      "url": "https://api.graunt.com/v1/mcp"
    }
  }
}

Tools

10

fetch

Read a Graunt packet

Read one Graunt catalog packet by id. Returns its title, description, price and whether an account is needed, its seller-declared rights, and its public URL. A free packet that needs no account also returns its files: small text files (CSV, JSON, Markdown, text and similar) in the text, and a short-lived download link for each listed file in metadata.files (at most 100 per fetch; files_not_listed counts the rest). Images, audio and video carry no link and download from the packet's public URL. A video listing also returns metadata.video: its subjects, measured hours, per-hour price with volume tiers, and the seller's declarations.

Parametersidrequired

search_assets

Search catalog listings

Search the public catalog and return listing rows as Graunt's API gives them (GET /v1/listings), paginated. To find data for a person, use search, then fetch.

Parametersqkindlimitcamera_viewai_generationvideo_subject

get_asset

Read a catalog listing

Read one listing by id as Graunt's API gives it (GET /v1/listings/{id}). To answer a question from a listing or cite it, use fetch.

Parameterslisting_idrequired

get_agent_commerce_manifest

Read a listing's commercial terms

Read the agent commerce manifest for a listing: price, rights, and how to buy it.

Parameterslisting_idrequired

get_asset_manifest

Read a listing's packet manifest

Read the canonical asset manifest (sha256-stamped).

Parameterslisting_idrequired

get_bundle_manifest

Read a bundle's file inventory

Read the per-asset bundle inventory: every delivered file with role, format, size and content hash, plus counts that name the population each one counted.

Parameterslisting_idrequired

meta_capabilities

Read what Graunt offers

Read /v1/meta/capabilities: what Graunt offers to an agent, in machine-readable form.

Takes no parameters.

meta_refinery_support_matrix

Read supported packet source types

Read /v1/meta/refinery-support-matrix: the source types Graunt accepts and what the Refinery does with each. Every upload gets deterministic extraction; a model drafts only the listing fields a seller leaves empty.

Takes no parameters.

match_video_spec

Count the hours of video that meet a spec

Find out how many hours of video on Graunt meet a spec, and in which categories. Give the requirements that matter (shortest side, frame rate, clip length, sound, on-screen text, overlays, first and last shots, freezes, slowed footage, releases, clearances, AI generation, uses, delivery); leave the rest out. Returns matching hours per category and per listing: hours that meet every requirement on recorded evidence, and hours that meet every requirement the evidence covers but lack evidence for one or more. Each listing carries its price, price per hour and volume tier, its delivery modes and where each number comes from. Thresholds snap to fixed steps and the answer says which were applied.

Parametersusesaudiolimitmin_fpsno_loopssubjectsno_slowedsublicensenative_onlycamera_viewsno_grayscaleorientations+24 more

Version history

3
  1. v1.1.0LatestOct 31, 2026
  2. v1.0.1Oct 31, 2026
  3. v1.0.0Sep 16, 2026

Score

83% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.