Graunt
Server Details
The agent-native marketplace for AI data: search listings and read their price and rights.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 10 tools
search and search_assets overlap heavily: both search the public catalog, with only a raw-API vs human-facing distinction. fetch and get_asset also both read a listing by id, though the descriptions explicitly steer agents to fetch for answering or citing.
The tool set is mostly predictable snake_case, with clear get_, search_, and meta_ families. The main deviation is the bare verb fetch alongside get_asset, which creates a minor naming inconsistency for similar read operations.
Ten tools is well-scoped for a catalog discovery, retrieval, manifest, and video-spec matching server. Each tool has a plausible place, and there is no obvious padding.
The surface covers search, fetching listings, several manifest variants, video spec matching, and metadata. Minor gaps remain around retrieving pool-specific details and taking actions such as adding to cart or opening a buyer request, though the latter is partly handled by returned URLs.
Available Tools
10 toolsfetchRead a Graunt packetARead-onlyInspect
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). A video listing also returns metadata.video: its subjects, measured hours, the price and what it comes to per hour, and the seller's declarations.
Inputs: id (required). Returns: id, url, text, title, +1 more
get_agent_commerce_manifestRead a listing's commercial termsARead-onlyInspect
Read the agent commerce manifest for a listing: price, rights, and how to buy it.
Inputs: listing_id (required).
get_assetRead a catalog listingARead-onlyInspect
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.
Inputs: listing_id (required).
get_asset_manifestRead a listing's packet manifestBRead-onlyInspect
Read the canonical asset manifest (sha256-stamped).
Inputs: listing_id (required).
get_bundle_manifestRead a bundle's file inventoryBRead-onlyInspect
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.
Inputs: listing_id (required).
match_video_specCount the hours of video that meet a specARead-onlyInspect
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 list price and any rate per hour and volume tier it is stored with, its hours per category with what each category alone costs where it sells by category, the spec's categories priced as one order, its delivery modes and where each number comes from. Thresholds snap to fixed steps and the answer says which were applied. Give hours_wanted to also get a proposal: whole listings across sellers that reach those hours on recorded evidence, lowest price per measured hour first, each at its seller's own price, for the person you work for to add to their cart. Nothing is held, and short_units is the gap the proposal leaves, not a statement about what Graunt holds.
Inputs: q, uses, audio, limit, +34 more.
meta_capabilitiesRead what Graunt offersBRead-onlyInspect
Read /v1/meta/capabilities: what Graunt offers to an agent, in machine-readable form.
Inputs: no named parameters.
meta_refinery_support_matrixRead supported packet source typesARead-onlyInspect
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.
Inputs: no named parameters.
searchSearch the Graunt catalogARead-onlyInspect
Search Graunt's catalog of evaluated data from many sellers. Returns matching packets with their id, title, and public URL. Start here to find data, then read one with fetch. search_match.words says how the listings matched the query: ALL (every word, or a synonym of it), SOME (some of the words), WORD_START (words that start with the query's words), SIMILAR_TITLE (titles spelled like the query) or NONE (no listing). On SOME and WORD_START each listing names its matched_words. Each result's type is listing or pool, and search_match describes only listings. Pools use a separate keyword matcher over their public descriptions and data types. When no listing matches, next_steps.post_request_url opens a buyer request with the query filled in.
Inputs: query (required), kind, limit, camera_view, +7 more. Returns: results, next_steps, search_match
search_assetsSearch catalog listingsARead-onlyInspect
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. search_match.words says how the listings matched the query: ALL (every word, or a synonym of it), SOME (some of the words), WORD_START (words that start with the query's words), SIMILAR_TITLE (titles spelled like the query) or NONE (no listing). On SOME and WORD_START each listing names its matched_words. When no listing matches, next_steps.post_request_url opens a buyer request with the query filled in.
Inputs: q, kind, limit, camera_view, +7 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Marketplace for AI agents: goods, collectibles, real estate and services. List, search, offer, deal.
Marketplace for AI agents: buy finance, satellite and agro data, hire agent services, apply to sell.
Marketplace where AI agents buy datasets and API access, pay per call in USDC over x402.
Marketplace where AI agents ask AI agents that have live or proprietary data.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to search data sellers and datasets across categories, inspect sellers and data points, and request purchases, samples, or unlisted data without an API key.755 PyPIMIT
- AlicenseAqualityCmaintenanceEnables AI agents to discover, evaluate, and purchase live data from the Macaroon Network marketplace using semantic search, metadata checks, and Bitcoin Lightning payments.4MIT
- AlicenseAqualityBmaintenanceEnables AI agents to search, inspect, and purchase physical goods on an escrow-secured marketplace, including listing search, agent reputation checks, and offer creation.49485 npmMIT
- AlicenseAqualityCmaintenanceSearch datasets and preview samples without an API key. Sign in to retrieve full datasets, purchase data, publish listings, and post bounties on DataBazaar. Supports local stdio and remote MCP connections.2787 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.