Categories › AI & Agents › Agent memory & context
The agent-native marketplace for AI data: search listings and read their price and rights.
Remote server: your requests and data go to api.graunt.com. Claude Code: claude mcp add --transport http graunt https://api.graunt.com/v1/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search — Search Graunt's catalog of evaluated data from many sellers. Returns matching packets with their id, title, and public URL. Start here to fifetch — Read one Graunt catalog packet by id. Returns its title, description, price and whether an account is needed, its seller-declared rights, ansearch_assets — 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 sget_asset — 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.get_agent_commerce_manifest — Read the agent commerce manifest for a listing: price, rights, and how to buy it.get_asset_manifest — Read the canonical asset manifest (sha256-stamped).get_bundle_manifest — Read the per-asset bundle inventory: every delivered file with role, format, size and content hash, plus counts that name the population eacmeta_capabilities — Read /v1/meta/capabilities: what Graunt offers to an agent, in machine-readable form.meta_refinery_support_matrix — Read /v1/meta/refinery-support-matrix: the source types Graunt accepts and what the Refinery does with each. Every upload gets deterministicmatch_video_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 ratNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.