Server definition

Hash: sha256:c3f8dc2b5cdb2d55f596d7d922618cd144b40ba1d5d7f8e032418a662c895085
What it is: What a remote MCP server returned when asked what it offers: 4 tools

The blob, as servednamed by its sha256

{
  "instructions": "FrameThrower is a cinematography reference library. Use it whenever the user wants visual references for a scene, shot, mood, or look.\n\nPresentation: ALWAYS surface the \"View all on FrameThrower\" gallery link first and prominently — it opens the full visual result grid on FrameThrower, which is the reliable way for the user to actually see the thumbnails (inline image rendering in chat is unreliable). Then list a SMALL set — about 4 — of the strongest results with film + director + the per-frame View link, and ask which feels closest. Do not dump long lists.\n\nRefining (the core loop): when the user reacts (\"more like #2\", \"more anamorphic, less daylight\", \"tighter and colder\"), refine — call find_similar on the id of a frame they liked, or find_by_craft with the adjusted attributes (lens, shot_size, visual_style, setting, time_of_day, director, year range). Keep the set small and iterate until they are happy.\n\nAlways keep the View link with each frame so the user can open or save it on FrameThrower. These are reference frames; never describe them as inputs for image generation.\n\nImage quality: each frame carries TWO urls. The inline ![frame] preview is a 1280px thumbnail, sized for chat. The \"Full-resolution image\" url is the original file — use that one whenever the user is building a slide deck, lookbook, PDF, moodboard or any document, and when they ask to download, insert, embed or export an image. Never put the thumbnail into a deliverable. Both are public urls, so tools that fetch an image by url (Google Slides \"Insert > Image > By URL\", Docs, Keynote) can take the full-resolution one directly. Frames come from finished films at their native resolution, so it varies per frame — some are HD, some are far larger, and no url makes a frame sharper than the source.",
  "tools": [
    {
      "description": "Find frames by specific cinematography craft attributes — lens character, shot size, visual style, setting, time of day, director, or year range. All optional; combine to narrow. Use this to refine a search precisely.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "director": {
            "type": "string"
          },
          "lens": {
            "description": "e.g. \"anamorphic\", \"spherical\", \"vintage_soft\"",
            "type": "string"
          },
          "limit": {
            "maximum": 40,
            "minimum": 1,
            "type": "number"
          },
          "setting": {
            "description": "\"interior\" or \"exterior\"",
            "type": "string"
          },
          "shot_size": {
            "description": "e.g. \"closeup\", \"wide\", \"medium\"",
            "type": "string"
          },
          "time_of_day": {
            "description": "e.g. \"night\", \"day\"",
            "type": "string"
          },
          "visual_style": {
            "type": "string"
          },
          "year_max": {
            "type": "number"
          },
          "year_min": {
            "type": "number"
          }
        },
        "type": "object"
      },
      "name": "find_by_craft",
      "outputSchema": null
    },
    {
      "description": "Find frames visually/semantically similar to a given frame id (from a prior result). Use this to pull more references like one the user shortlisted.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "frameId": {
            "type": "string"
          },
          "limit": {
            "maximum": 40,
            "minimum": 1,
            "type": "number"
          }
        },
        "required": [
          "frameId"
        ],
        "type": "object"
      },
      "name": "find_similar",
      "outputSchema": null
    },
    {
      "description": "Get the full metadata + preview thumbnail + full-resolution image URL + depth map URL + link for a single frame id. The depth map is precomputed and free — use it when the user is generating images and needs the composition or camera geometry of this frame.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "frameId": {
            "type": "string"
          }
        },
        "required": [
          "frameId"
        ],
        "type": "object"
      },
      "name": "get_frame_details",
      "outputSchema": null
    },
    {
      "description": "Search the FrameThrower cinematography reference library by concept, mood, color, composition, or scene. Returns reference frames with film/credits metadata, a preview thumbnail, the full-resolution image URL (use this one for slide decks and documents), a precomputed DEPTH MAP url (greyscale, same dimensions as the frame — pass it straight to a depth ControlNet or any image-to-image pipeline that wants geometry), and a link to view on FrameThrower.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "limit": {
            "maximum": 40,
            "minimum": 1,
            "type": "number"
          },
          "query": {
            "description": "Natural-language description, e.g. \"neon-lit rainy street at night\"",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_frames",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:c3f8dc2b5cdb2d55f596d7d922618cd144b40ba1d5d7f8e032418a662c895085 | sha256sum