Server definition

Hash: sha256:aa2552132e8974f30814c8648149f3764536d9c4fce49a482827c03f9e540014
What it is: What a remote MCP server returned when asked what it offers: 19 tools

The blob, as servednamed by its sha256

{
  "instructions": "sprkly schedules social media posts.\n\nBE FAST. The whole point of this connector is that posting takes one exchange, not a\nconversation. Every extra tool call costs the user an approval click, and every extra\nquestion costs them a reply. If you have what to post, where, and when, go.\n\nGo straight to sprkly_schedule_post. Do not call other tools to prepare for it.\nIt validates the post itself and returns the same platform errors a separate check\nwould (caption limits, missing media for Instagram and TikTok, missing YouTube title).\nIf a target platform has more than one connected account it does NOT post: it returns\n`needsAccountChoice` with the accounts to choose from. Put that question to the user,\nthen re-call with `profile_ids` set to every chosen account — `profile_ids` alone is a\ncomplete call and replaces `platforms` entirely.\n\nMEDIA: just pass the link in `media_urls`. sprkly pulls it into storage itself when the\nplatform needs that, and it converts Google Drive and Dropbox share links for you. You do\nNOT need sprkly_add_media_from_url first. Use that tool only when the user wants a media id\nback for reuse across several posts.\n\nTimes are ISO 8601. Ask only for what you are missing. Do not read the whole plan back for\nconfirmation before scheduling: the user can see what they asked for, and a post can be\nedited or deleted afterwards. Ask before DELETING something.\n\nThe four things a post needs are what, where, when, and how many. Everything else has a\nsane default. If the user gave you all four, schedule it and report the result in one line.\n\nThe read tools are for when the user asks, not for preparation: sprkly_list_profiles\n(what is connected), sprkly_list_scheduled_posts (what is queued),\nsprkly_validate_post_policy (check a draft WITHOUT scheduling it).\n\nFor \"what should I post\" or \"when should I post\", call sprkly_get_analytics first and\nreason from what it returns. It gives you evidence, not advice: totals, period-on-period\nchange, best hour and weekday, and the top posts behind them. Two rules when you use it.\nCheck `samples` before calling anything a pattern — a best hour backed by one post is not\na finding, and saying so is more useful than a confident guess. Check `coverage` before\ncomparing platforms: Instagram reports reach, saves, shares and views only for accounts\nconnected or reconnected with the insights permission, and likes and comments only for\nthe rest (`coverage.notes` says which this is). Threads and Facebook report nothing at all,\nand posts published outside sprkly are invisible. Never rank platforms on a metric one of\nthem lacks.",
  "tools": [
    {
      "description": "Download an image or video from a public link into sprkly and get a media_id back, for reuse across several posts. You usually do NOT need this: sprkly_schedule_post accepts a link directly in media_urls and pulls it into storage itself whenever the target platform requires that. Reach for this tool only when the user wants one media_id to attach to more than one post. Google Drive and Dropbox share links are converted automatically; the file must be shared publicly. Limit 50 MB.",
      "inputSchema": {
        "properties": {
          "url": {
            "description": "Direct https link to the image or video file. Must be publicly reachable.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "sprkly_add_media_from_url",
      "outputSchema": null
    },
    {
      "description": "Remove a post from the queue. This is a soft delete. The user can restore it from the Deleted tab for 30 days. Posts that have already published cannot be deleted this way. Always confirm with the user before calling.",
      "inputSchema": {
        "properties": {
          "post_id": {
            "description": "The scheduled post id to delete.",
            "type": "string"
          }
        },
        "required": [
          "post_id"
        ],
        "type": "object"
      },
      "name": "sprkly_delete_scheduled_post",
      "outputSchema": null
    },
    {
      "description": "Compose a caption from a content hint and save it as a draft in sprkly, shaped to the tightest caption limit among the target platforms. Returns a draft id; the draft appears under /drafts for the user to review.",
      "inputSchema": {
        "properties": {
          "content_hint": {
            "description": "What the post should be about: a topic, phrase, or key message.",
            "type": "string"
          },
          "name": {
            "description": "Optional label for the draft.",
            "type": "string"
          },
          "platforms": {
            "description": "Intended platforms, used to pick the caption length ceiling.",
            "items": {
              "enum": [
                "instagram",
                "tiktok",
                "youtube",
                "threads",
                "facebook"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "profile_ids": {
            "description": "Optional accounts to pre-select on the draft. From sprkly_list_profiles.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "tone": {
            "default": "casual",
            "description": "Voice for the draft.",
            "enum": [
              "casual",
              "professional",
              "promotional"
            ],
            "type": "string"
          }
        },
        "required": [
          "content_hint"
        ],
        "type": "object"
      },
      "name": "sprkly_draft_post",
      "outputSchema": null
    },
    {
      "description": "Download one Instagram auto reply as a shareable template. The file holds the trigger, the keyword and the message, and never a post id, a profile id or any account details, so it is safe to send to someone else. An auto reply that is still a draft has nothing published to export.",
      "inputSchema": {
        "properties": {
          "automation_id": {
            "description": "The automation id to export.",
            "type": "string"
          }
        },
        "required": [
          "automation_id"
        ],
        "type": "object"
      },
      "name": "sprkly_export_automation_template",
      "outputSchema": null
    },
    {
      "description": "Plan tier, trial state, connected account count, scheduled post counts by status, and the next three upcoming posts. Never returns tokens or secrets.",
      "inputSchema": {
        "type": "object"
      },
      "name": "sprkly_get_account_summary",
      "outputSchema": null
    },
    {
      "description": "How the user's published posts actually performed: total views and engagement, week-on-week / month-on-month / year-on-year change, their best posting hour, weekday and content category, and the top posts behind those numbers. Every recommendation carries a `samples` count — say how thin the evidence is rather than presenting a one-post pattern as a finding. Every period-on-period percentage carries the post counts and raw totals it came from: quote those, because a big percentage off a tiny base is not a big change. `topPosts` is grouped by platform and ranked only inside each group; `relativeToPlatformBest` compares a post with others on its OWN platform and never across platforms, so use the absolute `value` and its `metric` label to weigh one platform against another. Instagram contributes reach, saves, shares and views only for accounts connected or reconnected with the insights permission, and likes and comments only for the rest. Threads and Facebook produce no metrics at all. Read `coverage` before comparing platforms, and never rank platforms on a metric one of them lacks.",
      "inputSchema": {
        "properties": {
          "days": {
            "description": "How many days back to analyse. Default 30.",
            "maximum": 365,
            "minimum": 1,
            "type": "integer"
          },
          "profile_ids": {
            "description": "Limit to these accounts. Omit for every account this connection can see.",
            "items": {
              "type": "string"
            },
            "type": "array"
          }
        },
        "type": "object"
      },
      "name": "sprkly_get_analytics",
      "outputSchema": null
    },
    {
      "description": "Subscription status, current plan, period end, purchased handles and the last few billing events. No payment method details; the Stripe customer id is truncated.",
      "inputSchema": {
        "type": "object"
      },
      "name": "sprkly_get_billing_summary",
      "outputSchema": null
    },
    {
      "description": "Whether a post is awaiting human review, approved or rejected, including reviewer notes and timestamps.",
      "inputSchema": {
        "properties": {
          "post_id": {
            "description": "The scheduled post id.",
            "type": "string"
          }
        },
        "required": [
          "post_id"
        ],
        "type": "object"
      },
      "name": "sprkly_get_post_approval_status",
      "outputSchema": null
    },
    {
      "description": "Full detail for one post: status, targets, scheduled and published times, permalink, and the failure reason if it did not publish. Media comes back as mediaIds in slide order, not as links. Ids and profile ids are plumbing: talk to the user about accounts by handle and about posts by their caption, and do not read ids out unless they ask for one.",
      "inputSchema": {
        "properties": {
          "post_id": {
            "description": "The scheduled post id.",
            "type": "string"
          }
        },
        "required": [
          "post_id"
        ],
        "type": "object"
      },
      "name": "sprkly_get_post_status",
      "outputSchema": null
    },
    {
      "description": "This creator's allowed TikTok privacy levels and interaction settings, fetched live from TikTok. You usually do NOT need this before scheduling: sprkly_schedule_post checks privacyLevel against this same list itself and, when it is wrong, returns the levels that would work. Call this only when the user asks what their options are, or you want to offer them a choice.",
      "inputSchema": {
        "properties": {
          "profile_id": {
            "description": "The TikTok profile id to query, from sprkly_list_profiles.",
            "type": "string"
          }
        },
        "required": [
          "profile_id"
        ],
        "type": "object"
      },
      "name": "sprkly_get_tiktok_posting_options",
      "outputSchema": null
    },
    {
      "description": "Read an auto reply template, and optionally set it up. With no profile_id NOTHING is written: the template is checked and handed back, which is the safe first call. With a profile_id the automation is created, and it goes live when the trigger can be satisfied. A trigger that watches one post (a keyword on a post, or every comment on a post) needs post_id as well. Without one it saves as a draft that sends nothing until a post is chosen. A keyword on any post and a Profile DM need no post_id. A template that DMs every commenter on the whole account is turned off and is refused.",
      "inputSchema": {
        "properties": {
          "post_id": {
            "description": "The published post to watch. Only for a trigger that watches one post. Leave it out for a keyword on any post or a Profile DM.",
            "type": "string"
          },
          "profile_id": {
            "description": "The Instagram account to set it up on. Leave this out to only check the template.",
            "type": "string"
          },
          "template": {
            "description": "The template, as an object or as the file text.",
            "type": "object"
          }
        },
        "required": [
          "template"
        ],
        "type": "object"
      },
      "name": "sprkly_import_automation_template",
      "outputSchema": null
    },
    {
      "description": "Every ACTIVE social account linked to this sprkly account: platform, handle, follower count, and whether it needs reconnecting. Disconnected/inactive accounts are never listed, so any profileId returned here is a valid posting target. Never returns access tokens.",
      "inputSchema": {
        "type": "object"
      },
      "name": "sprkly_list_connected_social_accounts",
      "outputSchema": null
    },
    {
      "description": "The profile ids needed to target a post, with each one's platform and handle. Call this before sprkly_schedule_post.",
      "inputSchema": {
        "type": "object"
      },
      "name": "sprkly_list_profiles",
      "outputSchema": null
    },
    {
      "description": "The post queue, newest first, with a caption preview, targets, status and failure reason. Supports a status filter and cursor pagination.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor. Pass the nextCursor value from a previous response.",
            "type": "string"
          },
          "limit": {
            "default": 20,
            "description": "Maximum posts to return.",
            "maximum": 50,
            "minimum": 1,
            "type": "integer"
          },
          "status": {
            "description": "Filter by status.",
            "enum": [
              "draft",
              "pending_approval",
              "scheduled",
              "posted",
              "failed"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "sprkly_list_scheduled_posts",
      "outputSchema": null
    },
    {
      "description": "Submit a draft post for human review. Moves the post to pending_approval and returns an approval id to poll with sprkly_get_post_approval_status. Use this when the user wants a person to sign off before anything publishes.",
      "inputSchema": {
        "properties": {
          "note": {
            "description": "Optional context for the reviewer.",
            "type": "string"
          },
          "post_id": {
            "description": "The draft post id to submit.",
            "type": "string"
          }
        },
        "required": [
          "post_id"
        ],
        "type": "object"
      },
      "name": "sprkly_request_post_approval",
      "outputSchema": null
    },
    {
      "description": "Queue a post for publishing, in ONE call. Attach media by passing the user's link straight to media_urls: sprkly downloads it into storage itself for the platforms that need that, so no upload tool has to run first. Runs the same quota, duplicate-content and platform pre-flight checks as the sprkly app. Instagram and TikTok require media at submission time; YouTube and TikTok require a title, and TikTok also requires platform_meta.tiktok.privacyLevel — just send the level the user asked for and this tool names the allowed values if it is not one of them. It reads the real bytes of the media and the response says what will actually publish on each platform (a Reel, a 3-slide carousel, a photo set, a Page feed video) plus anything worth passing on: relay that to the user. Confirm the date, time and target accounts with the user first. If a target platform has more than one connected account and profile_ids is not given, the tool returns needsAccountChoice with the options instead of scheduling — put that choice to the user, then re-call.",
      "inputSchema": {
        "properties": {
          "all_accounts": {
            "default": false,
            "description": "Explicitly post to EVERY connected account on every listed platform, skipping the needsAccountChoice question. Only pass true when the user has said they want all accounts.",
            "type": "boolean"
          },
          "caption": {
            "description": "Post caption, max 2200 characters.",
            "type": "string"
          },
          "category": {
            "description": "Optional content category, e.g. \"fitness\".",
            "type": "string"
          },
          "media_id": {
            "description": "Id of a single media file already uploaded to sprkly. Shorthand for a one-item media_ids.",
            "type": "string"
          },
          "media_ids": {
            "description": "Ids of media files already uploaded to sprkly, in slide order. Array order is the published order. Use these when the user already has media in sprkly, or when one file is going on several posts; for a link the user just gave you, media_urls is fewer steps. Every photo in a set must be the SAME shape or the call is refused: export them all at 1080x1920 (9:16), 1080x1440 (3:4), 1080x1350 (4:5) or 1080x1080 (1:1). Instagram takes at most 10 slides; TikTok photo sets take up to 35.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "media_urls": {
            "description": "Publicly reachable image or video URLs to attach, in slide order. Pass links through for ANY platform. Instagram and Threads fetch them directly; for TikTok, YouTube and Facebook sprkly downloads the file into its own storage while scheduling, so a link works there too and any problem with it is reported now, in this call. Google Drive and Dropbox share links are converted automatically. JPEG, PNG, WebP, GIF, MP4, MOV and WebM only: AVIF and HEIC (the iPhone camera default) are refused with re-export instructions, because sprkly cannot convert them. Each file must be publicly reachable and under 50 MB.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "platform_meta": {
            "description": "Platform-specific publishing options, keyed by platform.",
            "properties": {
              "instagram": {
                "description": "Instagram publishing options.",
                "properties": {
                  "surface": {
                    "description": "Where to publish. 'story' posts to the account's Story instead of the feed: it disappears after 24 hours, takes exactly ONE photo or video, and sends no caption — Instagram Stories have no caption field. Omit for a normal feed post or Reel. The media cannot decide this: a 9:16 video is a Reel or a Story, so ask the user which they want rather than guessing.",
                    "enum": [
                      "feed",
                      "story"
                    ],
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "tiktok": {
                "description": "TikTok publishing options. privacyLevel is REQUIRED for every TikTok post.",
                "properties": {
                  "autoAddMusic": {
                    "default": true,
                    "description": "Attach TikTok's recommended music. Photo posts only; defaults true.",
                    "type": "boolean"
                  },
                  "brandContentOptIn": {
                    "description": "Branded content: the post promotes a third party. Cannot be combined with privacyLevel SELF_ONLY.",
                    "type": "boolean"
                  },
                  "brandName": {
                    "description": "Optional brand name shown with the commercial content disclosure.",
                    "type": "string"
                  },
                  "brandOrganicOptIn": {
                    "description": "Organic branding: the post promotes the creator's own brand.",
                    "type": "boolean"
                  },
                  "commercialContentDisclosure": {
                    "description": "Declare the post as commercial content. When true, at least one of brandContentOptIn or brandOrganicOptIn must also be true.",
                    "type": "boolean"
                  },
                  "disableComment": {
                    "description": "Turn off comments on the post.",
                    "type": "boolean"
                  },
                  "disableDuet": {
                    "description": "Disallow duets of the video.",
                    "type": "boolean"
                  },
                  "disableStitch": {
                    "description": "Disallow stitches of the video.",
                    "type": "boolean"
                  },
                  "privacyLevel": {
                    "description": "REQUIRED for TikTok posts. Must be one of this creator's allowed options: fetch them with sprkly_get_tiktok_posting_options.",
                    "enum": [
                      "PUBLIC_TO_EVERYONE",
                      "MUTUAL_FOLLOW_FRIENDS",
                      "FOLLOWER_OF_CREATOR",
                      "SELF_ONLY"
                    ],
                    "type": "string"
                  },
                  "title": {
                    "description": "Optional TikTok-only title, used instead of the top-level title on TikTok. Trimmed to 150 characters. The top-level title is still required even when you set this one.",
                    "type": "string"
                  }
                },
                "type": "object"
              }
            },
            "type": "object"
          },
          "platforms": {
            "description": "Platforms to publish to. A platform with exactly one connected account is targeted directly; one with several makes the tool answer needsAccountChoice so the user can pick.",
            "items": {
              "enum": [
                "instagram",
                "tiktok",
                "youtube",
                "threads",
                "facebook"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "profile_ids": {
            "description": "Specific accounts to publish to, from sprkly_list_profiles. When given, this list IS the target set — platforms are not fanned out.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "scheduled_time": {
            "description": "ISO 8601 timestamp to publish at. Must be in the future. If omitted the post goes out on the next publisher run, about a minute from now — there is no smart slot-picking, so pass an explicit time unless the user wants it published immediately. sprkly_get_analytics can suggest one.",
            "type": "string"
          },
          "title": {
            "description": "Post title. Required for YouTube (max 100 characters) and TikTok (max 150 characters).",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "sprkly_schedule_post",
      "outputSchema": null
    },
    {
      "description": "Change the caption, publish time, target accounts or attached media on a post that has not published yet. Only posts with status \"scheduled\" can be edited.",
      "inputSchema": {
        "properties": {
          "caption": {
            "description": "Replacement caption, max 2200 characters.",
            "type": "string"
          },
          "media_id": {
            "description": "Replacement sprkly media file id. Shorthand for a one-item media_ids.",
            "type": "string"
          },
          "media_ids": {
            "description": "Replacement media, in slide order. Replaces the whole set, it does not append — pass every slide you want the post to keep.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "post_id": {
            "description": "The scheduled post id.",
            "type": "string"
          },
          "profile_ids": {
            "description": "Replacement target accounts. Platforms are re-derived from them.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "scheduled_time": {
            "description": "New ISO 8601 publish time. Must be in the future.",
            "type": "string"
          }
        },
        "required": [
          "post_id"
        ],
        "type": "object"
      },
      "name": "sprkly_update_scheduled_post",
      "outputSchema": null
    },
    {
      "description": "Upload files the user has on their machine (slides, photos, a short video) into sprkly and get a media_id for each. LINK MODE is the way to send a file from disk. Send files, one entry per file with its filename, sha256 and size_bytes. You get back one uploadUrl per file. PUT the bytes to it: curl -sS -X PUT --data-binary @01.jpg \"<uploadUrl>\". Each PUT answers JSON with mediaId. Links last 15 minutes. Up to 50 MB per file and 35 files per call. The bytes never pass through you, so a whole carousel costs a few hundred tokens. INLINE MODE is for tiny files only (a few KB): data_base64 plus filename, 25 MB at most. base64 costs about one token per character, so never inline a real slide. When files is sent, data_base64 and filename are ignored. For a public link use media_urls on sprkly_schedule_post instead. The same bytes sent twice return the same media_id.",
      "inputSchema": {
        "properties": {
          "content_type": {
            "description": "INLINE MODE. Optional MIME hint such as image/jpeg. sprkly sniffs the bytes and that wins.",
            "type": "string"
          },
          "data_base64": {
            "description": "INLINE MODE, tiny files only. The file contents, base64 encoded. Standard or URL-safe alphabet, with or without a data: prefix. Ignored when files is sent.",
            "type": "string"
          },
          "filename": {
            "description": "INLINE MODE. The file name, for example 01.jpg. Used in the response and in error messages. The bytes decide the real type. Ignored when files is sent.",
            "type": "string"
          },
          "files": {
            "description": "LINK MODE. One entry per file, in slide order. Get the values in Bash: sha256sum 01.jpg (first 64 characters) and stat -c %s 01.jpg. 1 to 35 entries.",
            "items": {
              "properties": {
                "filename": {
                  "description": "The file name, for example 01.jpg.",
                  "type": "string"
                },
                "sha256": {
                  "description": "SHA-256 of the file, 64 hex characters.",
                  "type": "string"
                },
                "size_bytes": {
                  "description": "Exact file size in bytes.",
                  "minimum": 1,
                  "type": "integer"
                }
              },
              "required": [
                "filename",
                "sha256",
                "size_bytes"
              ],
              "type": "object"
            },
            "maxItems": 35,
            "minItems": 1,
            "type": "array"
          }
        },
        "required": [],
        "type": "object"
      },
      "name": "sprkly_upload_media",
      "outputSchema": null
    },
    {
      "description": "Check a caption against each target platform's posting rules before scheduling: caption length, media requirements, hashtag ceilings, whether links are clickable, required YouTube titles, and PII or prohibited-content warnings. Pure analysis. Writes nothing.",
      "inputSchema": {
        "properties": {
          "caption": {
            "description": "The caption to check.",
            "type": "string"
          },
          "hashtags": {
            "description": "Hashtags posted alongside the caption, if they are not already in it.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "mediaUrlsCount": {
            "description": "How many images or videos will be attached. Instagram and TikTok require at least one.",
            "minimum": 0,
            "type": "integer"
          },
          "platformMeta": {
            "description": "Platform-specific publishing options, keyed by platform.",
            "type": "object"
          },
          "platforms": {
            "description": "Target platforms to check against.",
            "items": {
              "enum": [
                "instagram",
                "tiktok",
                "youtube",
                "threads",
                "facebook"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "title": {
            "description": "Post title. Required for YouTube, max 100 characters.",
            "type": "string"
          }
        },
        "required": [
          "caption",
          "platforms"
        ],
        "type": "object"
      },
      "name": "sprkly_validate_post_policy",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:aa2552132e8974f30814c8648149f3764536d9c4fce49a482827c03f9e540014 | sha256sum