Server definition

Hash: sha256:2929199bdc983f7349e2280d6b4a15eea626323d13be00258def26ad416f8735
What it is: What a remote MCP server returned when asked what it offers: 14 tools

The blob, as servednamed by its sha256

{
  "instructions": "Read-only access to Twitter/X data via the SocialData API.\n\nEvery tool call fetches one page of live data from Twitter and is billed to\nthe caller's SocialData balance. Do not call tools in a loop to exhaustively\npage through results unless the user explicitly asked for that; ask first.\n\nUser IDs are numeric strings, not integers. Usernames are given without the\nleading \"@\". Tools that paginate return a `next_cursor`; pass it back as\n`cursor` to fetch the following page. An absent or null `next_cursor` means\nthere are no further pages.",
  "tools": [
    {
      "description": "Check whether one Twitter/X user follows another. Far cheaper than fetching a follower list — use this whenever the question is about a specific pair of accounts. Both IDs must be numeric.",
      "inputSchema": {
        "properties": {
          "source_user_id": {
            "description": "The numeric ID of the user who might be following, as a string.",
            "type": "string"
          },
          "target_user_id": {
            "description": "The numeric ID of the user who might be followed, as a string.",
            "type": "string"
          }
        },
        "required": [
          "source_user_id",
          "target_user_id"
        ],
        "type": "object"
      },
      "name": "check_is_following",
      "outputSchema": null
    },
    {
      "description": "Fetch one page of posts from a Twitter/X list, newest first. A page is large — around 100 posts — plus a next_cursor. Billing is per result, so one call here costs several times a single-user timeline call; do not page through a busy list unless the user asked for that.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "list_id": {
            "description": "The numeric Twitter/X list ID, as a string.",
            "type": "string"
          }
        },
        "required": [
          "list_id"
        ],
        "type": "object"
      },
      "name": "get_list_tweets",
      "outputSchema": null
    },
    {
      "description": "Fetch a single Twitter/X post by its numeric ID, including engagement counts. Bills one post request against the caller's balance.",
      "inputSchema": {
        "properties": {
          "tweet_id": {
            "description": "The numeric post ID, as a string.",
            "type": "string"
          }
        },
        "required": [
          "tweet_id"
        ],
        "type": "object"
      },
      "name": "get_tweet",
      "outputSchema": null
    },
    {
      "description": "Fetch one page of replies to a Twitter/X post. Returns about 20 replies plus a next_cursor. The first item of a page can repeat the last item of the previous page, so de-duplicate by post id when paging. Each call bills against the caller's balance — do not page through the whole conversation unless the user asked for that.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "tweet_id": {
            "description": "The numeric ID of the post whose replies you want, as a string.",
            "type": "string"
          }
        },
        "required": [
          "tweet_id"
        ],
        "type": "object"
      },
      "name": "get_tweet_comments",
      "outputSchema": null
    },
    {
      "description": "Fetch one page of a Twitter/X thread — the chain of follow-up posts the author wrote under their own post (\"1/\", \"2/\", ...). Give it the ID of any post in the chain and it returns that chain in order. It does NOT return what other people replied; use get_tweet_comments for those. A post the author never followed up on is a one-post thread and correctly returns just that post. Roughly 30 posts per page plus a next_cursor, so a long thread takes several calls. Each call bills against the caller's balance — do not page through a long thread unless the user asked for that.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "tweet_id": {
            "description": "The numeric post ID, as a string.",
            "type": "string"
          }
        },
        "required": [
          "tweet_id"
        ],
        "type": "object"
      },
      "name": "get_tweet_thread",
      "outputSchema": null
    },
    {
      "description": "Look up a Twitter/X user profile by numeric user ID. Bills one user request against the caller's balance.",
      "inputSchema": {
        "properties": {
          "user_id": {
            "description": "The numeric Twitter/X user ID, as a string (IDs exceed safe integer precision).",
            "type": "string"
          }
        },
        "required": [
          "user_id"
        ],
        "type": "object"
      },
      "name": "get_user_by_id",
      "outputSchema": null
    },
    {
      "description": "Look up a Twitter/X user profile by username (handle). Returns the profile including follower and following counts. Bills one user request against the caller's balance.",
      "inputSchema": {
        "properties": {
          "username": {
            "description": "The Twitter/X username (handle), with or without the leading @.",
            "type": "string"
          }
        },
        "required": [
          "username"
        ],
        "type": "object"
      },
      "name": "get_user_by_username",
      "outputSchema": null
    },
    {
      "description": "Fetch one page of a user's followers. This is one of the most expensive tools: a page is set upstream and can run to ~100 user records, every one of which is billed. Never page through a large account's followers without the user explicitly asking. Requires a numeric user ID.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "user_id": {
            "description": "The numeric Twitter/X user ID whose followers you want, as a string.",
            "type": "string"
          }
        },
        "required": [
          "user_id"
        ],
        "type": "object"
      },
      "name": "get_user_followers",
      "outputSchema": null
    },
    {
      "description": "Fetch one page of the accounts a user follows. Expensive: a page is set upstream and can run to ~100 user records, every one of which is billed. Never page through a large account's following list without the user explicitly asking. Requires a numeric user ID.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "user_id": {
            "description": "The numeric Twitter/X user ID whose following list you want, as a string.",
            "type": "string"
          }
        },
        "required": [
          "user_id"
        ],
        "type": "object"
      },
      "name": "get_user_following",
      "outputSchema": null
    },
    {
      "description": "Fetch one page of posts mentioning a given user, newest first. Returns about 20 posts plus a next_cursor. The first item of a page can repeat the last item of the previous page, so de-duplicate by post id when paging. Each call bills against the caller's balance.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "username": {
            "description": "The Twitter/X username (handle) being mentioned, with or without the leading @.",
            "type": "string"
          }
        },
        "required": [
          "username"
        ],
        "type": "object"
      },
      "name": "get_user_mentions",
      "outputSchema": null
    },
    {
      "description": "Fetch one page of a user's own posts (excluding replies), newest first. Returns about 20 posts plus a next_cursor. If the account has a pinned post it is prepended to every page, so de-duplicate by post id when paging. Each call bills against the caller's balance — do not page through a whole timeline unless the user asked for that. Requires a numeric user ID: call get_user_by_username first if you only have a handle.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "user_id": {
            "description": "The numeric Twitter/X user ID, as a string.",
            "type": "string"
          }
        },
        "required": [
          "user_id"
        ],
        "type": "object"
      },
      "name": "get_user_tweets",
      "outputSchema": null
    },
    {
      "description": "Fetch one page of a user's posts including their replies, newest first. Returns about 20 items plus a next_cursor. If the account has a pinned post it is prepended to every page, so de-duplicate by post id when paging. Each call bills against the caller's balance. Requires a numeric user ID: call get_user_by_username first if you only have a handle.",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "user_id": {
            "description": "The numeric Twitter/X user ID, as a string.",
            "type": "string"
          }
        },
        "required": [
          "user_id"
        ],
        "type": "object"
      },
      "name": "get_user_tweets_and_replies",
      "outputSchema": null
    },
    {
      "description": "Search Twitter/X posts. Returns one page of about 20 results plus a\nnext_cursor, and bills one search request against the caller's balance.\n\nThe query supports Twitter's advanced search operators, and using them is\nalmost always better than a bare keyword search:\n  from:handle          posts by an account\n  to:handle            replies to an account\n  @handle              posts mentioning an account\n  #tag                 hashtag\n  \"exact phrase\"       phrase match\n  since:2026-01-01     posts on or after a date\n  until:2026-02-01     posts before a date\n  min_faves:100        at least N likes\n  min_retweets:10      at least N retweets\n  filter:links         posts containing links\n  -filter:replies      exclude replies\nCombine them freely: from:jack min_faves:500 since:2026-01-01",
      "inputSchema": {
        "properties": {
          "cursor": {
            "description": "Pagination cursor from a previous call's next_cursor. Omit for the first page.",
            "type": "string"
          },
          "query": {
            "description": "The search query. Supports Twitter advanced search operators such as from:, to:, since:, until:, min_faves: and filter:.",
            "type": "string"
          },
          "type": {
            "default": "Latest",
            "description": "Latest returns the newest matching posts; Top returns the most engaged-with. Defaults to Latest.",
            "enum": [
              "Latest",
              "Top"
            ],
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_tweets",
      "outputSchema": null
    },
    {
      "description": "Search Twitter/X user profiles by name or handle. Returns one page of matching profiles and bills against the caller's balance. Use this when you know roughly who someone is but not their exact handle.",
      "inputSchema": {
        "properties": {
          "query": {
            "description": "Name or handle to search for.",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_users",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:2929199bdc983f7349e2280d6b4a15eea626323d13be00258def26ad416f8735 | sha256sum