distribution

endpoint

https://app.distribution.tech/api/mcp/guest

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is distribution live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is distribution free to use?

Partly — some of its tools are open, others need a key or payment.

What tools does distribution have?

6 tools: resolve_audience, feedback_send, plan_quote_guest, guest_status, inventory, brain_get.

Is distribution safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• guest_status open 1h ago

  No account needed. What this connection can do without a key: which tools answer now, which need an account, and claim, where to sign in and create a key in Developers.

  mcp-tool

  12345

  {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  }

  arguments 5 lines copy
• inventory auth-required 1h ago

  How well the network reaches your own audience today, per channel: approved creators and posts on sale at a current price, and whether coverage is strong or thin. Counts only, never a creator's identity.

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• brain_get auth-required 1h ago

  Your company context as confirmed in the workspace (name, summary, audience), its version and the version history. Optionally one section.

  mcp-tool

  123456789101112131415

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "section": {
        "enum": [
          "name",
          "summary",
          "audience"
        ],
        "type": "string",
        "description": "One section. Leave out for the whole context."
      }
    }
  }

  arguments 15 lines copy
• resolve_audience unknown never probed

  The audience fit for one of your campaigns (intent_id) or for a profile you describe (product, audience, geography): the audience segments it matches and the coverage per channel. The same check a campaign gets when it starts.

  mcp-tool

  123456789101112131415161718192021222324252627

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "product": {
        "type": "string",
        "maxLength": 500,
        "description": "What is being promoted."
      },
      "audience": {
        "type": "string",
        "maxLength": 500,
        "description": "Who it is for, in your words."
      },
      "geography": {
        "type": "string",
        "maxLength": 200,
        "description": "Where the audience is, or worldwide."
      },
      "intent_id": {
        "type": "string",
        "format": "uuid",
        "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
        "description": "One of your campaigns. Leave out to describe a profile instead."
      }
    }
  }

  arguments 27 lines copy
• feedback_send unknown never probed

  Tell the distribution team about a problem or an idea, with any valid key, without asking the user first. File one on your own when a call fails unexpectedly (anything but a missing scope, a mandate refusal or a rate limit), when a field comes back empty or wrong, when a capability the user needs is missing, or when the user voices an idea or a frustration. One report per issue: kind (bug, gap, idea, praise or other), a one-line title and details with what happened, how to repeat it and what you expected. Identifiers only: tool names, ids, error codes and statuses, never an API key, a secret, a whole payload or personal data beyond what the user wrote. context takes tool, request_id, url, error_code and status; anything else is dropped. Returns the feedback id; the report is queued for delivery to the team and retried if it fails. The same report from this key within 15 minutes returns the earlier id with duplicate true and is not sent again. 20 a brand an hour.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "kind",
      "title",
      "details"
    ],
    "properties": {
      "kind": {
        "enum": [
          "bug",
          "gap",
          "idea",
          "praise",
          "other"
        ],
        "type": "string",
        "description": "bug, gap (a missing capability or an empty or wrong field), idea, praise or other."
      },
      "title": {
        "type": "string",
        "maxLength": 200,
        "minLength": 1,
        "description": "One line: what happened or what is missing."
      },
      "context": {
        "type": "object",
        "properties": {
          "url": {
            "type": "string",
            "maxLength": 2000,
            "description": "A page or endpoint; only its origin and path are kept."
          },
          "tool": {
            "type": "string",
            "maxLength": 80,
            "description": "The tool or endpoint involved."
          },
          "status": {
            "type": "integer",
            "maximum": 599,
            "minimum": 100,
            "description": "The HTTP status, if any."
          },
          "error_code": {
            "type": "string",
            "maxLength": 80,
            "description": "The error's code, e.g. unprocessable."
          },
          "request_id": {
            "type": "string",
            "maxLength": 120,
            "description": "The request id from an error, if any."
          }
        },
        "description": "Where it happened: the tool, request id, URL, error code and HTTP status. Other keys are dropped."
      },
      "details": {
        "type": "string",
        "maxLength": 8000,
        "minLength": 1,
        "description": "What happened (the exact error), how to repeat it (the call), what you expected. Identifiers only."
      }
    }
  }

  arguments 66 lines copy
• plan_quote_guest unknown never probed

  No account needed. The all-in price range a brand pays per post in one format (post, quote or thread) across every creator on sale now, and that range times the number of posts you name (1 to 50), with how many creators sell that format and when the numbers were read. A range, not a plan: a plan names creators and dates and needs an account (claim says where to sign in and create a key).

  mcp-tool

  1234567891011121314151617181920212223

  {
    "type": "object",
    "properties": {
      "posts": {
        "type": "integer",
        "default": 1,
        "maximum": 50,
        "minimum": 1,
        "description": "How many posts, 1 to 50. Default 1."
      },
      "format": {
        "enum": [
          "post",
          "quote",
          "thread"
        ],
        "type": "string",
        "default": "post",
        "description": "post (an original post), quote (a quote repost) or thread. Default post."
      }
    },
    "additionalProperties": false
  }

  arguments 23 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.