Siftree over MCP

Siftree speaks the Model Context Protocol over streamable HTTP. Point any MCP-compatible client or agent framework at a single endpoint and it can search unstructured documents, aggregate them, define datasets, and author and run tasks — scoped to the permissions of the account that authorized the connection.

https://app.siftree.com/api/mcp

tools across 7 areas

Connect

Transport: Streamable HTTP
Protocol: JSON-RPC 2.0
Auth: OAuth, handled by the client
Scope: Channels the authorizing account can reach

Most desktop and IDE clients read a JSON file in this shape. Check your client's docs for where the file lives.

mcp.json

{
  "mcpServers": {
    "siftree": {
      "url": "https://app.siftree.com/api/mcp"
    }
  }
}

Channels

Workspace discovery

Documents

Search, count, aggregate

Sources & datasets

Ingestion and schema

Tasks

Authoring and execution

Reports

Saved output

Skills

Packaged workflows

Web

External context

Filter grammar

Every document tool takes the same filter shape. A leaf is { field, op, value }; compose leaves with and and or, nested arbitrarily deep.

eqequals

neqdoes not equal

gtgreater than

gtegreater than or equal

ltless than

lteless than or equal

invalue is in list

not_invalue is not in list

array_containsarray field contains value

string_containssubstring match

existsfield is present

not_existsfield is absent

is_nullfield is null

not_nullfield is not null

nested filter

{
  "and": [
    { "field": "language", "op": "eq", "value": "en" },
    {
      "or": [
        { "field": "themes", "op": "array_contains", "value": "pricing" },
        { "field": "body", "op": "string_contains", "value": "too expensive" }
      ]
    },
    { "field": "deleted_at", "op": "is_null" }
  ]
}