# Replace pipeline URL: https://docs.hanzo.ai/docs/openapi/world/put-world-pipeline > Replaces the caller project's news pipeline and returns what was stored. `PUT /v1/world/pipeline` > [World →](https://docs.hanzo.ai/docs/openapi/world) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | ------------- | ---------------------------------------- | | **Address** | `https://api.hanzo.ai/v1/world/pipeline` | | **Method** | `PUT` | | **Operation** | `put_world_pipeline` | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | Replaces the caller project's news pipeline and returns what was stored. It is a WHOLE replacement, not a patch: a field the request leaves out is stored empty, so sending only feeds clears the filters. Every feed URL is validated HERE, at the write boundary — http(s) only, and the host must be on the server's allowlist — so a stored pipeline can never name a host the fetcher would later refuse, and the allowlist is one decision in one place rather than a check at each fetch. ## Request 5 fields, body `application/json` (required). | Field | In | Type | Required | Description | | ------------------ | ---- | ------------- | -------- | ------------------------------------------------------------------------------------------------------ | | `feeds` | body | string\[] | — | Feeds is the RSS/Atom feed URLs to read, at most 64. | | `filters` | body | world.Filters | — | | | `filters.keywords` | body | string\[] | — | Keywords keeps only items whose TITLE contains one of these, case-insensitively. | | `filters.regions` | body | string\[] | — | Regions keeps only items whose TITLE contains one of these, matched case-insensitively as a substring. | | `filters.sources` | body | string\[] | — | Sources keeps only items whose outlet name contains one of these, case-insensitively. | ## Response | Status | Body | Meaning | | --------- | ------------------ | ------- | | `200` | world.pipelineView | ok | | `default` | problem-details | refused | `200` body — 10 fields. | Field | In | Type | Always | Description | | ------------------ | ---- | ------------- | ------ | ------------------------------------------------------------------------------------------------------ | | `createdAt` | body | string | — | CreatedAt is when the pipeline was first stored, RFC3339 UTC. | | `default` | body | boolean | — | Default is true when no pipeline is stored for this project and these are the built-in world feeds. | | `feeds` | body | string\[] | — | Feeds is the RSS/Atom feed URLs the pipeline reads. | | `filters` | body | world.Filters | — | | | `filters.keywords` | body | string\[] | — | Keywords keeps only items whose TITLE contains one of these, case-insensitively. | | `filters.regions` | body | string\[] | — | Regions keeps only items whose TITLE contains one of these, matched case-insensitively as a substring. | | `filters.sources` | body | string\[] | — | Sources keeps only items whose outlet name contains one of these, case-insensitively. | | `org` | body | string | — | Org is the tenant the pipeline belongs to, resolved server-side from the validated principal. | | `project` | body | string | — | Project is the org sub-scope the pipeline belongs to. | | `updatedAt` | body | string | — | UpdatedAt is when it was last written, RFC3339 UTC. | Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors). ## Examples **CLI** ```bash hanzo world pipeline replace ``` **SDK** **.ts** ```ts import { Configuration, WorldApi } from 'hanzoai'; const api = new WorldApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.putWorldPipeline({ feeds: [""], filters: {"keywords":[""],"regions":[""],"sources":[""]} }); ``` **.py** ```python from hanzoai.cloud import ApiClient, Configuration from hanzoai.cloud.api import WorldApi client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])) result = WorldApi(client).put_world_pipeline(feeds=[""], filters={"keywords":[""],"regions":[""],"sources":[""]}) ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.WorldAPI.PutWorldPipeline(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust use hanzo_client::apis::{configuration::Configuration, world_api}; let mut cfg = Configuration::new(); cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok(); let result = world_api::put_world_pipeline(&cfg, Default::default()).await?; ``` **.java** ```java import ai.hanzo.cloud.ApiClient; import ai.hanzo.cloud.api.WorldApi; ApiClient client = new ApiClient(); client.setBearerToken(System.getenv("HANZO_API_KEY")); var result = new WorldApi(client).putWorldPipeline(); ``` **HTTP** ```bash curl -X PUT https://api.hanzo.ai/v1/world/pipeline \ -H "Authorization: Bearer $HANZO_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "feeds": [ "" ], "filters": { "keywords": [ "" ], "regions": [ "" ], "sources": [ "" ] } }' ``` **MCP** MCP reaches **world** through the `world` tool, which names its 5 operations with its own verbs — this one among them, under a name only MCP declares. `describe` explains any of them: ```bash curl -X POST https://api.hanzo.ai/v1/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "describe", "arguments": { "op": "list_worlds" } } }' ``` --- [World API](https://docs.hanzo.ai/docs/openapi/world) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)