Search Lemmy instance
lemmy_searchSearch Lemmy posts, comments, communities, users, or exact URLs on a specified instance to locate relevant discussions, content, and accounts.
Instructions
Search Lemmy posts, comments, communities, users or exact URLs; All and Comments can take longer. Requires instance and query. Returns a list (use cursor when paginated).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"instance": "<instance>",
"query": "<query>",
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "lemmy_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number, 1 to 100. Default: 1. An instance refuses pages past 100. Lemmy pages by number over a live order, so new or re-ranked items can shift a row onto the next page. Remove repeats by `id`. | |
| sort | No | Order. `Scaled` and `Controversial` are refused by 0.18 instances. | |
| type | No | `Posts` (default), `All` (every kind), `Comments` (comment text), `Communities`, `Users` or `Url` (posts linking to an exact URL). `All` and `Comments` can take much longer than the other kinds. | |
| limit | No | Rows per page, 1 to 50. Default: 10. | |
| query | Yes | Required. Search term, 1 to 300 characters, in any language. Required, never empty and no control characters. | |
| scope | No | `local` reads only this instance's own items; `all` includes federated items the instance has seen. Default: the endpoint's own listing. | |
| author | No | Restrict to one author, by username. | |
| cursor | No | Pass `page.nextCursor` from the previous response to get the next page. It only works with the same filters; do not send it with `page`. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| instance | Yes | Required. The Lemmy instance, e.g. `lemmy.world`. A URL on the instance is also accepted. Ids and counts belong to this instance. | |
| community | No | Community name, e.g. `technology`, or `technology@lemmy.world` to resolve a community on another instance. Prefer the community's home instance for counts. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |