Skip to main content
Glama
Upload-Post

Upload-Post

Official

Read Bluesky

bluesky_read
Read-only

Read Bluesky profiles, posts, threads, feeds, followers and engagement, plus connected-account notifications and settings, by calling public and account XRPC methods.

Instructions

Read-only Bluesky lookups. Fields go in params with the API's names; lists page with limit (1-100) and cursor. profiles (actor: handles or DIDs, comma-separated, up to 25; without it the connected account); search_posts (q, sort latest|top, since, until, author, mentions, lang, domain, url, tag; needs user); search_accounts (q, typeahead); followers / follows (actor, or the connected account with user); post_thread (uri, depth, parentHeight), author_feed (actor, filter), feed (feed: at:// URI of a feed generator): Bluesky's own answer, with Bluesky's camelCase parameter names; post_engagement (post_id, type likes|reposts|quotes): who liked, reposted or quoted a post; xrpc (nsid plus its parameters): other public read methods such as app.bsky.feed.getPosts, app.bsky.feed.getQuotes, app.bsky.graph.getLists, app.bsky.actor.searchActorsTypeahead. Of the connected account (need user): notifications (reasons: reply, mention, quote, like, repost, follow…), unread_count, notification_preferences, activity_subscriptions, labels (post_ids: up to 25 at:// URIs), own_profile, status, settings, preferences, drafts, chat_status, chat_preferences.

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": {
      "action": "<action>"
    },
    "name": "bluesky_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
userNoUpload-Post profile name with Bluesky connected. Required for account reads and search_posts; optional for public reads.
actionYes
paramsNoOther API fields for this action, with the REST API's own names (snake_case) and shapes. See the description for each action's fields. Leave out what you do not want to change.

Output Schema

NameRequiredDescriptionDefault
resultNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.25.0

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds meaningful constraints beyond that: pagination via `limit` (1-100) and `cursor`, actor lists capped at 25, labels capped at 25 at:// URIs, and the fact that `user` gates account-scoped actions. No mention of rate limits or how partial failures behave if one actor in a 25-item list is invalid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loading the read-only framing and the paging convention before the action list is correct, and the density is largely justified by 22 actions. But the body is a run-on semicolon chain, and phrases like "Bluesky's own answer, with Bluesky's camelCase parameter names" are confusing rather than informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 22-action multiplexer this is close to complete: every enum value is at least named, the parameter-bearing actions get their fields listed, and the paging contract is stated. An output schema exists, so return shapes need not be described.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

This is where the description carries real weight: `params` is a free-form additionalProperties object, so the per-action field listings (q, sort, since/until, author, mentions, lang, domain, url, tag; depth/parentHeight; reasons) are information the schema cannot express. It loses a point because it says fields use "Bluesky's camelCase parameter names" while the schema says the REST API's own names are snake_case — an agent cannot tell which convention actually applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The definition opens with a specific verb+resource ("Read-only Bluesky lookups") and then enumerates each of the 22 actions with a short gloss ("who liked, reposted or quoted a post", "other public read methods such as app.bsky.feed.getPosts"). It is clearly a read tool, which implicitly distinguishes it from the manage_bluesky_account sibling, but it never names that sibling or states the split explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Strong action-level routing: it distinguishes public reads from account reads ("Of the connected account (need `user`)"), marks search_posts as needing `user`, and notes profiles falls back to the connected account when actor is omitted. What is missing is tool-level guidance — when to pick this over manage_bluesky_account or the other read siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools