Skip to main content
Glama

bluesky-mcp-server

Get Bluesky Feed

bsky_get_feed
Read-onlyIdempotent

Read the posts a Bluesky feed generator serves, in the order the feed ranks them. Accepts the feed's AT-URI (at:///app.bsky.feed.generator/) or its bsky.app page (https://bsky.app/profile//feed/). Feeds come from the "feedUri" of each bsky_get_trending topic — the way to read what a trend is about — from a quoted feed in a post (an embed with recordKind "generator"), or from a shared link; Discover is at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.generator/whats-hot. Returns posts with full text, engagement counts, embeds, and AT-URIs for drilling into threads via bsky_get_post_thread. A post the feed pinned to its top carries "pinned: true"; a repost carries "repostedBy". Personalized feeds, which Bluesky serves only to a signed-in account, cannot be read here. Supports cursor pagination.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
feedYesThe feed to read — its AT-URI, e.g. "at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.generator/whats-hot", or its bsky.app URL, e.g. "https://bsky.app/profile/bsky.app/feed/whats-hot"; a trailing "/", "?…", or "#…" on the URL is ignored. The owner may be a handle or a DID; a handle costs one extra lookup. A trend's "feedUri" works as-is.
limitNoMaximum number of posts to return (1–100). Default 25. A feed may return fewer than the limit on a page that still has more after it — follow the cursor, not the count. A page that would pass the 48,000-byte response budget is asked for again with fewer posts and carries "budgetCapped: true"; its cursor continues after the posts it holds.
cursorNoOpaque pagination cursor from a previous response of the same feed. Omit for the first page.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
capNoThe limit applied to this page.
errorNoPresent when the call failed. Absent on success.
postsNoPosts the feed served, in the order it ranked them.
shownNoNumber of posts returned on this page.
cursorNoOpaque cursor for the next page. Absent when the feed has nothing further.
noticeNoGuidance when the feed returned nothing, or was cut.
truncatedNoTrue when the feed has more posts after this page (a cursor was returned).
budgetCappedNoTrue when a page of the requested limit would have passed this server's 48,000-byte response budget, so the feed was asked again for fewer posts and that page was returned whole. The cursor comes from that same response, so paging on from it continues where these posts end. Independent of "truncated", which still means only that a cursor was returned.
totalReturnedNoNumber of posts in this response page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of posts to return (1–100). Default 25. A feed may return fewer than the limit on a page that still has more after it — follow the cursor, not the count."New value: +"Maximum number of posts to return (1–100). Default 25. A feed may return fewer than the limit on a page that still has more after it — follow the cursor, not the count. A page that would pass the 48,000-byte response budget is asked for again with fewer posts and carries \"budgetCapped: true\"; its cursor continues after the posts it holds."
    • addedOutput schema / properties / budgetCapped
      Added value: +{
      +  "description": "True when a page of the requested limit would have passed this server's 48,000-byte response budget, so the feed was asked again for fewer posts and that page was returned whole. The cursor comes from that same response, so paging on from it continues where these posts end. Independent of \"truncated\", which still means only that a cursor was returned.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when the feed returned nothing."New value: +"Guidance when the feed returned nothing, or was cut."
    • addedOutput schema / properties / posts / items / properties / author / properties / verification
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Bluesky verification of the author — what tells a verified account from a look-alike handle. Absent when Bluesky sent none. Who issued it is on bsky_get_profile.",
      +  "properties": {
      +    "trustedVerifierStatus": {
      +      "description": "Whether the author is itself a trusted verifier — same values as verifiedStatus.",
      +      "type": "string"
      +    },
      +    "verifiedStatus": {
      +      "description": "Whether a trusted verifier verified the author: \"valid\", \"invalid\" (verified once, no longer holds), or \"none\". Passed through as Bluesky sends it, so another value may appear.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "verifiedStatus",
      +    "trustedVerifierStatus"
      +  ],
      +  "type": "object"
      +}
  2. Changed3 schema fields changed
    • changedInput schema / properties / feed / description
      Previous value: -"The feed to read — its AT-URI, e.g. \"at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.generator/whats-hot\", or its bsky.app URL, e.g. \"https://bsky.app/profile/bsky.app/feed/whats-hot\". The owner may be a handle or a DID; a handle costs one extra lookup. A trend's \"feedUri\" works as-is."New value: +"The feed to read — its AT-URI, e.g. \"at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.generator/whats-hot\", or its bsky.app URL, e.g. \"https://bsky.app/profile/bsky.app/feed/whats-hot\"; a trailing \"/\", \"?…\", or \"#…\" on the URL is ignored. The owner may be a handle or a DID; a handle costs one extra lookup. A trend's \"feedUri\" works as-is."
    • changedInput schema / properties / feed / pattern
      Previous value: -"^(?:at:\\/\\/((?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\\.)+[a-zA-Z](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?|did:[a-z]+:[a-zA-Z0-9._:%-]*[a-zA-Z0-9._-])\\/app\\.bsky\\.feed\\.generator\\/([a-zA-Z0-9._~:-]{1,512})|https:\\/\\/bsky\\.app\\/profile\\/((?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\\.)+[a-zA-Z](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?|did:[a-z]+:[a-zA-Z0-9._:%-]*[a-zA-Z0-9._-])\\/feed\\/([a-zA-Z0-9._~:-]{1,512}))$"New value: +"^(?:at:\\/\\/(?:(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\\.)+[a-zA-Z](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?|did:[a-z]+:[a-zA-Z0-9._:%-]*[a-zA-Z0-9._-])\\/app\\.bsky\\.feed\\.generator\\/[a-zA-Z0-9._~:-]{1,512}|https:\\/\\/bsky\\.app\\/profile\\/(?:(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\\.)+[a-zA-Z](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?|did:[a-z]+:[a-zA-Z0-9._:%-]*[a-zA-Z0-9._-])\\/feed\\/[a-zA-Z0-9._~:-]{1,512}\\/?(?:[?#].*)?)$"
    • changedOutput schema / properties / posts / items / properties / quoteCount / description
      Previous value: -"Number of quote posts."New value: +"Number of quote posts Bluesky counts — read them with bsky_get_post_quotes. An upper bound on what that returns, since the counter keeps quotes that have left the index."
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, setting expectations for safety. The description adds valuable behavioral context: it explains that reposts and pinned posts are marked, that personalized feeds are inaccessible, and that pagination is cursor-based. It also notes the feed may return fewer than the limit and can be budget-capped, providing deeper insights.

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

Conciseness4/5

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

The description is compact, using short sentences and front-loaded information about what the tool does and how to use it. It packs in many details without being overly verbose, though it could be argued it covers a lot in one paragraph, but it remains readable and efficient.

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?

Given the complexity of the AT-URI formats and pagination, the description is remarkably complete. It covers input formats, output content, behaviors like pinned/reposted flags, and limitations on personalized feeds. The output schema exists, so return-value details are covered, and the description fills any gaps for proper invocation.

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?

The schema description coverage is 100%, so the schema already documents each parameter thoroughly, including default values and constraints. The description adds some value by explaining the feed parameter can be a handle or DID, noting the extra lookup cost, and clarifying how the cursor works, but it doesn't add much beyond the schema's own descriptions.

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

Purpose5/5

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

The description clearly states the tool reads posts from a Bluesky feed generator in ranked order, using a specific verb and resource. It distinguishes itself from siblings by mentioning bsky_get_trending, bsky_get_post_thread, and feed-related concepts, but primarily differentiates through the unique input format and purpose.

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

Usage Guidelines5/5

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

The description explicitly explains when to use this tool: to read what a trend is about, from quoted feeds, or from shared links. It also mentions that personalized feeds cannot be read and that the Discover feed is a common example, guiding the agent on appropriate contexts.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.