Skip to main content
Glama
brianellin

Bluesky MCP Server

by brianellin

search-feeds

Search for custom feeds on Bluesky using a specific query and limit results to streamline content discovery and access relevant posts efficiently.

Instructions

Search for custom feeds on Bluesky

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoNumber of results to fetch (1-100)
queryYesSearch query for finding feeds

Implementation Reference

  • Full implementation of the 'search-feeds' tool including registration, inline Zod input schema (query: string, limit: number 1-100 default 10), and handler logic that uses Bluesky's unspecced getPopularFeedGenerators API to search feeds, formats results as numbered list with name, URI, description, creator, likes, and handles errors.
      "search-feeds",
      "Search for custom feeds on Bluesky",
      {
        query: z.string().describe("Search query for finding feeds"),
        limit: z.number().min(1).max(100).default(10).describe("Number of results to fetch (1-100)"),
      },
      async ({ query, limit }) => {
        if (!agent) {
          return mcpErrorResponse("Not logged in. Please check your environment variables.");
        }
    
        try {
          const response = await agent.api.app.bsky.unspecced.getPopularFeedGenerators({ 
            query, 
            limit 
          });
          
          if (!response.success) {
            return mcpErrorResponse("Failed to search for feeds.");
          }
    
          const { feeds } = response.data;
          
          if (!feeds || feeds.length === 0) {
            return mcpSuccessResponse(`No feeds found for query: "${query}"`);
          }
    
          const results = feeds.map((feed: any, index: number) => {
            return `Feed #${index + 1}:
    Name: ${feed.displayName || 'Unnamed Feed'}
    URI: ${feed.uri}
    ${feed.description ? `Description: ${feed.description}` : ''}
    Creator: @${feed.creator.handle} ${feed.creator.displayName ? `(${feed.creator.displayName})` : ''}
    Likes: ${feed.likeCount || 0}
    ${feed.indexedAt ? `Indexed At: ${new Date(feed.indexedAt).toLocaleString()}` : ''}
    ---`;
          }).join("\n\n");
    
          return mcpSuccessResponse(results);
        } catch (error) {
          return mcpErrorResponse(`Error searching for feeds: ${error instanceof Error ? error.message : String(error)}`);
        }
      }
    );

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action and target, with no mention of read-only behavior, pagination, rate limits, authentication requirements, or what a 'custom feed' entails. This is a significant gap for a search operation.

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

Conciseness5/5

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

The description is a single concise sentence that directly states the tool's purpose without redundancy. It is front-loaded and contains no filler, earning a high score for efficiency.

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

Completeness2/5

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

With no output schema, no annotations, and simple parameters, the description should compensate by explaining expected results or limitations. It does not mention return format, feed selection criteria, or any constraints beyond what the schema provides, leaving the tool poorly contextualized.

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

Parameters3/5

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

Schema description coverage is 100% as both 'query' and 'limit' have descriptions. The tool description adds no extra meaning beyond the schema, so the baseline of 3 is appropriate.

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 description 'Search for custom feeds on Bluesky' clearly states the action (search) and the target resource (custom feeds), distinguishing it from sibling tools like search-posts and search-people. It lacks extra specificity about feed attributes but is unambiguous enough to identify the tool's core purpose.

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

Usage Guidelines3/5

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

The description implies this tool should be used when searching for feeds specifically, given the resource is 'custom feeds'. However, it provides no explicit when-to-use guidance or alternatives, leaving the agent to infer based on sibling tool names.

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