Skip to main content
Glama
MissionSquad

@missionsquad/mcp-rss

Official

search_feed_items

Search for specific content across multiple RSS feeds by querying titles, descriptions, or full content. Use this tool to filter and locate relevant feed items efficiently.

Instructions

Search for content across one or more RSS feeds

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
feedsYesRSS feed URLs to search across
queryYesSearch query string
searchInNoWhich fields to search inall

Implementation Reference

  • The execute handler function implementing the search_feed_items tool. It searches across specified RSS feeds for items matching the query in title, description, content, or all fields, using cache or fetching if needed.
      execute: async (args, context) => {
        logger.info(`Searching ${args.feeds.length} feeds for: "${args.query}"`);
    
        const searchResults: Array<{
          feedUrl: string;
          feedTitle: string | null;
          item: FeedItem;
          matches: string[];
        }> = [];
    
        // Fetch all feeds
        for (const feedUrl of args.feeds) {
          try {
            let feed: FeedResult | null = feedCache.get(feedUrl);
            if (!feed) {
              feed = await rssReader.fetchFeed(feedUrl);
              feedCache.set(feedUrl, feed);
            }
    
            // Search items
            const queryLower = args.query.toLowerCase();
            for (const item of feed.items) {
              const matches: string[] = [];
    
              // Search in specified fields
              if (args.searchIn === "all" || args.searchIn === "title") {
                if (item.title?.toLowerCase().includes(queryLower)) {
                  matches.push("title");
                }
              }
    
              if (args.searchIn === "all" || args.searchIn === "description") {
                if (item.description?.toLowerCase().includes(queryLower)) {
                  matches.push("description");
                }
              }
    
              if (args.searchIn === "all" || args.searchIn === "content") {
                if (item.content?.toLowerCase().includes(queryLower)) {
                  matches.push("content");
                }
              }
    
              if (matches.length > 0) {
                searchResults.push({
                  feedUrl,
                  feedTitle: feed.info.title,
                  item,
                  matches,
                });
              }
            }
          } catch (error: any) {
            logger.error(`Failed to search feed ${feedUrl}: ${error.message}`);
          }
        }
    
        logger.info(`Found ${searchResults.length} matching items`);
    
        return JSON.stringify(
          {
            query: args.query,
            searchIn: args.searchIn,
            feedsSearched: args.feeds.length,
            totalMatches: searchResults.length,
            results: searchResults,
          },
          null,
          2
        );
      },
    });
  • Zod schema defining input parameters for the search_feed_items tool: feeds (array of URLs), query (string), and optional searchIn field.
    const SearchFeedItemsSchema = z.object({
      feeds: z.array(z.string()).describe("RSS feed URLs to search across"),
      query: z.string().describe("Search query string"),
      searchIn: z
        .enum(["title", "description", "content", "all"])
        .optional()
        .default("all")
        .describe("Which fields to search in"),
    });
  • src/index.ts:250-325 (registration)
    Registration of the search_feed_items tool via server.addTool, specifying name, description, parameters schema, and execute handler.
    server.addTool({
      name: "search_feed_items",
      description: "Search for content across one or more RSS feeds",
      parameters: SearchFeedItemsSchema,
      execute: async (args, context) => {
        logger.info(`Searching ${args.feeds.length} feeds for: "${args.query}"`);
    
        const searchResults: Array<{
          feedUrl: string;
          feedTitle: string | null;
          item: FeedItem;
          matches: string[];
        }> = [];
    
        // Fetch all feeds
        for (const feedUrl of args.feeds) {
          try {
            let feed: FeedResult | null = feedCache.get(feedUrl);
            if (!feed) {
              feed = await rssReader.fetchFeed(feedUrl);
              feedCache.set(feedUrl, feed);
            }
    
            // Search items
            const queryLower = args.query.toLowerCase();
            for (const item of feed.items) {
              const matches: string[] = [];
    
              // Search in specified fields
              if (args.searchIn === "all" || args.searchIn === "title") {
                if (item.title?.toLowerCase().includes(queryLower)) {
                  matches.push("title");
                }
              }
    
              if (args.searchIn === "all" || args.searchIn === "description") {
                if (item.description?.toLowerCase().includes(queryLower)) {
                  matches.push("description");
                }
              }
    
              if (args.searchIn === "all" || args.searchIn === "content") {
                if (item.content?.toLowerCase().includes(queryLower)) {
                  matches.push("content");
                }
              }
    
              if (matches.length > 0) {
                searchResults.push({
                  feedUrl,
                  feedTitle: feed.info.title,
                  item,
                  matches,
                });
              }
            }
          } catch (error: any) {
            logger.error(`Failed to search feed ${feedUrl}: ${error.message}`);
          }
        }
    
        logger.info(`Found ${searchResults.length} matching items`);
    
        return JSON.stringify(
          {
            query: args.query,
            searchIn: args.searchIn,
            feedsSearched: args.feeds.length,
            totalMatches: searchResults.length,
            results: searchResults,
          },
          null,
          2
        );
      },
    });
  • TypeScript interface defining the parameter types for search_feed_items tool, matching the Zod schema.
    export interface SearchFeedItemsParams {
      feeds: string[];
      query: string;
      searchIn?: 'title' | 'description' | 'content' | 'all';
    }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool searches for content, but doesn't describe how results are returned (e.g., format, pagination, sorting), error handling, rate limits, or authentication needs. For a search tool with zero annotation coverage, this is a significant gap in transparency.

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, efficient sentence that states the core purpose without any wasted words. It's appropriately sized and front-loaded, making it easy to parse quickly.

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?

Given the complexity of a search operation with no annotations and no output schema, the description is incomplete. It doesn't explain what the search returns (e.g., items, metadata), how results are structured, or any behavioral aspects like performance or limitations, leaving key contextual gaps.

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?

The input schema has 100% description coverage, so the schema already documents all parameters thoroughly. The description doesn't add any meaning beyond what's in the schema (e.g., it doesn't explain query syntax or feed URL validation). Baseline 3 is appropriate when the schema does the heavy lifting.

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 clearly states the action ('Search for content') and the resource ('across one or more RSS feeds'), making the purpose immediately understandable. However, it doesn't differentiate this tool from sibling tools like 'get_feed_headlines' or 'fetch_multiple_feeds' which might also involve feed content retrieval, so it doesn't reach the highest score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'get_feed_headlines' or 'fetch_multiple_feeds'. It doesn't mention any prerequisites, exclusions, or specific contexts that would help an agent choose between similar tools, leaving the usage ambiguous.

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

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MissionSquad/mcp-rss'

If you have feedback or need assistance with the MCP directory API, please join our Discord server