Skip to main content
Glama
MissionSquad

@missionsquad/mcp-rss

Official

monitor_feed_updates

Track new items in an RSS feed by specifying a URL and checking updates since a specific time or the last fetch, ensuring timely content monitoring.

Instructions

Check for new items in a feed since a specific time or last check

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sinceYesTime reference for checking updates
urlYesThe RSS feed URL to monitor

Implementation Reference

  • The execute handler function that fetches the RSS feed, computes the 'since' timestamp, filters for new items based on publish/update dates, updates the cache, and returns a structured response with new items and metadata.
    execute: async (args, context) => {
      logger.info(`Monitoring updates for: ${args.url} since ${args.since}`);
    
      // Get current feed state
      const currentFeed = await rssReader.fetchFeed(args.url);
    
      let sinceTimestamp: number;
    
      if (args.since === "last") {
        // Get last fetch time from cache
        const cached = feedCache.get(args.url);
        if (cached) {
          sinceTimestamp = cached.fetchedAt;
        } else {
          // If no cache, return all items as new
          sinceTimestamp = 0;
        }
      } else {
        sinceTimestamp = args.since;
      }
    
      // Filter items newer than timestamp
      const newItems = currentFeed.items.filter((item) => {
        const itemTime = item.published || item.updated || 0;
        return itemTime > sinceTimestamp;
      });
    
      // Update cache
      feedCache.set(args.url, currentFeed);
    
      logger.info(
        `Found ${newItems.length} new items since ${new Date(
          sinceTimestamp
        ).toISOString()}`
      );
    
      return JSON.stringify(
        {
          feedUrl: args.url,
          feedTitle: currentFeed.info.title,
          since: sinceTimestamp,
          sinceISO: new Date(sinceTimestamp).toISOString(),
          checkedAt: currentFeed.fetchedAt,
          checkedAtISO: new Date(currentFeed.fetchedAt).toISOString(),
          newItemsCount: newItems.length,
          totalItemsCount: currentFeed.items.length,
          newItems,
        },
        null,
        2
      );
    },
  • Zod schema defining input parameters: url (string) and since (number timestamp or 'last').
    const MonitorFeedUpdatesSchema = z.object({
      url: z.string().describe("The RSS feed URL to monitor"),
      since: z
        .union([
          z.number().describe("Timestamp in milliseconds to check updates since"),
          z.literal("last").describe("Check updates since last fetch"),
        ])
        .describe("Time reference for checking updates"),
    });
  • src/index.ts:180-237 (registration)
    Registers the 'monitor_feed_updates' tool with the FastMCP server, specifying name, description, parameter schema, and execute handler.
    server.addTool({
      name: "monitor_feed_updates",
      description:
        "Check for new items in a feed since a specific time or last check",
      parameters: MonitorFeedUpdatesSchema,
      execute: async (args, context) => {
        logger.info(`Monitoring updates for: ${args.url} since ${args.since}`);
    
        // Get current feed state
        const currentFeed = await rssReader.fetchFeed(args.url);
    
        let sinceTimestamp: number;
    
        if (args.since === "last") {
          // Get last fetch time from cache
          const cached = feedCache.get(args.url);
          if (cached) {
            sinceTimestamp = cached.fetchedAt;
          } else {
            // If no cache, return all items as new
            sinceTimestamp = 0;
          }
        } else {
          sinceTimestamp = args.since;
        }
    
        // Filter items newer than timestamp
        const newItems = currentFeed.items.filter((item) => {
          const itemTime = item.published || item.updated || 0;
          return itemTime > sinceTimestamp;
        });
    
        // Update cache
        feedCache.set(args.url, currentFeed);
    
        logger.info(
          `Found ${newItems.length} new items since ${new Date(
            sinceTimestamp
          ).toISOString()}`
        );
    
        return JSON.stringify(
          {
            feedUrl: args.url,
            feedTitle: currentFeed.info.title,
            since: sinceTimestamp,
            sinceISO: new Date(sinceTimestamp).toISOString(),
            checkedAt: currentFeed.fetchedAt,
            checkedAtISO: new Date(currentFeed.fetchedAt).toISOString(),
            newItemsCount: newItems.length,
            totalItemsCount: currentFeed.items.length,
            newItems,
          },
          null,
          2
        );
      },
    });
  • TypeScript interface defining the tool's input parameters, matching the Zod schema.
    export interface MonitorFeedUpdatesParams {
      url: string;
      since: number | 'last';
    }
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 checks for updates but lacks details on permissions, rate limits, error handling, or what constitutes 'new items' (e.g., format, pagination). This is inadequate for a tool with potential network or data implications.

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 front-loads the core functionality without unnecessary words. Every part earns its place by specifying the action, resource, and key constraint.

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 tool's complexity (involving network calls and temporal logic), no annotations, and no output schema, the description is incomplete. It doesn't address return values, error cases, or behavioral nuances, leaving significant gaps for agent understanding.

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%, so the schema fully documents the parameters. The description adds no additional semantic context beyond implying temporal filtering, which is already covered in the schema. This meets the baseline for high schema coverage.

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 tool's purpose with specific verbs ('Check for new items') and resource ('in a feed'), and specifies temporal scope ('since a specific time or last check'). It doesn't explicitly differentiate from sibling tools like 'fetch_rss_feed' or 'get_feed_headlines', which prevents a score of 5.

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 'fetch_rss_feed' or 'search_feed_items'. It mentions the temporal aspect but doesn't clarify use cases, exclusions, or prerequisites, leaving the agent without contextual direction.

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