Skip to main content
Glama

list_articles

Retrieve RSS articles from FreshRSS with filters for read status, feeds, categories, labels, and sorting options.

Instructions

List articles from FreshRSS with optional filtering

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoNumber of articles to return (1-100)
filterNoFilter by read status
starredNoOnly return starred articles
stateNoPredefined stream/state to list. Overrides other selectors if set.
streamIdNoFull greader stream ID (e.g., feed/123, user/-/label/FolderName, user/-/state/com.google/reading-list). Overrides all other selectors.
feedIdNoFilter by feed ID
categoryNoFilter by category/folder name
labelNoFilter by label name
orderNoSort order
continuationNoContinuation token for pagination

Implementation Reference

  • The handler function for 'list_articles' that calls the API client and formats the results.
    wrapTool('list_articles', async (args: z.infer<typeof listArticlesSchema>) => {
      const result = await client.articles.list(args);
      const formatted = formatArticleList(result.articles);
      const continuation =
        result.continuation !== undefined
          ? `\n\nMore articles available. Use continuation: ${result.continuation}`
          : '';
    
      return textResult(formatted + continuation);
    })
  • Registration of the 'list_articles' tool in the MCP server.
    server.registerTool(
      'list_articles',
      {
        description: 'List articles from FreshRSS with optional filtering',
        inputSchema: listArticlesSchema,
      },
      wrapTool('list_articles', async (args: z.infer<typeof listArticlesSchema>) => {
        const result = await client.articles.list(args);
        const formatted = formatArticleList(result.articles);
        const continuation =
          result.continuation !== undefined
            ? `\n\nMore articles available. Use continuation: ${result.continuation}`
            : '';
    
        return textResult(formatted + continuation);
      })
    );
  • Zod schema definition for 'list_articles' input validation.
    export const listArticlesSchema = z
      .object({
        count: z.number().min(1).max(100).optional().describe('Number of articles to return (1-100)'),
        filter: z.enum(['all', 'read', 'unread']).optional().describe('Filter by read status'),
        starred: z.boolean().optional().describe('Only return starred articles'),
        state: z
          .enum(['reading-list', 'starred', 'read', 'unread'])
          .optional()
          .describe('Predefined stream/state to list. Overrides other selectors if set.'),
        streamId: z
          .string()
          .optional()
          .describe(
            'Full greader stream ID (e.g., feed/123, user/-/label/FolderName, user/-/state/com.google/reading-list). Overrides all other selectors.'
          ),
        feedId: z.string().optional().describe('Filter by feed ID'),
        category: z.string().optional().describe('Filter by category/folder name'),
        label: z.string().optional().describe('Filter by label name'),
        order: z.enum(['newest', 'oldest']).optional().describe('Sort order'),
        continuation: z.string().optional().describe('Continuation token for pagination'),
      })
      .strict();
Behavior2/5

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It mentions 'optional filtering' but fails to explain the override behavior where 'state' overrides other selectors and 'streamId' overrides all selectors, nor does it mention pagination capabilities.

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 single sentence is efficient with zero fluff—every word earns its place. However, given the tool's complexity (10 parameters, override rules, pagination), it is arguably undersized rather than perfectly concise.

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

Completeness3/5

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

While the schema has excellent coverage of individual parameters, the description lacks synthesis of the behavioral model (override hierarchy, pagination). It is minimally viable given the rich schema, but an agent would benefit from explicit mention of the override rules and continuation token usage.

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%, with all 10 parameters well-documented in the schema itself. The description mentions 'optional filtering' which loosely references the parameters but adds no additional semantic meaning, syntax guidance, or examples beyond what the schema provides. Baseline 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?

States a clear verb (List) and resource (articles from FreshRSS) and mentions the filtering capability. However, it fails to distinguish from siblings like list_starred_article_ids or list_unread_article_ids, which return specific subsets of article IDs versus full articles.

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?

Provides no guidance on when to use this tool versus alternatives (e.g., list_starred_article_ids for just IDs). Does not mention pagination with continuation tokens or the parameter override hierarchy (state/streamId overrides) that is critical for correct invocation.

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

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/alysson-souza/freshrss-mcp'

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