Skip to main content
Glama
padmapriyavj

rss-digest-bot

by padmapriyavj
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

RSS Digest BotAdd commentMore actions

A Python-based RSS Digest Bot powered by the Model Context Protocol (MCP) that fetches items from your favorite tech blogs and news sites, and returns AI-generated summaries via Claude.

Related MCP server: OmniWire-MCP

Features

  • Pulls the latest posts from:

  • On-demand summaries driven by Claude (or any other LLM client)

  • Easy to run under:

    • STDIO (for direct stdin/stdout JSON-RPC)

    • HTTP (via mcp dev + Inspector / Claude Desktop HTTP mode)

    • Uvicorn (expose as ASGI app)

  • Minimal dependencies: feedparser, mcp[cli], uvicorn

Installation

  1. Clone this repo:

    git clone https://github.com/padmapriyavj/rss-digest-bot.git cd rss-digest-bot

  2. Create & activate a virtual environment:

    python3 -m venv .venv source .venv/bin/activate

  3. Install dependencies:

    pip install mcp[cli] feedparser uvicorn

  4. Running the app

    uv run main.py

  5. Restart Claude Desktop to view the tool added to it

Configuration for Claude Desktop

Add or edit claude_desktop_config.json in:

~/Library/Application Support/Claude/claude_desktop_config.json

to include:

jsonc { "mcpServers": { "rss-digest-bot": { "command": "/full/path/to/your/project/.venv/bin/mcp", "args": ["run", "main.py"], "transport": "stdio" } } }

  1. Quit & relaunch Claude Desktop.

  2. Under Developer → rss-digest-bot, ensure it’s Enabled.

  3. In chat, click ⚙️ (Search & tools) → confirm rss-digest-bot appears → On.

Available Tools

1 tool
get_digestA
Fetch up to `limit` items total from your default RSS feeds (not per feed).
Returns a list of strings "title: link".
ParametersJSON Schema
NameRequiredDescriptionDefault
limitYes

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are provided, so the description bears full responsibility. It discloses fetching from default feeds and the return format, and that the limit is total. However, it omits details on error handling, empty feed behavior, or authentication requirements.

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?

Two sentences, each serving a distinct purpose: action description and output format. No redundant information. Highly efficient.

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

Completeness4/5

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

For a tool with one parameter and no output schema, the description covers the source, limit behavior, and output format. It is mostly complete, though could mention edge cases like empty feeds or invalid limit values.

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 description incorporates the 'limit' parameter by explaining it controls the total number of items retrieved. Since schema coverage is 0%, this adds essential meaning beyond the schema's type and required fields.

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 fetches items from default RSS feeds, specifies the return format as 'title: link', and clarifies the scope (total, not per feed). This is specific and distinguishes from potential per-feed alternatives.

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

Usage Guidelines4/5

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

The description implies use cases: when a global digest is needed. It provides a negative guideline ('not per feed') but no explicit when-not-to-use or alternative tools. Context is clear.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev0.1.0
    • First observedget_digest
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly stated.

Naming Consistency5/5

A single tool name 'get_digest' follows a clear verb_noun pattern, and there is no inconsistency from other tools.

Tool Count3/5

The server has only one tool, which is on the low end for typical MCP servers. While it might be sufficient for a simple fetch operation, it feels thin for a digest bot that might benefit from feed management tools.

Completeness2/5

The tool covers only fetching a digest from default feeds, but lacks tools for managing feeds (add, remove, list). This is a notable gap for common use cases where users need to configure sources.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • hn-tech-signal-mcp

    malkreide
    A
    license
    A
    quality
    A
    maintenance
    Aggregates tech and AI signals from HackerNews, arXiv, Lobste.rs, and GitHub into a structured briefing. No authentication required.
    8
    MIT

  • OmniWire-MCP

    furkankoykiran
    A
    license
    C
    quality
    C
    maintenance
    Enables AI models to fetch and aggregate news from RSS, Atom, JSON, and HTML feeds with fault-tolerant circuit breaker protection.
    4
    14
    6
    MIT

  • rss-news

    max1ab
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI to manage RSS subscriptions, fetch and summarize news, and organize results into tools like Notion.
    14
    3
    MIT

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/padmapriyavj/RSS-DIGEST-BOT'

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