article-research-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_COMPAT_MODEL | No | Model name for LLM scoring. | lfm2.5:latest |
| ARTICLE_DAILY_TOPICS | No | Comma-separated topics for daily briefs. | |
| ARTICLE_RESEARCH_ROOT | No | Root directory for research output. | ~/research |
| OPENAI_COMPAT_API_KEY | No | API key for the OpenAI-compatible API. | ollama |
| OPENAI_COMPAT_BASE_URL | No | Base URL for an OpenAI-compatible API (e.g., local Ollama). | |
| ARTICLE_RESEARCH_RSS_FEEDS | No | Comma-separated URLs of RSS feeds to include as sources. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| plan_article_researchC | Return a structured research plan for agents (steps, tool order, output paths). depth: quick | standard | deep |
| get_research_methodologyA | Full methodology markdown (depth levels, source tiers, checklist). |
| search_articlesA | Search article sources (default: devto + hn). Returns unified summaries. Set score_with_llm=true when OPENAI_COMPAT_BASE_URL is configured (e.g. Ollama). |
| build_topic_briefC | Fetch, dedupe, rank articles and return a markdown brief for planning. depth=deep enables LLM scoring automatically when OPENAI_COMPAT_* is set. |
| get_articleB | Fetch full article body by source and numeric id (devto | hn). |
| save_research_noteC | Persist a research note under ~/research// (creates dirs). |
| list_article_sourcesA | List supported sources and whether LLM scoring is configured. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| methodology_resource |
TDQS
Scored across 7 tools
Each tool serves a distinct function: planning, searching, briefing, fetching articles, saving notes, and providing metadata. No two tools have overlapping purposes, ensuring clear selection.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., build_topic_brief, get_article, list_article_sources). No mixing of styles or conventions.
Seven tools cover the core research workflow without being excessive. The scope is well-balanced, providing essential functionality without bloat.
The set covers planning, searching, fetching, and saving, but lacks a tool to retrieve or list saved research notes. This minor gap does not critically impair the workflow.