Skip to main content
Glama
Ravicha2

io.github.Ravicha2/lit-review-council

by Ravicha2
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ENG_MODELNoModel for engineer agents (default: openrouter/moonshotai/kimi-k2.6)
JUDGE_MODELNoModel for reviewers & synthesis (default: openrouter/deepseek/deepseek-v4-pro)
GITHUB_TOKENYesPractitioner track (GitHub search)
RESEARCH_MODELNoModel for research agents (default: openrouter/z-ai/glm-5.1)
TAVILY_API_KEYYesWeb search across both tracks
OPENALEX_API_KEYNoAcademic track (OpenAlex API)
OPENROUTER_API_KEYYesLLM access via OpenRouter

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
conduct_literature_reviewA
Executes a multi-agent literature review on the provided research question and topics.

Args:
    question: The overarching research question driving the literature review.
    topics: A list of topic dictionaries. Each topic must have:
        - slug: (str) a short hyphenated identifier
        - description: (str) explanation of the topic
        - search_keywords: (list[str]) 2-4 highly specific search queries
        - rationale: (str, optional) why this topic was chosen
    output_dir: (str) Directory to save the final OKF markdown bundle. Defaults to current directory.
    
Returns:
    A success message with the path to the generated OKF bundle directory.

Prompts

Interactive templates invoked by user choice

NameDescription
lit_review_council_instructionsGet the instructions and guidelines for using the lit-review-council orchestrator.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no chance of selecting between overlapping tools. The single tool's purpose is also clearly conveyed by its name and description.

Naming Consistency5/5

The tool name follows a clear verb_noun pattern: conduct_literature_review. With only one tool in the set, there are no naming inconsistencies to evaluate.

Tool Count3/5

A single tool is on the thin side, but it functions as a high-level workflow orchestrator for the entire literature review process. The count feels borderline rather than excessive or trivially mismatched.

Completeness4/5

The tool covers the core workflow from research question and topics to a generated output bundle, so there is no dead end. Minor gaps exist around auxiliary capabilities like validating topics in advance or checking the status of past reviews, but these are workable for a one-shot orchestration tool.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources