Skip to main content
Glama
AdiRatnam

AI Research Agent

by AdiRatnam
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GEMINI_API_KEYYesYour Gemini API key from Google AI Studio.

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
research_topicB

Search the internet for any AI topic.

Args:
    topic: The AI topic to research
manage_reportC

Perform CRUD operations on reports.

Args:
    action: One of 'create', 'read', 'update', 'delete'.
    filename: The name of the file in the reports/ directory.
    content: The text content for create/update.
render_dashboardA

Use Prefab to display the report dashboard in the background and return the URL.

Args:
    title: The research title.
    summary: The summary of the research.
    key_points: List of key points.
    references: List of references URLs.
    file_name: The saved file name.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

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

A3.5/5.0

Scored across 3 tools

Disambiguation5/5

Each tool serves a distinctly different purpose: researching a topic, managing report files with CRUD operations, and rendering a dashboard. There is no overlap or ambiguity between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case: research_topic, manage_report, render_dashboard. No mixing of conventions.

Tool Count4/5

Three tools is slightly low but still reasonable for a focused AI research agent covering the essential tasks of researching, managing reports, and displaying a dashboard. It feels well-scoped.

Completeness3/5

The basic workflow is covered, but there is a notable gap: no tool to list existing report filenames, which is needed for the read/update/delete actions without prior knowledge.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources