ai-research-assistant-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| add_researchC | Add research to the research file |
| read_researchD | – |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| research_summary_prompt | Generate a prompt asking the AI to summarize the latest research topics Returns: str: A prompt asking the AI to summarize the latest research topics |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_latest_research |
TDQS
Scored across 2 tools
The two tools are clearly distinct: one for adding research, one for reading research. No overlap in purpose, making selection unambiguous for an agent.
Both tools follow a consistent verb_noun pattern ('add_research', 'read_research'), making the naming predictable and easy to understand.
With only 2 tools, the server feels thin for a research assistant, but it may suffice for a simple file-based read/write system. The count is acceptable but on the low end.
The tool set is incomplete: it lacks update, delete, search, or any organizational operations. An agent cannot manage or modify research after adding, leading to dead ends.