research-scope-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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| plan_researchB | Turn a research scope into a source-target plan with kill criteria: primary-source targets, corroborating targets, and when to abandon the topic for lack of sources. |
| fetch_and_scoreA | Crawl one source URL and return an explainable 0-100 quality score: primary-source detection, publication freshness, paywall and conflict-of-interest flags. Scores are registered for use in build_report/check_report. |
| build_reportA | Assemble a report shell from already-scored sources: claims section stubs, numbered citation registry, scoring appendix. Returns the markdown and saves it under data/reports/. |
| check_reportA | Verify every substantive claim in a report cites at least one scored source. Orphan claims are returned as an error list — never a pass. Accepts a report id (as built) or a markdown file path. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool occupies a distinct stage of a linear research pipeline: plan_research (planning), fetch_and_score (acquisition), build_report (assembly), and check_report (verification). There is no overlap in purpose, so an agent can select unambiguously.
All names use snake_case with a verb-led pattern (plan_research, build_report, check_report), which is predictable and readable. fetch_and_score is the one deviation, using a compound verb_and_verb form rather than verb_noun, but it remains clear.
Four tools is well-scoped for a focused research workflow, with each tool earning its place as a pipeline stage. It is slightly lean, as there is no dedicated source-discovery step, but nothing is redundant.
The surface covers the full lifecycle: plan, fetch+score, build, and verify, including a citation registry and orphan-claim checking. The main gap is source discovery/search, leaving the agent to supply URLs itself, but core workflows have no dead ends.