Review Metric is a powerful AI tool designed for researchers, academics, and scientists. By installing this MCP server, you give Claude the ability to securely submit your local .docx manuscripts to a sophisticated 15-agent pipeline that rigorously analyzes your work for methodological flaws, novelty, and literature alignment.
Multi-Agent Rigor: Your manuscript is analyzed by 15 specialized AI agents, simulating a real-world peer review panel.
Comprehensive Scoring: Receive a definitive 0-100 quality score to gauge your readiness for journal submission.
Zero Data Retention: Your unpublished work is completely secure. We enforce strict zero-data retention, meaning your research is never used for AI training.
Local File Access: Claude can securely read manuscripts directly from your computer without you having to copy/paste massive documents into the chat.
To install this tool, simply add the following configuration to your claude_desktop_config.json file.
(Note: You will need your personal API key from the Review Metric web dashboard https://www.reviewmetric.it.com/).
{
"mcpServers": {
"review-metric": {
"command": "uvx",
"args": ["reviewmetric-mcp"],
"env": {
"REVIEWMETRIC_API_KEY": "your_api_key_here"
}
}
}
}Checks the status or retrieves the final report of a ReviewMetric analysis.
Args: run_id: The unique UUID of the analysis run.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It only states the tool checks status or retrieves report, but fails to disclose idempotency, side effects, error handling, or whether it requires prior submission. This is minimal behavioral insight.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief and front-loaded with the main purpose. The Args section is standard but not wasteful. It could be slightly tighter by integrating the parameter information into the main sentence, but still concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (not shown but indicated), the description does not need to detail return values. However, it lacks context on how the tool fits into the workflow (e.g., must be called after submit_manuscript), what happens if run_id is invalid, or whether it is polling versus one-shot. The description is incomplete for a tool with no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has one required parameter 'run_id' with only type and title. The description adds meaning by specifying it as 'the unique UUID of the analysis run', which clarifies the expected format beyond the schema. Since schema coverage is 0%, this addition is valuable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks status or retrieves a final report of a ReviewMetric analysis. The verb ('checks', 'retrieves') and resource ('ReviewMetric analysis') are specific, and it distinguishes from the sibling tool 'submit_manuscript' which handles a different workflow step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is used after submitting an analysis (sibling 'submit_manuscript'), but no explicit guidance on when to check status versus retrieve report, nor any exclusions or prerequisites. The usage context is somewhat clear but lacks depth.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submits a locally saved .docx manuscript to the ReviewMetric 15-agent AI pipeline.
Args: file_path: The absolute path on the local computer to the .docx file.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It mentions submission to a 15-agent pipeline but omits details on execution time, error handling, or side effects (e.g., file access requirements). Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with a structured args list. It is front-loaded with the core purpose and includes only necessary details, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's single parameter and presence of an output schema, the description covers the basic action but lacks details on whether the submission is synchronous or asynchronous, and what the immediate response indicates. It is adequate but not fully informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning to 'file_path' by specifying it must be an absolute local path for a .docx file. Since schema description coverage is 0%, this extra info is valuable but still leaves out format constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool submits a .docx manuscript to a specific AI pipeline, using a strong verb ('submits') and specifying the resource type and destination. It distinguishes itself from the sibling 'check_analysis_status' by focusing on submission.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the sibling 'check_analysis_status' or any prerequisites. The description only states what it does without context on appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0check_analysis_statussubmit_manuscriptScored across 2 tools
Only two tools with clearly distinct purposes: one is for submission, the other for checking status. No overlap or ambiguity.
Both tool names follow a consistent verb_noun pattern in snake_case (submit_manuscript, check_analysis_status), with clear and descriptive names.
With only two tools for a described 15-agent AI pipeline, the tool count feels too thin for the apparent scope, lacking intermediate or management tools.
The tool surface is severely limited, covering only submission and status checking. Missing are operations such as listing runs, retrieving full reports, or managing analyses.
Connect AI clients to biomedical data and tools.
Open scientific and engineering knowledge for AI agents: search, evidence, document publishing.
Connect AI agents to Replynodes over the Model Context Protocol.
Connect AI agents to SocioLogic's synthetic persona platform for market research.
