Skip to main content
Glama
deenesjakoruzh
pkotecha-eng

aria-mcp-server

by pkotecha-eng
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Remote

🧬 ARIA 临床研究 MCP 服务器

一个独立的 MCP 服务器，使任何 Claude 智能体都能实时访问生物医学文献和临床试验——无需 API 密钥。 aria-mcp-server MCP server

工具

工具

描述

search_pubmed

通过 NCBI E-utilities 搜索 3500 万+ 篇同行评审论文

search_clinical_trials

通过 ClinicalTrials.gov v2 API 搜索 40 万+ 项试验

search_isrctn

通过 ISRCTN 注册中心搜索英国/欧洲试验

Related MCP server: clinicaltrials-mcp

提示词

提示词

描述

clinical-research-brief

针对某种疾病的综合证据 + 试验简报

adverse-event-analysis

药物的结构化不良事件 (AE) 和安全性概况

trial-eligibility-checker

跨招募中试验的患者资格评估

资源

资源

描述

info://aria

ARIA 功能和数据源概览

reference://trial-phases

I–IV 期定义及 FDA 特殊指定

reference://high-impact-journals

按专业精选的高影响力期刊

reference://fda-databases

用于药物、安全性和监管研究的 FDA 数据库

查询示例

连接后，您可以询问 Claude：

  • "Search PubMed for ketogenic diet pediatric epilepsy outcomes"

  • "Find recruiting trials for lung cancer immunotherapy"

  • "What does the literature say about veliparib in ovarian cancer, and are there active trials?"

  • "Find UK and European trials for pediatric epilepsy via ISRCTN"

快速入门

pip install aria-mcp-server
aria-mcp-server

连接到 Claude Desktop

添加到 ~/Library/Application Support/Claude/claude_desktop_config.json：

{
  "mcpServers": {
    "aria-clinical-research": {
      "command": "aria-mcp-server"
    }
  }
}

重启 Claude Desktop。服务器将出现在“设置” → “开发者” → “本地 MCP 服务器”下。

数据源

  • PubMed — NCBI E-utilities（公共 API，无需密钥）

  • ClinicalTrials.gov — v2 REST API（公共 API，无需密钥）

  • ISRCTN — 英国/欧洲临床试验注册中心（公共 API，无需密钥）

技术栈

  • FastMCP — MCP 服务器框架

  • Python 3.12+

使用场景

  • 需要实时文献访问的生命科学研究人员

  • 检查资格和招募状态的临床试验协调员

  • 将已发表证据与活跃试验进行交叉引用的药物研发团队

  • 任何需要扎实生物医学知识的 Claude 智能体

项目结构

aria-mcp-server/          ← root, where mcp-publisher runs
├── aria_mcp_server/      ← Python package
│   ├── __init__.py
│   ├── server.py
│   └── tools.py
├── server.json           ← MCP registry metadata
├── pyproject.toml
├── README.md
├── LICENSE
└── glama.json

构建者

Pooja Kotecha · dinq.me/pkotecha-eng

Available Tools

3 tools
search_clinical_trialsA

Search ClinicalTrials.gov for clinical studies. Read-only operation. No authentication required. Uses ClinicalTrials.gov v2 public API (no rate limit documented). Returns up to 10 results per call. No pagination. Returns 'No clinical trials found.' if no results match. Use for: active trials, recruiting studies, inclusion/exclusion criteria, phase information, sponsor details, and trial locations.

ParametersJSON Schema
NameRequiredDescriptionDefault
statusNoTrial status: RECRUITING, COMPLETED, or ALLRECRUITING
conditionYesDisease or condition e.g. 'pediatric epilepsy', 'lung cancer'
max_resultsNoNumber of trials to return, between 1 and 10
interventionNoOptional drug or intervention name to narrow results

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYesFormatted list of trials with NCT ID, title, phase, status, sponsor, conditions, interventions, and eligibility criteria (inclusion and exclusion, listed separately). Returns 'no results' message if nothing found.

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Discloses read-only, no auth required, public API with no documented rate limit, batch size (up to 10), no pagination, fallback message. Sufficient for safe invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences plus a crisp list of use cases. Front-loaded with core purpose. Slightly redundant use-case list could be integrated, but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, so return values are covered. Description covers purpose, usage, behavioral details, and limitations. No gaps given the tool's simplicity and existing structured fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for all 4 parameters. Description adds no additional semantic value beyond what the schema already provides. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it searches ClinicalTrials.gov for clinical studies. Lists specific use cases (active trials, recruiting studies, etc.). Distinguishes from sibling tools (search_isrctn, search_pubmed) by focusing on this specific database.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly lists what to use it for and mentions constraints (max 10 results, no pagination, no auth). Lacks explicit 'when not to use' but context is clear given siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_isrctnA

Search the ISRCTN registry for UK and European clinical trials. Read-only operation. No authentication required. Complements ClinicalTrials.gov by covering trials at UK academic institutions and European research centers not listed on ClinicalTrials.gov. Returns up to 10 results per call, filtered for relevance. Returns 'No ISRCTN trials found.' if no results match. Use for: UK/European trials, academic institution studies, international coverage beyond ClinicalTrials.gov.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesCondition or search terms e.g. 'pediatric epilepsy', 'type 2 diabetes'
max_resultsNoNumber of trials to return, between 1 and 10

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYesFormatted list of trials with ISRCTN ID, title, phase, status, sponsor, condition, outcomes, countries, and inclusion/exclusion criteria.

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses read-only operation, no authentication required, result limits (up to 10), relevance filtering, and empty response message. With no annotations provided, description carries full burden and does well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

4 sentences covering purpose, behavior, complementary role, and usage hints. Front-loaded and no unnecessary words, though could be slightly more concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, usage, behavior, and limitations. With an output schema present, return values are presumably documented elsewhere. Sufficient for a moderate-complexity search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% description coverage, so baseline is 3. Description adds minimal extra meaning (e.g., 'filtered for relevance'), but mostly restates schema info like max results limit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool searches the ISRCTN registry for UK and European clinical trials, distinguishing itself from sibling tools like search_clinical_trials by explicitly noting it complements ClinicalTrials.gov coverage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit use cases: UK/European trials, academic studies, international coverage beyond ClinicalTrials.gov. Implicitly suggests alternatives by noting it complements other registries, though does not explicitly state when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_pubmedA

Search PubMed for peer-reviewed biomedical literature. Read-only operation. No authentication required. Uses NCBI E-utilities public API (rate limit: ~3 requests/sec). Returns up to 10 results per call. No pagination. Returns 'No papers found.' if no results match. Use for: research papers, drug mechanisms, clinical outcomes, disease studies, safety/efficacy data, biomarkers, diagnostics, and any scientific question.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query e.g. 'velarixin pediatric epilepsy phase 2'
max_resultsNoNumber of papers to return, between 1 and 10

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYesFormatted list of papers with title, authors, journal, year, PMID, and abstract. Returns 'no results' message if nothing found.

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully discloses behavioral traits: read-only operation, no authentication, NCBI E-utilities API with rate limit, max 10 results, no pagination, and empty result message. This is thorough and adds significant value beyond structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise paragraph, front-loaded with the purpose, followed by behavioral traits and usage context. Every sentence adds value with no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers all necessary aspects: purpose, behavioral traits, rate limits, result limits, empty result handling, and usage contexts. With an output schema present, return values are not needed. It is complete for a simple tool with two parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add additional meaning beyond what is already in the schema for the two parameters (query and max_results). It restates the max_results limit but provides no new semantic detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it searches PubMed for peer-reviewed biomedical literature, with a specific verb and resource. It distinguishes from sibling tools (clinical trials, ISRCTN) by listing use cases like research papers and drug mechanisms.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a 'Use for' list that implies contexts (research papers, drug mechanisms, clinical outcomes, etc.), but does not explicitly state when not to use or name alternative tools. The sibling context provides implicit guidance, so it is clear but lacks exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.2.1
    • Changedsearch_clinical_trials1 field changed
      • changedOutput schema / properties / result / description
        Previous value: -"Formatted list of trials with NCT ID, title, phase, status, sponsor, conditions, interventions, and eligibility criteria. Returns 'no results' message if nothing found."New value: +"Formatted list of trials with NCT ID, title, phase, status, sponsor, conditions, interventions, and eligibility criteria (inclusion and exclusion, listed separately). Returns 'no results' message if nothing found."
  2. 3 tool updatesv0.2.0
    • Changedsearch_clinical_trials4 fields changed
      • addedInput schema / properties / condition / minLength
        Added value: +1
      • addedInput schema / properties / max_results / maximum
        Added value: +10
      • addedInput schema / properties / max_results / minimum
        Added value: +1
      • addedInput schema / properties / status / enum
        Added value: +[
+  "RECRUITING",
+  "COMPLETED",
+  "ALL"
+]
    • Changedsearch_isrctn4 fields changed
      • addedInput schema / properties / max_results / maximum
        Added value: +10
      • addedInput schema / properties / max_results / minimum
        Added value: +1
      • addedInput schema / properties / query / minLength
        Added value: +1
      • changedOutput schema / properties / result / description
        Previous value: -"Formatted list of trials with ISRCTN ID, title, phase, status, sponsor, condition, outcomes, countries, and eligibility criteria."New value: +"Formatted list of trials with ISRCTN ID, title, phase, status, sponsor, condition, outcomes, countries, and inclusion/exclusion criteria."
    • Changedsearch_pubmed3 fields changed
      • addedInput schema / properties / max_results / maximum
        Added value: +10
      • addedInput schema / properties / max_results / minimum
        Added value: +1
      • addedInput schema / properties / query / minLength
        Added value: +1
  3. 1 tool updatev0.1.8
    • Addedsearch_isrctn
  4. 2 tool updatesv0.1.2
    • Changedsearch_clinical_trials5 fields changed
      • changedInput schema / properties / condition / description
        Previous value: -"Disease or condition (e.g. \"pediatric epilepsy\", \"lung cancer\")"New value: +"Disease or condition e.g. 'pediatric epilepsy', 'lung cancer'"
      • changedInput schema / properties / max_results / description
        Previous value: -"Number of trials to return (1-10, default 5)"New value: +"Number of trials to return, between 1 and 10"
      • changedInput schema / properties / status / description
        Previous value: -"Trial status — RECRUITING, COMPLETED, or ALL (default: RECRUITING)"New value: +"Trial status: RECRUITING, COMPLETED, or ALL"
      • addedOutput schema / properties / result / description
        Added value: +"Formatted list of trials with NCT ID, title, phase, status, sponsor, conditions, interventions, and eligibility criteria. Returns 'no results' message if nothing found."
      • removedOutput schema / x-fastmcp-wrap-result
        Removed value: -true
    • Changedsearch_pubmed4 fields changed
      • changedInput schema / properties / max_results / description
        Previous value: -"Number of papers to return (1-10, default 5)"New value: +"Number of papers to return, between 1 and 10"
      • changedInput schema / properties / query / description
        Previous value: -"Search query (e.g. \"velarixin pediatric epilepsy phase 2\")"New value: +"Search query e.g. 'velarixin pediatric epilepsy phase 2'"
      • addedOutput schema / properties / result / description
        Added value: +"Formatted list of papers with title, authors, journal, year, PMID, and abstract. Returns 'no results' message if nothing found."
      • removedOutput schema / x-fastmcp-wrap-result
        Removed value: -true
  5. 2 tool updates
    • First observedsearch_clinical_trials
    • First observedsearch_pubmed
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a distinct data source: PubMed (literature), ClinicalTrials.gov (global trials), and ISRCTN (UK/European trials). The descriptions include specific use cases and overlap is minimal, so an agent can easily select the appropriate tool.

Naming Consistency5/5

All tools follow a clear 'search_<source>' pattern, making the naming perfectly consistent and predictable. The verb 'search' is used uniformly with the database name as the object.

Tool Count5/5

Three tools are appropriate for a search-focused server covering the key biomedical research databases. Each tool provides a distinct and essential capability without unnecessary bloat.

Completeness4/5

The server covers the main sources for biomedical literature and clinical trials, but lacks other registries (e.g., EU-CTR, WHO ICTRP). Minor gaps exist, but the core search workflows are well covered and agents can work around them.

Maintenance

ActivitySlowing
ResponsivenessResponsive

Resources

Related MCP Connectors

Related MCP Servers