diyan-research-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DIYAN_API_KEY | Yes | Your tenant credential for Diyan research services. | |
| DIYAN_TRANSPORT | No | Transport protocol for the MCP server (e.g., stdio). | stdio |
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 |
|---|---|
| framework_excerptB | 读取经过批准的研究框架片段。framework 为 enterprise/business/finance/people/brand。 |
| stock_snapshot_latestA | 读取最新冻结的股票研究快照，不代表实时市场状态。 |
| hypothesis_getA | 读取通过交付证据门槛的冻结假设；不返回未验证假设。 |
| cognition_radar_readA | 读取历史主题研究雷达摘要，并标注其非实时性。 |
| ic_backtest_summaryA | 读取冻结的因子历史 IC 摘要；不提供原始行情或面板。 |
| research_analyze_safeD | 调用受控研究接口，删除交易字段并附加研究辅助边界。 |
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 6 tools
Each tool targets a distinct research artifact—framework, stock snapshot, hypothesis, radar, IC backtest, and safe analysis—with no overlap in purpose. The descriptions clearly delineate what each returns, eliminating ambiguity.
Tool names mix noun compounds (framework_excerpt, ic_backtest_summary) with verb-suffix patterns (hypothesis_get, cognition_radar_read) and a verb-adjective combo (research_analyze_safe), lacking a unified convention. This inconsistency makes the naming pattern hard to predict.
Six tools is well within the ideal 3-15 range and appropriately scoped for a read-only research server providing diverse artifact views. Each tool earns its place without bloat.
The surface covers multiple research components, but lacks discovery tools to list available frameworks, stocks, or hypotheses. This could require agents to have prior knowledge of entity identifiers, creating a notable gap in usability.