investment-agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEEPSEEK_MODEL | No | DeepSeek model identifier. | deepseek-v4-flash |
| DEEPSEEK_API_KEY | No | Your DeepSeek API key. Required only when using a real model with INVESTMENT_MODEL_MODE=live; not needed for the fixture/demo mode. | |
| DEEPSEEK_BASE_URL | No | Base URL for the DeepSeek API. | https://api.deepseek.com |
| INVESTMENT_MODEL_MODE | No | Operation mode for model calls: 'fixture' (default, no API calls) or 'live' (requires DEEPSEEK_API_KEY). | fixture |
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 |
|---|---|
| corpus_infoA | Read corpus coverage, available topics, cutoff and synthetic/live mode before research. |
| search_research_reportsA | Search original research reports. Return exact evidence, provenance and an evidence_set_id. |
| search_newsA | Search news AND company announcements within publication dates, including adverse evidence. |
| list_thesesB | List structured investment theses, IDs, dimensions and report evidence for one topic. |
| read_evidenceA | Read a known corpus chunk by ID, bounded by the research cutoff. No filesystem paths. |
| verify_thesisB | Retrieve subsequent events and verify thesis dimensions; separate facts, expectations and prices. |
| build_research_objectD | Build traceable cross-institution research with separate claim/report counts and mixed directions. |
| calculate_market_responseA | Calculate return, volatility and drawdown from local prices; prices do not validate fundamentals. |
| validate_research_outputA | Validate answer schema and exact quotes against previously returned evidence sets at one cutoff. answer requires summary, confidence (low/medium/high), insufficient_evidence (boolean), citations [{citation_id, document_id, chunk_id, evidence}], and findings [{title, claim, analysis, citation_ids}]. An insufficient answer has low confidence, empty citations and findings. Validation does not prove semantic entailment. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/wst1234566/investment-intelligence-agent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server