quant-mcp-poc
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PI_MODEL | No | Model name used by the Pi adapter. | v4flash |
| PI_API_KEY | No | API key used as a fallback for smolagents. Leave blank if Pi already has authentication configured. | |
| PI_PROVIDER | No | Provider used by the Pi adapter. | deepseek |
| PI_THINKING | No | Reasoning effort level for the Pi adapter. | medium |
| PI_EXECUTABLE | No | Executable path for the Pi CLI when using the 'pi' agent. | pi |
| DEEPSEEK_MODEL | No | Model name used by the smolagents adapter. | deepseek-v4-flash |
| PI_SESSION_DIR | No | Optional session directory for the Pi adapter. | |
| QUANT_MCP_AGENT | No | Agent backend to use. Choose 'smolagents', 'pi', or the limited 'local' demo. Defaults to 'local' when unset. | local |
| DEEPSEEK_API_KEY | No | API key for the DeepSeek model used by the smolagents adapter. Falls back to PI_API_KEY if not set. | |
| DEEPSEEK_API_BASE | No | OpenAI-compatible endpoint for the DeepSeek API. | https://api.deepseek.com |
| DEEPSEEK_THINKING | No | Set to 'enabled' for tasks that benefit from longer reasoning. Defaults to 'disabled'. | disabled |
| SMOLAGENTS_MAX_STEPS | No | Code-step budget including repairs for smolagents. | 8 |
| QUANT_MCP_LIBRARY_MODULES | No | Comma-separated list of Python modules to discover for the agent. Replaces the default module list. | quant_mcp.pricing |
| SMOLAGENTS_MODEL_TIMEOUT_SECONDS | No | Timeout in seconds per model request, capped by the supplied task timeout. | 120 |
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 |
|---|---|
| run_quant_coding_taskA | Write, run, and debug a quant task automatically, without code-review prompts. timeout_seconds bounds the whole task, including model calls and repairs. |
| analyze_option_portfolioC | Backward-compatible option-analysis tool; prefer run_quant_coding_task for general use. |
| list_artifactsA | List recent generated quant analysis artifacts. |
| read_artifactA | Read a text artifact, or return the path for binary artifacts such as xlsx. |
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
Most tools are clearly distinct: run/analyze execute analysis, while list/read manage artifacts. The only real ambiguity is between run_quant_coding_task and analyze_option_portfolio, but the descriptions clarify that the latter is a backward-compatible specialized option-analysis tool.
All four tools follow a consistent verb_noun pattern: run_quant_coding_task, analyze_option_portfolio, list_artifacts, and read_artifact. There are no mixed conventions or inconsistent verb styles.
Four tools is a well-scoped surface for a POC: one general execution tool, one legacy/specialized analyzer, and two artifact-access tools. Each tool has a clear role with no unnecessary bulk.
The surface covers the core workflow of generating quant analysis and consuming the resulting artifacts. Minor gaps exist, such as no artifact deletion or task-status listing, but agents can generally work around these for a POC.