DocSentinel
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_PROVIDER | No | The LLM provider to use (ollama or openai). | ollama |
| OLLAMA_MODEL | No | The model to use with Ollama. | llama2 |
| OPENAI_MODEL | No | The OpenAI model to use. | |
| OPENAI_API_KEY | No | The API key for OpenAI. | |
| OLLAMA_BASE_URL | No | The base URL for the local Ollama instance. | http://localhost:11434 |
| UPLOAD_MAX_FILES | No | Maximum number of files allowed for upload. | 10 |
| CHROMA_PERSIST_DIR | No | The absolute path or relative path to the directory where Chroma DB data is persisted. | ./data/chroma |
| UPLOAD_MAX_FILE_SIZE_MB | No | Maximum allowed file size for uploads in MB. | 50 |
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 |
|---|---|
| assess_documentC | Assess a security document (PDF, Word, etc.) and return a risk report. Args: file_path: Absolute path to the file to be assessed. scenario_id: The assessment scenario ID (default: "default"). Returns: JSON string containing the assessment report (risks, gaps, remediations). |
| query_knowledge_baseB | Query the internal security knowledge base (policies, standards). Args: query: The search query (e.g., "password complexity requirements"). top_k: Number of results to return. Returns: JSON string with retrieved document chunks. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_kb_stats | Get statistics about the knowledge base (document count, etc.) |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: assess_document analyzes security documents for risks, while query_knowledge_base searches an internal knowledge base. There is no overlap in functionality or ambiguity between them.
Both tools follow a consistent verb_noun naming pattern (assess_document, query_knowledge_base). The naming is predictable and readable across the set.
With only two tools, the server feels thin for its apparent security document assessment domain. This limited set may force agents to work around gaps in functionality, such as missing operations for managing documents or updating the knowledge base.
The tool surface is severely incomplete for a security document assessment system. There are no tools for creating, updating, or deleting documents or knowledge base entries, and no way to manage assessment scenarios or reports beyond the basic assess_document operation.