contract-sentinel
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| set-company-profileA | Store the company context (industry, headcount, jurisdiction, risk tolerance) for this session. Every other Contract Sentinel tool reads this profile when scoring contracts. |
| ingest-contractA | Store a contract from its raw text. Assigns a unique id, extracts key clauses, the deadline date and the obligations into structured data, and adds it to the tracked contract portfolio. |
| run-sentinel-cycleA | Run the autonomous Contract Sentinel agent loop over the entire tracked portfolio: perceive every contract, score its clause risk with full evidence, decide whether it needs action (deadline close, high risk score, or never reviewed), then act by setting status to needs_attention and recording a recommended action (renew as-is / renegotiate with talking points / let lapse). Designed to run on a schedule in production; runnable on demand here. Renders the contract-board widget. |
| review-portfolioA | Return the contract board: every tracked contract as a card with its risk score, classification (safe or danger), the exact clause text that drove the score, and the recommended action. Optionally filter to safe, danger, or contracts needing attention. Renders the contract-board widget. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Contract Portfolio | The full list of tracked contracts with current status, risk score, classification (safe or danger), the clause text driving each score, deadlines, obligations and the recommended action recorded by the last sentinel cycle. |
| Health Checks | Current health status of all registered health checks |
| Contract Board | UI component for Contract Board |
| Widget Examples | Provides metadata and examples for all registered UI widgets |
TDQS
Scored across 4 tools
Each tool serves a distinct role: profile setup, contract ingestion, automated analysis, and portfolio review. There is no functional overlap between them.
All tool names follow a clear verb-noun pattern using hyphens (set-, ingest-, run-, review-), making the naming predictable and consistent.
With four tools, the set is well-scoped for a contract monitoring workflow: setup, input, processing, and output. No redundancy or excessive expansion.
The core lifecycle (profile setup, contract ingestion, analysis, and review) is covered. Minor gaps like deleting or manually updating contracts are not essential for the sentinel's autonomous monitoring purpose.