cuad-audit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTHROPIC_API_KEY | No | Anthropic API key for LLM calls in audit_clause and eval-verdicts |
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 |
|---|---|
| search_clausesA | Search the precedent clause library (CUAD liability spans). Returns chunks with stable chunk_ids, source contract, char offsets and scores. If evidence is too weak (status: "below_threshold"), that is an abstention, not an error: do NOT retry with rephrased queries to force a result — relay the abstention. top_scores shows how far below the threshold the best matches were. |
| get_standardA | Return the company standard (playbook) for a clause type: positions P1-P6 with provenance. The standard is data derived from the clause library, not legal advice; see scope_claim in the result. |
| audit_clauseA | Audit a clause against the company standard with grounded citations. Verdicts: acceptable / risky / off-standard (each carries a citation chunk_id resolved by the server to the exact precedent span); insufficient-grounding (evidence too weak OR the verdict failed the faithfulness check — escalate to a human, do NOT guess a verdict yourself); escalate-infra (API failure — retry later; not a judgment about the clause). Relay abstentions verbatim; they are first-class results. |
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 3 tools
Each tool has a distinct purpose: audit_clause evaluates clauses, get_standard retrieves the standard playbook, search_clauses searches precedents. There is no overlap or ambiguity.
All tool names follow a consistent verb_noun pattern: audit_clause, get_standard, search_clauses. No mixing of conventions.
Three tools is appropriate for the focused scope of clause auditing. Each tool serves a necessary role without being redundant or insufficient.
The tool set covers the full workflow: retrieving the standard, searching precedents, and auditing clauses. There are no obvious gaps for the stated purpose.