proofspec
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROOFSPEC_CONFIG | No | Path to the proofspec.json configuration file. The server reads proofspec.json from the project directory by default. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Proofspec evaluates narrow software claims against constrained evidence. Use proofspec_validate before a run, proofspec_check to create fresh receipts, and proofspec_explain for one claim. Treat unknown, unsupported, blocked, and failed as unverified. A satisfied verifier proves only the configured observation, not the broader quality of a project.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| proofspec_validateB | Validate a Proofspec configuration, including unique IDs and an acyclic claim graph, without checking evidence. |
| proofspec_checkC | Evaluate every claim, append independently labelled evidence receipts, verify the ledger, and return the complete report. |
| proofspec_explainC | Evaluate the specification and return one claim with its policy, dependencies, limitations, evidence, and receipts. |
| proofspec_renderC | Evaluate a specification and render JSON, Markdown, standalone HTML, Mermaid, or SARIF. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| audit-public-claims | Convert public software claims into narrow, executable evidence contracts |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| schema | Proofspec 1 JSON Schema |
| example | A complete executable claim specification |
TDQS
Scored across 4 tools
Each tool has a distinct primary output: validation, full evaluation report, single-claim explanation, and multi-format rendering. However, check, explain, and render all evaluate the specification, so their boundaries overlap somewhat even though the descriptions clarify the differences.
All four tools use the same proofspec_ prefix followed by a clear verb: validate, check, explain, render. The naming pattern is fully consistent and predictable.
Four tools is a well-scoped set for a proofspec configuration utility, with each tool covering a distinct operation. There is no obvious bloat or missing core operation at this count.
The surface covers validation, full evaluation, per-claim explanation, and rendering across multiple formats, which is strong lifecycle coverage for analysis. A minor gap is the absence of a create/init or edit operation, though the server may intentionally be read-only over existing specifications.