# thoughtproof-mcp

> Use this tool when you need to verify the reasoning of AI agents through adversarial multi-model testing, solving problems of decision reliability and trustworthiness. It takes in AI decision outputs and returns ALLOW or HOLD with a JWKS-signed attestation, providing a secure interface for validation. Ideal for use cases requiring high-confidence decision-making, such as critical infrastructure or sensitive information processing.

Canonical page: https://skillsregistry.net/skills/thoughtproof-thoughtproof-mcp  
JSON: https://api.skillsregistry.net/v1/skills/thoughtproof-thoughtproof-mcp

## Description

Adversarial multi-model reasoning verification for AI agents. Claude, Grok, and DeepSeek challenge each decision — returns ALLOW or HOLD with JWKS-signed attestation. x402-gated on Base.

## Trust

- **Trust score (0–1):** 0.57
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/pkpij9fmye)
- **Repository:** <https://github.com/ThoughtProof/thoughtproof-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "thoughtproof-thoughtproof-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/thoughtproof-thoughtproof-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/thoughtproof-thoughtproof-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt