Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/jschunter/witnessd-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/jschunter/witnessd-mcp/plugin)<a href="https://agentmods.dev/plugins/jschunter/witnessd-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/jschunter/witnessd-mcp/plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/jschunter/witnessd-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/jschunter/witnessd-mcp/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
witnessd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "witnessd",
"version": "1.0.1",
"displayName": "witnessd: neutral web witness",
"description": "Teaches Claude when to get tamper-evident, third-party evidence of what a public URL or API returned, and connects the witnessd MCP server ($0.02 per snapshot via x402 USDC on Base, Merkle-anchored on-chain, verifiable by anyone).",
"author": { "name": "witnessd" },
"homepage": "https://witnessd.vip",
"repository": "https://github.com/jschunter/witnessd-mcp",
"license": "MIT",
"keywords": ["evidence", "notary", "witness", "timestamp", "x402", "mcp", "agent-payments", "audit"],
"mcpServers": {
"witnessd": {
"command": "npx",
"args": ["-y", "[email protected]"],
"env": {
"WITNESSD_URL": "https://witnessd.vip",
"EVM_PRIVATE_KEY": "${user_config.evm_private_key}",
"WITNESSD_API_KEY": "${user_config.witnessd_api_key}"
}
}
},
"userConfig": {
"evm_private_key": {
"type": "string",
"title": "Wallet private key (USDC on Base)",
"description": "Key of a SMALL dedicated wallet holding a few dollars of USDC on Base. Used only to pay witnessd per call ($0.02 witness, $0.05 retrieve). Leave empty if you use an API key instead, or for free certificate lookups only.",
"sensitive": true,
"default": ""
},
"witnessd_api_key": {
"type": "string",
"title": "witnessd API key (optional alternative)",
"description": "Prepaid witnessd credit key (starts with wk_). Use this OR the wallet key. Leave empty if unused.",
"sensitive": true,
"default": ""
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 187 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 39 lines scan A 322f2ea680dc
witnessd is a plugin published in the GitHub repository jschunter/witnessd-mcp (0 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-27.
Other plugins, from other repositories
legal-risk
Contract review, privacy and data protection, enterprise risk, corporate governance, compliance, and audit readiness. Reviewer-class: its findings are not overrulable by the department under review.
claude-patent-creator-standalone
Complete self-contained patent creation system - NO MCP server required. Uses Claude Code skills, agents, commands, and hooks.
solana-onchain
Interact with the Solana blockchain through Claude Code. Query accounts, analyze transactions, and execute operations with built-in safety safeguards.
sui-dev-tools
Sui blockchain development skills — Move smart contracts, TypeScript SDK, frontend dApp Kit, Seal secrets, and Walrus storage.
evm-decimal-validation
Validate and configure token decimals for EVM-compatible blockchain deployments to prevent amount calculation errors.
safe-ai-skill
Security firewall + supply-chain verifier for Solana AI dev — gates transactions/deploys/secrets and verifies skills/MCPs.