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/edwiniac/mcp-witnessWrote 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/mcp/edwiniac/mcp-witness/mcp-witness)<a href="https://agentmods.dev/mcp/edwiniac/mcp-witness/mcp-witness"><img src="https://agentmods.dev/badge/mcp/edwiniac/mcp-witness/mcp-witness/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/mcp/edwiniac/mcp-witness/mcp-witness"><img src="https://agentmods.dev/badge/mcp/edwiniac/mcp-witness/mcp-witness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-witness 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 12d ago.
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
{ "mcp-witness": { "command": "uvx", "args": [ "mcp-witness" ] } }
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.
- 12d ago First seen · 8 lines scan A cb0a7376db65
mcp-witness is an MCP server published in the GitHub repository edwiniac/mcp-witness (1 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.
Other mcp servers, from other repositories
ai-audit-trail
Cryptographically verifiable audit trail for AI systems — Ed25519 signed, hash-chained Decision Receipts with ISO 42001 / NIST AI RMF compliance mappings. Runs locally from the ai-audit-trail Python package.
gia-mcp-server
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping. Runs locally from the gia-mcp-server npm package.
agentseal
Verifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain. Runs locally from the agentseal-mcp npm package. Needs 1 environment variable to run.
a2a-trustgate
A2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 49 tools. Runs locally from the a2a-trustgate npm package. Needs 2 environment variables to run.
agent-security
Security scanning and threat detection for AI agents. Runs locally from the agent-security-mcp npm package.
cloud-audit
Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance…