Harbor is a framework for evaluating and improving AI agents and language models across reusable benchmarks and execution environments. Developers and researchers use it to run agent evaluations, create benchmarks, perform parallel experiments, and generate rollouts for reinforcement-learning optimization, with the catalogue offering skills, instructions, and an MCP integration for the framework.
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/harbor-framework/harborWrote 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/harbor-framework/harbor/mcp-proof-runtime_proof)<a href="https://agentmods.dev/mcp/harbor-framework/harbor/mcp-proof-runtime_proof"><img src="https://agentmods.dev/badge/mcp/harbor-framework/harbor/mcp-proof-runtime_proof/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/harbor-framework/harbor/mcp-proof-runtime_proof"><img src="https://agentmods.dev/badge/mcp/harbor-framework/harbor/mcp-proof-runtime_proof.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
runtime_proof 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- runtime_proof — 100% identical, 0 lines differ
What it actually says
{
"runtime_proof": {
"type": "http",
"url": "http://runtime-mcp-server:8000/mcp"
}
}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.
- 1mo ago First seen · 6 lines scan A 50daf21a3d3c
runtime_proof is an MCP server published in the GitHub repository harbor-framework/harbor (6,185 stars, last pushed today), licensed Apache-2.0. 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 2026-08-30.
Other mcp servers, from other repositories
commutescout
Live California road conditions: CHP incidents, Caltrans closures, chain controls, and wildfires. Remote server at mcp.commutescout.com.
opengate-mcp
Check whether an AI answer is grounded in its context — deterministic, no LLM judge. Runs locally from the @pharmatools/opengate-mcp npm package.
rigforge
MCP server "rigforge" as configured in mrodgersjs-web/rigforge. Runs locally from the rigforge Python package.
agent-eval-gate
MCP server "agent-eval-gate" as configured in linus10x/agent-eval-gate. Runs locally from the agent-eval-gate Python package.
foreman
Python library to manipulate The Foreman through the API. Runs locally from the foreman Python package.
oficio
A calm interface between an Obsidian daily note and Hermes Agent. Runs locally from the oficio Python package.