A local guardian service for AI-agent sessions, secrets, policies, and tamper-evident activity records.

Use it to scope agent sessions, protect secrets, apply policy checks, and record activity.

It provides controlled access and an audit history for agent work, including encrypted secrets and chained records that reveal later changes.

haldir — MCP server by ExposureGuard

Install

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.

Clone the repo

git clone --depth 1 https://github.com/ExposureGuard/haldir

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/exposureguard/haldir/haldir/github.svg)](https://agentmods.dev/mcp/exposureguard/haldir/haldir)

Your own site

<a href="https://agentmods.dev/mcp/exposureguard/haldir/haldir"><img src="https://agentmods.dev/badge/mcp/exposureguard/haldir/haldir/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.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/exposureguard/haldir/haldir"><img src="https://agentmods.dev/badge/mcp/exposureguard/haldir/haldir.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

haldir 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.

server.json · 9 lines

What it actually says

{
  "haldir": {
    "command": "uvx",
    "args": [
      "haldir"
    ],
    "env": {}
  }
}

Changes

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 · 9 lines scan A 7761c45d2018

Subscribe to this mod's changes

haldir is an MCP server published in the GitHub repository ExposureGuard/haldir (4 stars, last pushed 21d 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.

Building agents Security ai-agents audit compliance governance identity mcp

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…

gebalamariusz/cloud-audit · not measured

iso20022-evidence-pack-mcp

MCP server that compiles ISO 20022 readiness findings, remediation diffs, and simulated responses into sealed audit evidence packs. Runs locally from the iso20022-evidence-pack-mcp Python package.

sebastienrousseau/iso20022-evidence-pack-mcp · not measured

bouncer

Static compliance-controls checker for UK Online Safety Act & ICO Children's Code. CLI + MCP. Runs locally from the @nugehs/bouncer npm package.

nugehs/bouncer · not measured

mcp-witness

Security testing toolkit for MCP servers and AI agents. Runs locally from the mcp-witness Python package.

edwiniac/mcp-witness · not measured

compliance-aiops

Governed compliance-evidence tooling: reads the AIops governance audit trails and produces framework-mapped (HIPAA/PCI-DSS/SOC2/GDPR), hash-chain-sealed evidence bundles with a built-in governance harness (audit, budget, risk tiers). Runs locally from the compliance-aiops Python package.

AIops-tools/Compliance-AIops · not measured

drp-compliance-sdk

MCP server "drp-compliance-sdk" as configured in TommyP949/drp-compliance-sdk. Runs locally from the drp-compliance-sdk npm package.

TommyP949/drp-compliance-sdk · not measured