HOL Guard
PYPI · HOL-GUARD
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
Available components
Last scanned (11 hours ago)
Scores higher than 72% of PyPI servers
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security43
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Declares code that runs automatically (build-time code we could not rule out (a Hatch, PDM or setuptools build hook, a dynamic version we could not read statically, shipped VCS metadata or a stray root module)) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does. View diagnostics → Partial
- 4 of 55 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to hashgraph-online/hol-guard). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 1 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 323 tokens (~53/item across 6 items; 6 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Oct 26 +1
- Stability: 0.97 → pass security
- 17 Oct 26 +42
- Injection markers: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.93 ▲ functional
- Package version: 3.17.2 → 3.25.2 functional
- 15 Oct 26 0
- Package version: 3.17.2 → 3.25.2 functional
- 14 Oct 26 0
- Stability: Stability not yet verified: this package could not be installed in a clean environment, so we have no schema to compare. security
- Tool safety: Tool safety not yet verified: this package could not be installed in a clean environment, so we have no tool text to scan. security
- Schema quality: Schema quality not yet verified: this package could not be installed in a clean environment, so we have no schema to assess. functional
- Capabilities: Protocol version not yet verified: this package could not be installed in a clean environment, so we never saw its MCP handshake. functional
- Tool coverage: Tool coverage not yet verified: this package could not be installed in a clean environment, so we have no tool definitions to assess. functional
- Package version: 3.17.2 → 3.25.2 functional
- 13 Oct 26 −13
- Malware scan: pass → unverified ▼ security
- Known CVEs: partial → pass ▲ security
- Dependency health: partial → 0.97 functional
- Package version: 3.17.2 → 3.25.2 functional
- 12 Oct 26 −25
- Stability: 0.50 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Install scripts: pass → partial ▼ security
- Known CVEs: pass → partial ▼ security
- Malware scan: unverified → pass ▲ security
- The code this package runs automatically changed: its declared build backend → build-time code we could not rule out (a Hatch, PDM or setuptools build hook, a dynamic version we could not read statically, shipped VCS metadata or a stray root module) security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Dependency health: 0.97 → partial functional
- Package version: 3.17.2 → 3.25.2 functional
- 4 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- 3 Oct 26 +15
- Malware scan: unverified → pass ▲ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 25 Oct 2026 · Analysed pypi/hol-guard@3.25.2
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | hashgraph-online/hol-guard |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/hashgraph-online/hol-guard/.github/workflows/publish.yml@refs/heads/main |
| Rekor log index | 3089825165 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:10557f810142867387cf35ff61f07b7bdb13a15a375725177b6bd0e81305c493 |
Background: How many MCP packages publish verified provenance →
Install scripts 2 scripts
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
| build_hook | unreviewed | tool.hatch.build.hooks.custom |
Background: Why install scripts are a supply-chain risk →
Dependencies 55 packages
| Packages resolved | 55 |
|---|---|
| Stale | 4 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
create_policy ~97
Stage a digest-bound policy creation request and initiate secure out-of-band human approval. Does not activate policy while pending. Changes active local enforcement only after human approval through the Guard dashboard. Non-read-only, destructive, idempotent, closed-world.
| Name | Type | Req | Description |
|---|---|---|---|
| candidateDigest | string | yes | – |
| expectedCurrentDigest | – | yes | – |
| idempotencyKey | string | yes | – |
| mode | string | yes | – |
| policyYaml | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
fetch ~40
Fetch a single Guard receipt or inventory item by its opaque namespaced ID. Returns at most 32 KiB of sanitized text.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_guard_status ~26
Report whether local Guard data is available and how fresh it is. Takes no input.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_policy_creation ~56
Read the status of one policy creation request by opaque request ID. Returns pending, applied, declined, expired, or failed. Read-only, non-destructive, idempotent, closed-world.
| Name | Type | Req | Description |
|---|---|---|---|
| requestId | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
search ~42
Search local Guard receipts and inventory. Returns at most 20 sanitized results. The query matches artifact names, harness names, and policy decisions.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
validate_policy ~62
Validate a canonical GuardPolicy YAML document without writing any state. Returns candidate/current digests, semantic diff, and write plan. Read-only, non-destructive, idempotent, closed-world.
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | – |
| policyYaml | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the HOL Guard MCP server?
HOL Guard runs locally as a PyPI package, launched with uvx hol-guard. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · hol-guard
claude mcp add hashgraph-online-hol-guard -- uvx hol-guard
What is the HOL Guard MCP server?
HOL Guard is an MCP server listed in the public MCP registry as io.github.hashgraph-online/hol-guard. Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. This page covers its PyPI package (hol-guard).
Is the HOL Guard MCP server safe to use?
HOL Guard scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the HOL Guard MCP server expose?
HOL Guard exposes 6 tools: search, fetch, get_guard_status, validate_policy, create_policy, get_policy_creation. Their descriptions and schemas cost roughly 323 tokens of context every time the server is loaded.
Is the HOL Guard MCP server still maintained?
HOL Guard is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the HOL Guard MCP server under?
HOL Guard declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.