HOL Guard
Score = points from our five tests (install, handshake, maintenance, docs, license). Not a quality or security rating. Methodology
- Install20/20
- Handshake30/30
- Maintenance25/25
- Docs10/15
- License10/10
Tested pypi hol-guard 3.59.0 (Apache-2.0; repo hashgraph-online/hol-guard). Installed pinned with scripts off (uv venv, Python 3.13) and launched with `mcp serve --stdio`: initialize and tools/list over stdio succeeded with no credentials and listed 6 tools (6 annotated by the server: 5 read-only, 1 destructive). Real calls: 1 of 1 real function calls passed.
Tool-call test (2026-11-13 UTC, direct MCP stdio client, no LLM): pass. 1 of 1 real function calls passed. Evidence: local test run, Nov 13, 2026 UTC.
Transport (tested 2026-11-13 UTC): stdio
Token cost (estimate): approx. 521 tokens, cl100k estimate (6 tools, measured 2026-11-13 UTC, version 3.59.0). This is an estimate from our testing of the tool names, descriptions and input schemas, counted with cl100k_base.
Permissions: 6 read, 0 write (state-changing), 0 unclassified · Auth: none · Rate limit: unknown · Pricing unit: unknown
Auth: none. Rate limit: unknown. Pricing unit: unknown.
create_policy— readfetch— readget_guard_status— readget_policy_creation— readsearch— readvalidate_policy— read
handshake and tools listed without a recorded key or OAuth
Score 95/100 · Tools 6 · Token cost approx. 521 tokens · Compare · Last tested 2026-11-13 UTC · Version tested 3.59.0 · Package hol-guard · Repo hashgraph-online/hol-guard
Summary: HOL Guard completed an MCP handshake without credentials and exposed 6 tools.
Evidence summary
- Handshake
- pass
- Tools listed
- 6
- Context cost
- approx. 521 tokens, cl100k estimate (6 tools, measured 2026-11-13 UTC, version 3.59.0; an estimate) ranking · add up your servers' context cost
- API key
- No key needed for the tools we called
- Tested
- 2026-11-13 UTC
Test results
| Test | Result | Points | Evidence |
|---|---|---|---|
| install | pass | 20 | uv pip install hol-guard (Python venv, Linux) succeeded in 4s. |
| handshake | pass | 30 | MCP initialize + tools/list over stdio succeeded with no credentials; 6 tools listed in 8.6s. |
| maintenance | pass | 25 | Repo pushed 0 days before test; 1,099 GitHub stars. |
| docs | partial | 10 | README over 3,000 chars; install instructions present. Check of the package's own README (PyPI long_description (package README)). |
| license | pass | 10 | Apache-2.0 (OSI-approved). |
Local-model readiness
Token cost (estimate): approx. 521 tokens, cl100k estimate for 6 tools · about 6% of an 8k context. This is an estimate from our testing (counted with cl100k_base).
Small-model friendly (schema heuristic, not a model result): unknown.
Not tested
Small-model task runs: Not yet tested.
What we tested and what we didn't
Tested on 2026-11-13 UTC
- Install from the registry
- We connected with no credentials and asked for its tool list: it listed 6 tools (Method details: MCP
initializethentools/list) - Maintenance signals (last push, archived/deprecated status)
- Docs (README length, install and config example)
- License (OSI-approved or not)
- Token cost (estimate)
Not tested
- Security: not audited (no code review, no permission or data-flow analysis)
- Real tasks (no functional task runs yet)
- Behaviour with real credentials or a real account
- Performance, rate limits or load
- Correctness of results beyond the listed tasks
Methodology: how we test. A high score means it installs and responds, not that giving it access to your data carries no risk.
Known security issues
Not yet checked.
Monthly roundup: MCP security issues, October 2026.
Tool list changes
Baseline recorded from the 2026-11-13 UTC test run; changes appear after the next test.
Snapshot hash (fingerprint of the tool list)
6b5ae1ef14b1: SHA-256 of the canonical tool names, descriptions and input schemas. If it changes, the tool list changed.
Raw test record (JSON)
{
"name": "hol-guard",
"version": "3.59.0",
"registry": "pypi",
"status": "working",
"tested": "2026-11-13",
"tools_count": 6,
"deprecated": false,
"archived": false,
"tests": {
"install": [
"pass",
20,
"`uv pip install hol-guard` (Python venv, Linux) succeeded in 4s."
],
"handshake": [
"pass",
30,
"MCP `initialize` + `tools/list` over stdio succeeded with no credentials; 6 tools listed in 8.6s."
],
"maintenance": [
"pass",
25,
"Repo pushed 0 days before test; 1,099 GitHub stars."
],
"docs": [
"partial",
10,
"README over 3,000 chars; install instructions present. Check of the package's own README (PyPI long_description (package README))."
],
"license": [
"pass",
10,
"Apache-2.0 (OSI-approved)."
]
}
}Install
uvx hol-guard mcp serve --stdio
Pin the version we tested
uvx hol-guard==3.59.0 mcp serve --stdio
pip install hol-guard==3.59.0
tested 2026-11-13 UTC. Newer versions may differ and were not tested by us.
{
"mcpServers": {
"hol-guard": {
"command": "uvx",
"args": [
"hol-guard==3.59.0",
"mcp",
"serve",
"--stdio"
]
}
}
}Tools listed
search, fetch, get_guard_status, validate_policy, create_policy, get_policy_creation
Quick config
{
"mcpServers": {
"hol-guard": {
"command": "uvx",
"args": [
"hol-guard",
"mcp",
"serve",
"--stdio"
]
}
}
}Add to config Opens the config generator with this server selected.
Setup
- Install. Run
uv pip install hol-guard(Python venv). This is the exact command we ran on 2026-11-13 UTC. - Configure. Add the mcpServers entry below to your MCP client config.
- Verify. Restart the client and check that tools/list returns tools (6 in our test).
{
"mcpServers": {
"hol-guard": {
"command": "uvx",
"args": [
"hol-guard",
"mcp",
"serve",
"--stdio"
]
}
}
}Test history
- 2026-11-13 UTC: New
FAQ
Is HOL Guard deprecated?
No. hol-guard was not deprecated or archived when we last tested it on 2026-11-13 UTC.
What replaces HOL Guard?
Nothing; HOL Guard is not deprecated as of 2026-11-13 UTC.
Does HOL Guard need an API key?
No. It completed an MCP handshake with no credentials and listed 6 tools.
Embed the badge
Every tested server gets a free embeddable badge. It shows the current score and test date and expires after 90 days. Testing is free; payment never changes a score.