HarnessScope
PYPI · HSCOPE · 2 COMPONENTS · SCANNED SEP 20
Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside.
Available components
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 0 of 16 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 68 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability70
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 650 tokens (~65/item across 10 items; 10 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage81
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 44% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
How do I install the HarnessScope MCP server?
HarnessScope runs locally as a PyPI package, launched with uvx hscope. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · hscope
claude mcp add moongioh-hscope -- uvx hscope
{
"mcpServers": {
"moongioh-hscope": {
"command": "uvx",
"args": [
"hscope"
]
}
}
} {
"servers": {
"moongioh-hscope": {
"command": "uvx",
"args": [
"hscope"
]
}
}
} codex mcp add moongioh-hscope -- uvx hscope
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"moongioh-hscope": {
"type": "local",
"command": [
"uvx",
"hscope"
],
"enabled": true
}
}
} openclaw mcp add moongioh-hscope --command uvx --arg hscope
mcp_servers:
moongioh-hscope:
command: "uvx"
args: ["hscope"] {
"McpServers": {
"moongioh-hscope": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"hscope"
]
}
}
} assistant mcp add moongioh-hscope -t stdio -c uvx -a hscope
{
"mcpServers": {
"moongioh-hscope": {
"command": "uvx",
"args": [
"hscope"
]
}
}
} 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 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 −3
- Stability: pass → 0.80 functional
- 17 Sept 26 0
- Stability: 0.97 → pass security
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 −3
- Stability: pass → 0.80 functional
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 20 Sept 2026 · Analysed pypi/hscope@0.1.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 16 packages
| Packages resolved | 16 |
|---|---|
| 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 →
get_setup_guide ~41
The closed archetype library with each archetype's params schema, the role/rule shapes, and where writes land. Read this before authoring rules.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_workspace_model ~59
The workspace model: roles, gates, rules, context tiers, and the clauses declared unmeasurable.
| Name | Type | Req | Description |
|---|---|---|---|
| workspace_id | string | – | workspace slug under ~/.hscope (default: the only one, or $HSCOPE_WORKSPACE_MODEL) |
No output schema declared.
No examples provided.
list_sessions ~34
Ingested sessions, newest first, with findings and waste.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | max rows (default 20) |
No output schema declared.
No examples provided.
rule_health ~18
Per-rule compliance, coverage and dead-rule candidates.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
session_report ~35
One session's governance report: gate lane, violated rules, findings and the tokens they cost.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | – |
No output schema declared.
No examples provided.
set_role ~130
Upsert a role (path/tool pattern -> label, circuit node, kinds) in the workspace model. Requires HSCOPE_MCP_WRITE=1.
| Name | Type | Req | Description |
|---|---|---|---|
| boundary | string | – | – |
| category | string | – | – |
| kinds | array | – | every rule-facing kind this resource answers to |
| label | string | yes | – |
| match | string | – | – |
| node | string | – | – |
| pattern | string | yes | – |
| rationale | string | – | – |
| workspace_id | string | – | workspace slug under ~/.hscope (default: the only one, or $HSCOPE_WORKSPACE_MODEL) |
No output schema declared.
No examples provided.
set_rule ~153
Upsert a rule instance (archetype + params) in the workspace model. Params are validated against the archetype's schema. Requires HSCOPE_MCP_WRITE=1.
| Name | Type | Req | Description |
|---|---|---|---|
| archetype | string | yes | – |
| canon | string | yes | source pointer, e.g. CLAUDE.md:Core Rules |
| enabled | boolean | – | – |
| id | string | yes | stable id, e.g. R14 |
| params | object | yes | – |
| rationale | string | yes | what this protects |
| severity | string | – | – |
| title | string | yes | – |
| workspace_id | string | – | workspace slug under ~/.hscope (default: the only one, or $HSCOPE_WORKSPACE_MODEL) |
No output schema declared.
No examples provided.
suggest_roles ~71
Roles found on disk that the workspace model lacks (deterministic scan, diffed against the model).
| Name | Type | Req | Description |
|---|---|---|---|
| root | string | yes | workspace root holding CLAUDE.md |
| workspace_id | string | – | workspace slug under ~/.hscope (default: the only one, or $HSCOPE_WORKSPACE_MODEL) |
No output schema declared.
No examples provided.
suggest_rules ~73
Canon clauses no rule covers yet, plus the archetypes available to cover them.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| root | string | yes | workspace root holding CLAUDE.md |
| workspace_id | string | – | workspace slug under ~/.hscope (default: the only one, or $HSCOPE_WORKSPACE_MODEL) |
No output schema declared.
No examples provided.
token_hotspots ~36
Sessions ranked by re-read waste, with cache-hit rate and duplicate-retrieval / loop pressure.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
No output schema declared.
No examples provided.
What is the HarnessScope MCP server?
HarnessScope is an MCP server listed in the public MCP registry as io.github.moongioh/hscope. Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside. This page covers its PyPI package (hscope).
Is the HarnessScope MCP server safe to use?
HarnessScope scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 HarnessScope MCP server expose?
HarnessScope exposes 10 tools: list_sessions, session_report, token_hotspots, rule_health, get_workspace_model, and 5 more. Their descriptions and schemas cost roughly 650 tokens of context every time the server is loaded.
Is the HarnessScope MCP server still maintained?
HarnessScope is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.