Hares — MCP security scanner
NPM · @ALIHASHIM313/HARES · SCANNED SEP 25
Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)
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 Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 16 of 67 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 45 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability71
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1037 tokens (~259/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the Hares — MCP security scanner server?
Hares — MCP security scanner runs locally as an npm package, launched with npx -y @alihashim313/hares. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @alihashim313/hares
claude mcp add alialrikabi313-hares -- npx -y @alihashim313/hares
{
"mcpServers": {
"alialrikabi313-hares": {
"command": "npx",
"args": [
"-y",
"@alihashim313/hares"
]
}
}
} {
"servers": {
"alialrikabi313-hares": {
"command": "npx",
"args": [
"-y",
"@alihashim313/hares"
]
}
}
} codex mcp add alialrikabi313-hares -- npx -y @alihashim313/hares
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"alialrikabi313-hares": {
"type": "local",
"command": [
"npx",
"-y",
"@alihashim313/hares"
],
"enabled": true
}
}
} openclaw mcp add alialrikabi313-hares --command npx --arg -y --arg @alihashim313/hares
mcp_servers:
alialrikabi313-hares:
command: "npx"
args: ["-y", "@alihashim313/hares"] {
"McpServers": {
"alialrikabi313-hares": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@alihashim313/hares"
]
}
}
} assistant mcp add alialrikabi313-hares -t stdio -c npx -a -y @alihashim313/hares
{
"mcpServers": {
"alialrikabi313-hares": {
"command": "npx",
"args": [
"-y",
"@alihashim313/hares"
]
}
}
} 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.
- 25 Sept 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 23 Sept 26 −3
- Stability: pass → 0.77 functional
- 22 Sept 26 0
- Stability: 0.97 → pass security
- 21 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.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 17 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.
- 16 Sept 26 −3
- Stability: pass → 0.80 functional
- 15 Sept 26 0
- Stability: 0.97 → 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 Sept 2026 · Analysed npm/@alihashim313/hares@0.1.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 67 packages
| Packages resolved | 67 |
|---|---|
| Stale | 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 →
diff_versions Compare two versions of an MCP server for rug-pull changes ~314
Compare two versions of an MCP server and report rug-pull indicators — the classic supply-chain trick where a benign version is installed and trusted, then a later version silently rewrites tool descriptions, schemas or capabilities to carry hidden instructions. Pass two targets (`old` and `new`) as local paths, `npm:pkg@version`, or `gh:owner/repo@ref`. Both are downloaded and analyzed statically; neither is ever installed or executed. A change alone is not an attack — legitimate upgrades change descriptions constantly. Only a change *toward* an injection pattern or a privilege escalation is confirmed; a bare wording change stays needs_review. Read `verdict`: `rug_pull` means review before upgrading.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language for all human-readable text in the result. |
| max_findings | integer | – | Maximum findings to return. The full count is always reported separately. |
| new | string | yes | The newer version to compare: a local path, `npm:<package>@<version>`, or `gh:<owner>/<repo>@<ref>`. Downloaded and analyzed statically; never installed or executed. |
| old | string | yes | The older (baseline) version to compare: a local path, `npm:<package>@<version>`, or `gh:<owner>/<repo>@<ref>`. Downloaded and analyzed statically; never installed or executed. |
| verbose | boolean | – | Return each difference with its full explanation and remediation. Off by default to save context. |
No output schema declared.
No examples provided.
explain_finding Explain a Hares rule in depth ~120
Look up the full catalog entry for a rule id returned by a scan: what it detects, why it is dangerous, how to fix it, its CWE ids, severity, and which layer produced it. Use this to explain a scan result to the user in depth instead of paraphrasing a one-line title.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language for all human-readable text in the result. |
| rule_id | string | yes | A rule id exactly as it appears in a scan result, e.g. 'HARES-L2-EXEC-001'. |
No output schema declared.
No examples provided.
quick_check Fast risk triage of an MCP server ~243
Fast triage of an MCP server: runs layer 1 (structure and metadata) and layer 3 (prompt injection and tool-description poisoning) only, skipping the expensive static-analysis and taint-tracking layer. Use this to decide whether a full `scan_server` is warranted. A clean quick_check does NOT mean the target is safe — code-level vulnerabilities live in the layer this tier skips, and `layers_skipped` says so in every result.
| Name | Type | Req | Description |
|---|---|---|---|
| disabled_rules | array | – | Rule ids to suppress, e.g. ['HARES-L2-EXEC-001']. Suppressed rules are removed from the result, not downgraded. |
| lang | string | – | Language for all human-readable text in the result. |
| max_findings | integer | – | Maximum findings to return. The full count is always reported separately. |
| path | string | yes | What to scan: a local directory path, `npm:<package>` (optionally `npm:pkg@version`), or `gh:<owner>/<repo>` (optionally `gh:owner/repo@ref`). Remote targets are downloaded and analyzed statically; n… |
No output schema declared.
No examples provided.
scan_server Scan an MCP server for security issues ~360
Run a full security scan of an MCP server or agent skill and return a compact risk summary. Covers four layers: package structure and metadata, static code analysis with taint tracking, prompt-injection and tool-description poisoning, and — only when `sandbox` is true — behavioral observation inside Docker. The scanned code is NEVER executed unless `sandbox: true` is passed. Remote targets (`npm:`, `gh:`) are downloaded and read, never installed. The result is deliberately compact: pass `verbose: true` for every finding with its explanation and fix. Always read `coverage` — a clean result over files that failed to parse is not evidence of safety.
| Name | Type | Req | Description |
|---|---|---|---|
| disabled_rules | array | – | Rule ids to suppress, e.g. ['HARES-L2-EXEC-001']. Suppressed rules are removed from the result, not downgraded. |
| lang | string | – | Language for all human-readable text in the result. |
| max_findings | integer | – | Maximum findings to return. The full count is always reported separately. |
| path | string | yes | What to scan: a local directory path, `npm:<package>` (optionally `npm:pkg@version`), or `gh:<owner>/<repo>` (optionally `gh:owner/repo@ref`). Remote targets are downloaded and analyzed statically; n… |
| sandbox | boolean | – | Run layer 4, which EXECUTES the scanned server inside a Docker container to observe its behavior. Off by default. Only enable with the user's explicit consent, and only when Docker is available. |
| verbose | boolean | – | Return every finding with its full explanation and remediation. Off by default because the compact form is far cheaper in context. |
No output schema declared.
No examples provided.
What is the Hares — MCP security scanner server?
Hares — MCP security scanner is listed in the public MCP registry as io.github.alialrikabi313/hares. Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration). This page covers its npm package (@alihashim313/hares).
Is the Hares — MCP security scanner server safe to use?
Hares — MCP security scanner scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 2026. It declares no install or post-install scripts. 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 Hares — MCP security scanner server expose?
Hares — MCP security scanner exposes 4 tools: scan_server, quick_check, diff_versions, explain_finding. Their descriptions and schemas cost roughly 1,037 tokens of context every time the server is loaded.
Is the Hares — MCP security scanner server still maintained?
Hares — MCP security scanner is still listed as active in the MCP registry. We last reached this channel on 25 September 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 Hares — MCP security scanner server under?
Hares — MCP security scanner declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.