io.github.andyscott88/agentsafe
NPM · AGENTSAFE-MCP-SERVER · SCANNED AUG 3
Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites.
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 →
Supply Chain Security87
- No malware found by supply-chain analysis.Pass
- Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
- No install/post-install scripts declared.Pass
- Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency6
- 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
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 69 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability63
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 176 tokens (~58/item across 3 items; 3 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 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
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
npm · agentsafe-mcp-server
claude mcp add andyscott88-agentsafe -- npx -y agentsafe-mcp-server
codex mcp add andyscott88-agentsafe -- npx -y agentsafe-mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"andyscott88-agentsafe": {
"type": "local",
"command": [
"npx",
"-y",
"agentsafe-mcp-server"
],
"enabled": true
}
}
} openclaw mcp add andyscott88-agentsafe --command npx --arg -y --arg agentsafe-mcp-server
mcp_servers:
andyscott88-agentsafe:
command: "npx"
args: ["-y", "agentsafe-mcp-server"] {
"mcpServers": {
"andyscott88-agentsafe": {
"command": "npx",
"args": [
"-y",
"agentsafe-mcp-server"
]
}
}
} 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.
- 3 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Aug 26 +42
- Provenance: unverified → fail ▼ security
- Install scripts: unverified → pass ▲ security
- Known CVEs: unverified → partial ▲ security
- Malware scan: unverified → pass ▲ security
- License: unverified → fail ▼ functional
- Dependency health: unverified → partial ▲ functional
- Maintenance: unverified → pass ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.23 ▲ functional
- Schema quality: unverified → good ▲ functional
- 1 Aug 26 −6
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 31 Jul 26 +4
- Malware scan: pass → unverified ▼ security
- Tool coverage: unverified → 100 ▲ functional
- 30 Jul 26 −22
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 27 Jul 26 40
First indexed and scored.
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 3 Aug 2026 · Analysed npm/[email protected]
Provenance none
Ecosystem: npm · Outcome: none
Dependencies 95 packages
95 packages in the resolved dependency tree · 95 deprecated · 29 stale.
The dependency tree was only partially resolved, so these counts may be incomplete.
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.
evaluate_login ~44
Check if a URL is safe for an AI agent to submit login credentials to. Prevents credential theft on phishing sites.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The login URL to evaluate |
No output schema declared.
No examples provided.
evaluate_payment ~53
Check if a URL is safe for an AI agent to make a payment on. Uses strict payment-context scoring.
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | — | Transaction amount in dollars |
| url | string | yes | The payment URL to evaluate |
No output schema declared.
No examples provided.
evaluate_url ~79
Check if a URL is safe for an AI agent to interact with. Returns ALLOW, BLOCK, or REQUIRE_HUMAN_APPROVAL with Claude AI reasoning.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | — | The action the agent wants to take |
| data_sensitivity | string | — | Sensitivity of data involved |
| url | string | yes | The URL to evaluate |
No output schema declared.
No examples provided.