$ timeahead_
/mcp/blog/about
← mcp scores
45
agentseal
githubgithub ↗hybrid

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

install
source-only — no published npm / pypi package detected.
clone and follow the build instructions in the repo: github.com/getagentseal/agentseal
owner of this server? claim your listing to get a verified badgeclaim →
⚠ 6 credentials detected in repository history via Gitleaks
score breakdown
security (35%)0
freshness (25%)100
adoption (20%)24
quality (10%)100
trust (10%)50
score history (10 updates)
5/10/20265/22/2026
capabilities · what this server can do
tool list unavailable — permissions from static analysis·auth: API key
high risk
● active   ○ not requested  ·  hover each badge for details
● fs read● fs write● network● exec● eval● secrets
why high risk: fs read + fs write + network + exec + eval + secrets active — can execute code, access credentials, and make external network calls.
maintenance health
52/ 100 · is this project alive
contributors (1y)5
top contributor share73%
releases (1y)2
last release57d ago
ci✓ passing
raw data
weekly downloads0
github stars274
forks37
open issues3
license✓ present
readme length12730 chars
last publish1d ago
last commit22d ago
last updated23h ago
score drop alerts
get notified by email when this server's score drops 5+ points