pulsemcp scanned Safe content atomic mcp-remote

Hooks

HooksMCP server that exposes project-specific development tools (tests, linters, formatters, type checkers) through YAML configuration files, enabling AI assistants to execute common development workflows within project boundaries. Built by Steve Cosman, the implementation provides secure command execution with path validation, parameter substitution, and shell injection protection, supporting various parameter types including project file paths, environment variables, and user-provided strings. Features comprehensive security measures including directory traversal prevention, ANSI code stripping for clean output, and configurable timeouts, making it valuable for developers who want AI assistants to run project-specific tooling like pytest, ruff, or mypy without compromising system security or breaking out of project sandboxes.

Cognium trust score
60%
Tier
Scanned

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.

Scan details: Circle-IR · 2026-09-19 · Appeal

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
mcp-remote
Category
security
Source
PulseMCP
Author type
human
Last scanned
2026-09-19
Updated
2026-09-19
View source Find related skills

Use via MCP

MCP

Resolve Hooks from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry