pulsemcp scanned Safe content atomic mcp-remote

Over-Reach Detector

An audit tool that compares declared task scope (via fnmatch glob patterns for allowed files and categories) against actual file changes made by AI coding agents. Reports mismatches across five categories: tests, docs, infra, config, and code. Functions as a disclosure tool rather than a blocker, leaving enforcement decisions to the caller. Integrates with Cursor, Claude Code, and other MCP-compatible agents via stdio transport.

Cognium trust score
65%
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 2026-09-01.

Scan details: Circle-IR · 2026-09-01 · Appeal

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
mcp-remote
Category
productivity
Source
PulseMCP
Author type
human
Last scanned
2026-09-01
Updated
2026-09-01
View source Find related skills

Use via MCP

MCP

Resolve Over-Reach Detector 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