Skip to main content
MCP
GitHub MCP Search

mcp-behave

Runtime behavioral auditor for MCP servers — detects undeclared network egress, credential reads, and rug-pulls via native syscall interposition.

What does this entry provide?

mcp-behave is an MCP server entry in ChatHome Skills, sourced from GitHub MCP Search and scored 40/100. Runtime behavioral auditor for MCP servers — detects undeclared network egress, credential reads, and rug-pulls via native syscall interposition. This catalog entry is the indexed repository navid72m/mcp-behave. The command only downloads the repository. It does not build, start, or connect a client. A token, runtime, and client configuration are not in this catalog record. An MCP server exposes callable tools to a client. An agent skill is an instruction package. This entry is an MCP server record, and the catalog only has a source checkout. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. Review the repository push date and repository status before adding mcp-behave to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

  • Source: GitHub MCP Search
  • Quality: 40/100
  • Install method: source code
  • Repo: navid72m/mcp-behave
  • Repo updated: Nov 19, 2026
  • Seen: Nov 20, 2026
Source checkout
git clone https://github.com/navid72m/mcp-behave.git
Install method: source code

The command only downloads the repository. It does not build, start, or connect a client. A token, runtime, and client configuration are not in this catalog record.

Review the upstream source before running this command.

Quality
40
Repo stars
2
Repo updated
Nov 19, 2026
How is this score calculated?
  • Weighted across six dimensions, scored 0-100.
  • Provenance (25): listed in an official or curated registry.
  • Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
  • Maintenance (20): recency of the last push; archived entries score zero here.
  • Adoption (20): repository stars on a log curve.
  • Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
  • Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
  • Security signals subtract up to 20. Scores are recomputed on every daily ingest.

Security signals

  • mediumMatched in: skillBody

    Contains language that tries to override an agent's prior instructions (prompt injection).

    Ignore previous instructionsDispute this flag?

Scan coverage: Install metadata and repository README.

Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.

MCP manifest
{
  "fullName": "navid72m/mcp-behave"
}
Discovery note

Runtime behavioral auditor for MCP servers — detects undeclared network egress, credential reads, and rug-pulls via native syscall interposition.

Report an issue with this listing