jev-mcp

Purpose: Reducing security and decision risks when agent harnesses process untrusted inputs and shell commands.

Inferred · not functionally tested

Audience: AI agent developers and security engineers

Inferred · not functionally tested

Functions: agents, data_extraction

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, api_only, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

In the AI security & guardrails space, jev-mcp takes a focused approach. Inferred · not functionally tested: It focuses on reducing security and decision risks when agent harnesses process untrusted inputs and shell commands. Inferred · not functionally tested: jev-mcp is an open-source project aimed at AI agent developers and security engineers. Basis unknown · not verified: jev-mcp is open source under the MIT license. Basis unknown · not verified: jev-mcp is available on the command line and API, and it can be self-hosted.

Behind jev-mcp is Aitejiu, and it first shipped in 2026. Development happens publicly on GitHub with 5 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are injection scanning, shell risk gating, and candidate ranking. Inferred · not functionally tested: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.