MCP servers · brevio-ventures

brevio-core: pull-request gate for agent-written code

A local scanner and MCP server that checks code changes for patterns coding agents tend to repeat, with no model call or API key.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

brevio-core flags common mistakes in agent-written code, including secrets written into source, eval on input, @ts-ignore type silencing, silently dropped exceptions, fixed sleeps in end-to-end tests, images without alt text and click handlers a keyboard cannot reach. Its checks are line-level pattern matches on the lines a change adds, not AST or dataflow analysis. Of its 123 catalogued rules, 13 have a scanner; the other 110 are documented for review and for agents.

It suits reviewing pull requests that agents have written, or running a check in continuous integration. The scan, the agent hook and the MCP server use no network and send nothing. It runs without installing, or can be installed, and `init` writes a pull-request workflow, agent rules and a baseline of existing findings, with a dry run and an undo option. Findings can be silenced with a reason. Output can be Markdown for a pull-request comment or SARIF for code scanning.

Teams set rules with a brevio-core.toml file at the repository root or in any folder, and `extends` can pull in a shared policy file. Scans skip dependencies, vendored code, minified files, bundle chunks and TypeScript declaration files by default. The `config` command shows which settings apply to a given file.

Limitations and requirements

Requires Python 3.10 or newer. Checks are line-level pattern matches, not AST or dataflow analysis, and only 13 of 123 rules have a scanner. Only a person can silence the gate: the agent hook and MCP tools ignore ignore comments, and a diff scan reports new suppressions for human review. `extends` reads only files already in the checkout and does not fetch policies. Preview rules never fail a scan.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source
    io.github.Brevio-Ventures/brevio-core

    Code rules for coding agents: scan, explain a rule, learn a guard. Local, with no model call.

    v0.11.2
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
modelcontextprotocol

MCP reference servers

Seven small example servers maintained by the Model Context Protocol project: files, Git, web fetching, memory, time, step-by-step thinking and a test server.

92K GitHub starsSoftware development
Updated 18 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
brevio-core: pull-request gate for agent-written code | AI Gate Discover