MCP servers · brightbeamai

CHAP Coordinator: auditable record of human decisions on agent work

Coordinator package for the CHAP protocol that records human approvals, edits, overrides and escalations on AI agent work in an auditable log.

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

The coordinator is the service that mediates a CHAP workspace. It checks each incoming call against the workspace's rules, answers it, and writes each accepted change to an ordered audit log. Calls cover task creation and completion, review requests, approvals, rejections, overrides, handoffs, escalations and reads of the audit log. Overrides are recorded with a diff, a rationale and tags that a team defines, so corrections can be analysed later. With the hash chain switched on, each log entry carries the hash of the one before it, which makes alterations detectable.

It suits teams where agents draft or recommend and people approve, correct or escalate, and where those decisions need to be queried or verified later rather than left in chat threads and ticket comments. Optional profiles add signed calls, verified identities and a transparency log for workspaces that need them.

The TypeScript package (npm) and the Python package (pip) both implement Core and every profile. Either can be embedded in your own process or run as a server. A new workspace advertises the Core and review profiles unless others are named, and the coordinator refuses calls that belong to profiles the workspace does not advertise.

Limitations and requirements

CHAP is a public draft. Before version 1.0, a minor release may break existing behaviour, and the changelog lists each break with a migration. Tamper detection through the hash chain depends on a recent chain head being kept out of the operator's reach. Calls for profiles a workspace does not advertise are refused.

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 13 Nov 2026 · its page on the source
    CHAP Coordinator

    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.

    v0.3.5
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
docker

Docker Hub MCP Server

Docker's MCP server that helps an AI assistant find and compare container images on Docker Hub and, with your token, manage your own repositories and tags.

171 GitHub starsCloud & DevOpsSoftware development
Updated 13 Nov 2026
MCP servers
awslabs

MCP servers for AWS (AWS Labs)

A large open-source collection of MCP servers from AWS Labs for building and operating on AWS: documentation, infrastructure, databases, AI services, cost and more.

9.9K GitHub starsCloud & DevOpsData & databases
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
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026