mcpbeat Sign in

DiffCI MCP Server

by adityankale190895 Your server? Claim it
answering

DiffCI is answering right now. Last checked moments ago. 1 494 installs a week from npm. It exposes 3 tools. Last commit 8 Oct 2026.

Change-aware CI validation and affected-test guidance for coding agents.

Installs per day peak 981 · avg 231 · +48% w/w
a month agotoday
Uptime history 16 days of history
16 days agonow
100.0%
Uptime 24h
92 of 92 checks
3
Tools
read from the server
118 ms
Response time
average over 24h
1 494
Installs / week
npm and PyPI

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 8 October 2026. No other catalogue keeps this.

8 Oct a tool changed version

What the code does

We read the source, 2 d ago · tools taken from the live server · rules ccca72095570

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

    await sandbox.exec("rm -rf /opt/diffci /workspace && mkdir -p /opt/diffci /workspace", { timeout: 30_000 });
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

File ships in the package but is absent from the source [пакет] dist-client/src/client/cli.js:1, [пакет] dist-client/src/client/context.js:1, [пакет] dist-client/src/client/economics.js:1 и ещё 17
этот файл ставится пользователю, но в репозитории его нет
    const child = spawn(step.executable, step.args, {

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch DiffCI and you get told the day something new turns up.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

run in your terminal
claude mcp add diffci --transport http https://diffci.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "diffci": {
      "url": "https://diffci.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.diffci]
url = "https://diffci.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "diffci": {
      "url": "https://diffci.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "diffci": {
      "url": "https://diffci.com/mcp"
    }
  }
}

Available tools 3

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

diffci
diffci_interpret_report
Validate and summarize a DiffCI observation report, including selective or full mode, affected-test counts, fallbacks, non-interference evidence, and the conservative next action.
diffci_validation_plan
Plan change-aware CI validation, affected-test selection, test impact analysis, or GitHub Actions workflow checks. Returns a safe local DiffCI command without accessing the checkout or executing it.
diffci_verify_workflow_text
Perform a stateless preliminary safety check of GitHub Actions YAML: dedicated observer job, continue-on-error, dependency isolation, read-only permissions, and immutable DiffCI references.

Endpoints

URLTransportStateLatencyChecked
https://diffci.com/mcp streamable-http answering 240 ms 0 min ago

Alternatives to DiffCI

same job, measured the same way
DiffCI
by diffci

Fail-closed, change-aware verification for AI coding agents with affected-test guidance.

3 tools answering
Agent Eval
by rudrendupaul

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

244 installs/wk local only
Guidance Lark MCP
by guidance-ai

Validate and test llguidance grammars with batch testing and documentation

99 installs/wk local only
Testing
by rog0x

Test generation, mocks, coverage analysis for AI agents

32 installs/wk local only
Kineti
by therawlogs

Kineti: spend cap, undo, and test proof for AI coding agents

326 installs/wk local only
Regex Lab
by ryudi84

MCP server for regex testing, matching, replacing, and validation

local only
MCP Test Runner
by lovranran

Local test execution and coverage summaries for onboarding agents.

82 installs/wk local only
Currents
by currents

Self-healing CI tests and proof of work for AI agents

answering

DiffCI — questions

Answers built from our own checks of this server.

What can DiffCI do?
It exposes 3 tools, read directly from the server on our last check. Among them: diffci_interpret_report, diffci_validation_plan, diffci_verify_workflow_text. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is DiffCI working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 118 ms. The bar chart above shows every period we have measured.
How do I connect DiffCI?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does DiffCI need an API key?
No. DiffCI completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is DiffCI?
It answers our handshake in 118 ms on average, which is faster than 78% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use DiffCI?
The npm package @diffci.com/diffci was installed 1 494 times in the last week. Week over week that is +48%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is DiffCI open source?
No, and the distinction matters: its licence is declared as AGPL-3.0-only. That makes it source-available — you can read the code, but the terms are the author's own, not one of the recognised open-source licences. Read them before you build on it.