SkillAgentSearch skills...

mcp-chaos-rig

A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry, all from a web UI.

Install / Use

claude mcp add Typewise -- npx -y github:Typewise/mcp-chaos-rig

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

78/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of mcp-chaos-rig

mcp-chaos-rig scores 78/100 on our quality scale, 3644th of 4,612 Development & Engineering skills we index.

Its MCP Server is 10 KB long, well organised into 14 sections with 6 code examples: a thorough specification that gives an agent plenty to work with.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
29/30
Structure
20/20
Description
15/15
Adoption
4/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-10-22 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 95/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

mcp-chaos-rig compared with similar skills

All 4 of these similar skills score higher than mcp-chaos-rig; compare them before choosing.

SkillScoreStarsUpdatedFormat
mcp-chaos-rig (this skill)by Typewise78103mo agoMCP Server
taste-skillby Leonxlnx100110.8k1d agoCLAUDE.md
Agent-Reachby Panniantong100109.3ktodayCLAUDE.md
headroomby headroomlabs-ai10079.0ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10069.9ktodayCLAUDE.md

Frequently asked questions

How do I install mcp-chaos-rig?
Run claude mcp add Typewise -- npx -y github:Typewise/mcp-chaos-rig. The install tabs above show the steps for each supported agent.
Which AI agents does mcp-chaos-rig work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is mcp-chaos-rig safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 95/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is mcp-chaos-rig still maintained?
The repository was last updated about 3 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
<p align="center"> <img src="src/ui/favicon.svg" alt="MCP Chaos Rig" width="80" height="80"> </p> <h1 align="center">MCP Chaos Rig</h1> <p align="center">A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry, all from a web UI.</p> <p align="center"> <a href="https://www.npmjs.com/package/mcp-chaos-rig"><img src="https://img.shields.io/npm/v/mcp-chaos-rig.svg" alt="npm version"></a> <a href="https://github.com/Typewise/mcp-chaos-rig/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/mcp-chaos-rig.svg" alt="license"></a> <a href="https://www.npmjs.com/package/mcp-chaos-rig"><img src="https://img.shields.io/npm/dm/mcp-chaos-rig.svg" alt="downloads"></a> </p>

The problem

You're building an MCP client. You need to test OAuth flows, token refresh, tool discovery, error handling, and session lifecycle. Production servers don't fail on command. You need a server that does.

What Chaos Rig does

Run a local MCP server where you control everything:

  • Break authentication: force 401s and 500s mid-session, expire tokens on demand, reject refresh tokens
  • Break tools: disable tools to trigger tools/changed, switch schema versions live
  • Break reliability: add random latency, make tool calls fail at configurable rates
  • See everything: live request log shows inbound JSON-RPC calls and outbound SSE responses, with click-to-expand bodies

Server tab

Test scenarios

| Scenario | How to test it | | --------------------------- | ------------------------------------------------------------------------------------------------ | | OAuth 2.1 consent flow | Use the interactive consent page: approve, decline, invalid code, tampered state | | Fixed header auth | Switch to Headers mode, configure key-value pairs, verify client sends them | | Missing/wrong headers | Send requests with missing or mismatched headers — 401 with details | | Token rejection mid-session | Toggle "Reject OAuth" to 401 or 500 while client is connected | | Token expiry and refresh | Set access token TTL to a short value, watch the client refresh | | Reject refresh tokens | Toggle "Reject refresh tokens" to force re-authentication | | Wrong client refreshing | Enable "Enforce refresh token ownership" — catches clients that lose credentials and re-register | | No dynamic registration | Switch to "Pre-registered client only" — /register 404s, only your client_id works | | Rotated client credentials | Change the pre-registered client_id mid-session — the old one now fails with invalid_client | | Scope discovery conflict | Set different scopes in metadata vs WWW-Authenticate header, test which the client trusts | | Tool disappearing | Disable a tool in the Tools tab. Clients receive tools/changed | | Tool schema changing | Switch echo or add between v1 and v2 schemas | | Flaky tool calls | Set failure rate 0-100%. Failed calls return isError: true | | Slow responses | Enable slow mode with configurable latency range | | PKCE code exchange | OAuth consent page offers "Wrong Code" and "Wrong State" options | | Database-backed tools | CRUD operations on a real SQLite contact database |


Quick start

npx mcp-chaos-rig

Control panel at localhost:4100/ui, MCP endpoint at http://localhost:4100/mcp. Requires Node 20+.

If you prefer a global install:

npm install -g mcp-chaos-rig
mcp-chaos-rig

Or run from source:

git clone https://github.com/Typewise/mcp-chaos-rig.git
cd mcp-chaos-rig
npm install
npm run dev

Remote access

If your production environment needs to reach Chaos Rig, expose it via a tunnel (ngrok, Cloudflare Tunnel, etc.) and set BASE_URL so OAuth redirects resolve correctly:

BASE_URL=https://your-tunnel.example.dev npx mcp-chaos-rig

Auth mode starts at Bearer, so a tunnel-facing rig usually wants AUTH_MODE too (none, bearer, headers, oauth). For OAuth with pre-registered credentials, see Client registration.

Auth state

All state is in-memory and resets on restart, back to whatever the environment seeds (AUTH_MODE, OAUTH_CLIENT_MODE, STATIC_*) or to the built-in defaults. Bearer starts with token test-token-123 (valid until changed). OAuth tokens expire per TTL. Refresh tokens track ownership per client when enabled. After restart, do one refresh with ownership off to re-seed, then turn it on.


Control panel tabs

Server

Configure auth mode, slow mode (random latency), and flaky tools (% failure rate).

| Auth mode | Behavior | | ------------- | ----------------------------------------------------- | | None | All requests pass through | | Bearer | Requires Authorization: Bearer test-token-123 | | Fixed Headers | Requires configured key-value header pairs on every request | | OAuth 2.1 | Full authorization flow with interactive consent page |

Bearer, Fixed Headers and OAuth modes support fault injection: force 401 or 500 responses to test error handling. The mode starts at Bearer unless AUTH_MODE says otherwise.

OAuth mode adds controls for client registration, access token TTL, refresh token rejection, and refresh token ownership enforcement. OAuth endpoints are listed in a collapsible section.

Client registration

| Mode | Behavior | | -------------------------- | ----------------------------------------------------------------------------------------- | | Dynamic registration | Clients register themselves at /oauth/register and get fresh credentials (RFC 7591) | | Pre-registered client only | Only the configured client_id / client_secret is accepted; registration is turned off |

Static mode reproduces authorization servers that issue credentials out of band (Google, Atlassian, most enterprise IdPs):

  • registration_endpoint disappears from the well-known metadata
  • POST /oauth/register and POST /register return 404 registration_not_supported
  • any other client_id gets invalid_client at /authorize and /token
  • an empty client_secret makes it a public client, so the token endpoint accepts auth method none
  • redirect URIs must match a configured one exactly, except the port on loopback hosts (RFC 8252)

The shipped default redirect URI points at a local client. Testing against a deployed client means registering that client's callback instead, or /authorize returns 400 invalid_request — the response lists the URIs that are registered, since the port relaxation only applies to loopback hosts and https:// callbacks must match exactly.

Set the client at boot so a tunnel-facing rig starts ready:

AUTH_MODE=oauth \
OAUTH_CLIENT_MODE=static \
STATIC_CLIENT_ID=acme-client \
STATIC_CLIENT_SECRET=acme-secret \
STATIC_REDIRECT_URIS=https://platform-api.example.app/api/mcp/oauth/callback \
BASE_URL=https://your-tunnel.example.dev npx mcp-chaos-rig

AUTH_MODE is required here: it defaults to bearer, and the OAuth endpoints 404 until it is oauth (none, bearer, headers, oauth; anything else fails at startup). STATIC_REDIRECT_URIS is comma-separated. An empty STATIC_CLIENT_SECRET= boots a public client. Everything stays editable from the Server tab afterwards.

Changing the client_id drops the previous one, so you can test credential rotation against a live client. Set it from the API too:

curl -X POST localhost:4100/api/oauth-client -H 'Content-Type: application/json' \
  -d '{"mode":"static","clientId":"acme-client","clientSecret":"acme-secret","redirectUris":["http://localhost:3000/api/mcp/oauth/callback"]}'

Tools

Tools tab

Toggle tools on/off. Disabling sends tools/changed to connected clients. Some tools (echo, add) support version switching.

Available tools:

  • echo: returns your message (v2 adds format options)
  • add: sums two numbers (v2 accepts an array)
  • get-time: current server time as ISO 8601
  • random-number: random integer in a range
  • reverse: reverses a string
  • typeEcho: echoes one optional parameter per JSON Schema primitive, to check a client round-trips every type
  • dispute-charge: files a billing dispute, returns a JSON receipt
  • list-contacts, get-contact-by-id, get-contact-by-email, search-contacts, create-contact, update-contact, delete-contact: SQLite CRUD

Three large-schema tools start disabled, for testing how a client handles wide inputs: submit-customs-declaration (all fields required), create-product-listing (25 required, 25 optional), search-properties (50 optional filters).

Contacts

Contacts tab

View and reset the SQLite database backing the contact tools. Starts with three seed records.

Log

Log tab

Live request log showing inbound requests and outbound SSE responses. Displays timestamp, source (mcp/auth/sse), method, status, JSON-RPC method, tool name, and arguments. Click any truncated body or args line to expand it. Keeps last 200 entries.


OAuth consent page

OAuth consent page

When auth mode is OAuth, the authorization endpoint shows an interactive consent page:

| Button | Result | | ----------- | -------------------------------------------------- | | Approve | Redirects with valid authorization code | | Decline | Redirects with error=access_denied | | Wrong Code | Redirects with invalid code (token exchange fails) | | Wrong State | Redirects with tampered state parameter |


Links

Related Skills

View on GitHub
GitHub Stars10
CategoryDevelopment
Updated3mo ago
Forks1

Languages

TypeScript

Trust signals

95/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 info