Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

MCP Failure Lab

OCI · GHCR.IO/CLOUDLABWORKS/MCP-FAILURE-LAB

Deliberately faulty MCP server for testing how agent clients handle tool errors and disconnects.

45 Trust /100

Last scanned (23 hours ago)

Scores higher than 64% of OCI servers

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security0
  • No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to cloudlabworks/mcp-failure-lab). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 2 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability45
  • AI-judged instruction clarity (poor).Fail
  • Tool/resource definitions use about 30 tokens (~30/item across 1 items; 1 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management10
  • Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 1 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (12)

  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (4)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  • Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  • Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
  • Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 5 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 3 Nov 26 +11
    • Provenance: fail → pass ▲ security
    • The attested source repository moved: cloudlabworks/mcp-failure-lab security
    • Package version: 0.1.1 → 0.1.2 functional
  • 2 Nov 26 33

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Analysed oci/ghcr.io/cloudlabworks/mcp-failure-lab@0.1.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem oci
Reason Verified
Discovered via OCI referrers API
Source repo cloudlabworks/mcp-failure-lab
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/cloudlabworks/mcp-failure-lab/.github/workflows/publish-mcp.yml@refs/tags/v0.1.2
Rekor log index 3653797642
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha256:ded2ecc71fc10a00a13b6eaa1df8bfa6c35df72724541ad05776de3811988432

Background: How many MCP packages publish verified provenance →

MCP tools · 1 exposed · ~30 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
lab_probe ~30

Synthetic failure-lab probe. No external services, filesystem changes or credentials.

NameTypeReqDescription
messagestring––

No output schema declared.

No examples provided.

Install

How do I install the MCP Failure Lab server?

MCP Failure Lab runs locally as a container image, launched with docker run --rm -i -e LAB_SCENARIO -e LAB_DELAY_MS -e LAB_FAILURES ghcr.io/cloudlabworks/mcp-failure-lab:0.1.2. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/cloudlabworks/mcp-failure-lab

# add to Claude Code
claude mcp add cloudlabworks-mcp-failure-lab -- docker run --rm -i -e LAB_SCENARIO -e LAB_DELAY_MS -e LAB_FAILURES ghcr.io/cloudlabworks/mcp-failure-lab:0.1.2

This image reads LAB_SCENARIO, LAB_DELAY_MS and LAB_FAILURES. Set them in your client's env block for this server; docker run -e passes each one through to the container.

Common questions

What is the MCP Failure Lab server?

MCP Failure Lab is listed in the public MCP registry as io.github.cloudlabworks/mcp-failure-lab. Deliberately faulty MCP server for testing how agent clients handle tool errors and disconnects. This page covers its container image (ghcr.io/cloudlabworks/mcp-failure-lab).

Is the MCP Failure Lab server safe to use?

MCP Failure Lab scores 45 out of 100 on VerifyMCP. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the MCP Failure Lab server expose?

MCP Failure Lab exposes 1 tool: lab_probe. Their descriptions and schemas cost roughly 30 tokens of context every time the server is loaded.

Is the MCP Failure Lab server still maintained?

MCP Failure Lab is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the MCP Failure Lab server under?

MCP Failure Lab declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the MCP Failure Lab server?

VerifyMCP ran 12 checks on MCP Failure Lab, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about MCP Failure Lab: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.