Glitch Toolkit MCP server
io.github.AbstractGlitch/glitch-toolkit·v0.1.4Read-only checks that fail a guardrail which is present but has stopped refusing anything
0 stars73 downloads/wk
Reviews
Write oneNobody has reviewed Glitch Toolkit yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Glitch Toolkit tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it
- Code scan7 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 33 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Glitch Toolkit compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 75% of 48,243 servers
- Downloads a week
- 73
- more than 54% of 12,306 servers with a package
Install Glitch Toolkit in Claude Code, Cursor or VS Code
claude mcp add glitch-toolkit -- uvx glitch-toolkit
What the publisher says
From the Glitch Toolkit repository's README, as published. We do not edit it. Read it on GitHub
<!-- mcp-name: io.github.AbstractGlitch/glitch-toolkit --> <!-- The line above is how the official MCP registry proves this PyPI package belongs to the namespace it claims. It is read out of the project description, which is this file baked into the distribution at build time, so it cannot be added to a release after the fact. -->
glitch
A check that has stopped refusing things still passes. That is the failure this looks for.
On 8 September 2026, in the repository this package was extracted from, a test guarded the one chapter of a paid book that is given away free — asserting the sample stops at its cut and does not leak the rest. It was green. It was searching a page that had no book on it, for passages it therefore could never find, and passing. Nothing was broken; the redaction worked fine. The alarm had been disconnected and was still showing a green light.
Every guardrail decays that way eventually, and the decay is silent, because a guardrail that has stopped refusing looks exactly like one with nothing to refuse.
glitch installs six guardrails into your repository and then, whenever you ask, runs each one against a case it is supposed to refuse. One that no longer refuses anything fails here, loudly, instead of passing quietly.
pip install glitch-toolkit
glitch install # put the artifacts in this repository
glitch status # what is installed, what is not
glitch check --all # verify every stepNo dependencies, no network calls, no telemetry. It writes nothing outside the directory you point it at.
What it actually checks
A step is not complete because a file is present. Every check does three things and reports which of them failed:
- finds the artifact
- runs it, and expects it to work
- runs it against a deliberately broken case, and expects it to refuse
Without the third, a check passes the moment you copy a file in, whether or not that file has any teeth left, and it would be green for every reader forever. tests/test_cli.py exists to prove the checker fails that case; its SABOTAGE test installs artifacts that run, exit 0 and refuse nothing.
What install will not do
It will not write your CLAUDE.md, FLEET.md, FLOOR.md or PLAN.md. Four of the six steps are checked against your own file, because for those four the file is the work: a rules file that holds, a desk table with one committer, a floor measured twice, a plan someone else approved. A command that wrote them would turn the path into "you ran an installer". The FLOOR.md and PLAN.md templates ship deliberately unpassable for the same reason.
It will not overwrite. An artifact already in your repo is left alone and reported as kept; --force is how you say otherwise.
It writes nothing outside the directory you point it at, makes no network calls, and has no dependencies outside the standard library.
Running it without installing it
cli.py is one file and stays one file. Copy it into a repository and status and check work with nothing on the path and no install step — that property is deliberate and there is a test for the search paths it uses. Only install needs the rest of the package, and it says so plainly rather than failing oddly.
The MCP server (read-only)
uvx --from 'glitch-toolkit[mcp]' glitch-mcp --repo .Install the extra in an isolated environment, not a system Python. The checker has no dependencies and that is a promise. The [mcp] extra is the opposite: mcp>=2.0 pulls pydantic, starlette, cryptography, opentelemetry and a dozen more, and pip will happily UPGRADE what is already there to satisfy them. Done against a global interpreter on 8 September 2026 it replaced pydantic 1.10 with 2.13 and starlette 0.46 with 1.6, breaking an unrelated FastAPI application on the same machine. uvx builds a throwaway environment and touches nothing else, which is why the registry entry launches it that way.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Glitch Toolkit: common questions
- Is Glitch Toolkit MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the Glitch Toolkit safety report
- How do I install Glitch Toolkit?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Glitch Toolkit need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Glitch Toolkit maintained?
- The last commit was 55 days ago (2026-09-11). The latest release is v0.1.4.
- How does Glitch Toolkit compare with other MCP servers?
- safety score 88/100 (higher than 75% of 48,243 servers); downloads a week 73 (more than 54% of 12,306 servers with a package). Full comparison.