1. Conduid
  2. Agents
  3. Ctxsentry
MCP server · Agents

Ctxsentry

by · github.com/EivinDDu/ctxsentry

Scan a repository for prompt-injection payloads before you point an AI coding agent at it.

Unclaimed ai-securityclicoding-agentdevsecopsllm-securitymcpprompt-injectionstatic-analysissupply-chain-security
InstallView source
34Low

Scored a month ago · breakdown

About Ctxsentry

Ctxsentry is an MCP server published by EivinDDu in the Agents category: scan a repository for prompt-injection payloads before you point an AI coding agent at it.

The repository has 1 stars and 0 forks, with the last commit a month ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/EivinDDu/ctxsentry

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Ctxsentry

Powered by Claude · Grounded in docs

I know everything about Ctxsentry. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.5.0ctxsentry 0.5.0 · 8 Sep 2026First real-world run → major false-positive reduction. Scanned a 3,300-file production repo: it produced 733 findings (75 "critical"), nearly all false positives. After this pass the same repo produces 5 findings, 0 critical —…
v0.4.0ctxsentry 0.4.0 · 8 Sep 2026`ctxguard` is now `ctxsentry` — the old name was already taken on PyPI. The GitHub repo moved too; old links redirect, and `pre-commit` / GitHub Action refs are unaffected. Now installable pip install ctxsentry # or: pipx install…
v0.3.0ctxguard 0.3.0 · 7 Sep 2026Added `ctxguard bench` — scores the detectors against a labelled corpus in `benchmark/` (20 malicious fixtures across every family, 18 realistic benign ones) and reports precision / recall / F1 / false-positive rate / per-rule…
v0.2.0ctxguard 0.2.0 · 6 Sep 2026Added `--changed [REF]` — scan only files changed vs `REF` (default `HEAD`) plus staged / unstaged / untracked. Fast pre-commit and PR-diff gating. Encoded-payload detector — base64 and hex blobs are decoded and the plaintext rescanned…
v0.1.0ctxguard 0.1.0 · 5 Sep 2026First release of ctxguard — a static scanner for the prompt-injection payloads an AI coding agent ingests the moment it opens a repository: READMEs, docs, `CLAUDE.md` / `.cursorrules`, `.mcp.json` tool descriptions, filenames, and…
Questions

About Ctxsentry

How do I install Ctxsentry?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Ctxsentry safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Ctxsentry still maintained?

Yes — the latest release is v0.5.0 (8 Sep 2026), and the last commit was a month ago. The repository has 1 stars.