Build verified, comprehensive context packs from a folder — with citations, contradiction detection, self-test calibration, and a one-page actionable digest. A Claude Code skill.
Deep Context is an MCP server published by googlarz in the RAG category: build verified, comprehensive context packs from a folder — with citations, contradiction detection, self-test calibration, and a one-page actionable digest. A Claude Code skill.
The repository has 1 stars and 0 forks, with the last commit 5 months ago. Recent commit activity is the strongest signal that reported issues will get attention.
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 Deep Context
Powered by Claude · Grounded in docs
I know everything about Deep Context. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.
Releases
v1.5.0v1.5.0 — Honesty and correctness fixes (round 4) · 29 Apr 2026Round 4 adversarial review. Five findings, all addressed — four of them about the spec overclaiming what it can actually deliver. Medical scrub scope narrowed.** The atomic temp-dir scrub previously claimed to prevent PHI from reaching…
v1.4.0v1.4.0 — Statistical honesty + probe quality + integrity checks · 29 Apr 2026Five improvements to measurement honesty, probe quality, and pack integrity. Statistical honesty — confidence intervals on all pass rates.** Pass rates reported as point estimates on n=10 samples are statistically meaningless (90% at n=10…
v1.3.0v1.3.0 — Quality improvements · 29 Apr 2026Five improvements to verification quality, trust calibration, and usability. What changed Cross-file synthesis in self-test.** The prior self-test sampled only single-file Key content claims — it never tested whether the pack understands…
v1.2.0v1.2.0 — Round 3 adversarial hardening · 28 Apr 2026Security and correctness hardening from a third adversarial review pass. Five findings, all addressed. What changed High-severity fixes Prompt injection now guarded in all verifiers.** The TRUST BOUNDARY block previously only appeared in…
v1.1.0v1.1.0 — security & correctness hardening · 28 Apr 2026Security and correctness hardening from a deep adversarial review (round 2). Six findings, all addressed. What changed Critical fixes Prompt-injection trust boundary.** Subagent extraction prompts now include an explicit `## TRUST…
No package has been published for this server, so install it from source: clone the repository and follow its README.
Is Deep Context 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 Deep Context still maintained?
Yes — the latest release is v1.5.0 (29 Apr 2026), and the last commit was 5 months ago. The repository has 1 stars.