Warning

34/100

7 days ago

claude-env-platform

Item: claude-env-platform
Rating: 34
Author: M8ven

Turbocharge Claude Code with a privacy-first AI workspace that never leaves your machine. Local RAG, graph memory, auditing with hash chains, policy enforcement, and specialist agents—built for secure, autonomous software development on Apple Silicon.

→ Atri10/claude-env-platform · listed on github_code

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

Atri10

Source: github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

🚨

Hardcoded credentials detected

1 live-looking API key in source: 1 AWS access key

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configCLAUDE_ENV_HOMEEverything runs through a single Python virtual environment at $/venv/

configCLAUDE_ENV_TIER

configCLAUDE_ENV_DOCS_DIR

configCLAUDE_ENV_SESSION

configCLAUDE_ENV_REPO_ROOTgit MCP: fatal: not a git repository unset claude-env onboard <repo>; restart Claude Code.

configCLAUDE_ENV_MAX_READ_BYTES

configCLAUDE_ENV_REPO_NAMElancedb-rag returns empty Wrong /BRANCH Check ls ~/.claude-env/knowledge/lancedb/; re-onboard; restart.

configCLAUDE_ENV_BRANCH

configCLAUDE_ENV_MEMORY_NS(CLAUDE_ENV_REPO_ROOT=$ProjectFileDir$, tier, =proj-<slug>). Do

configCLAUDE_ENV_MEMORY_ISOLATEDMemory leaks across repos unset for tier ≥ 2 Set tier ≥ 2 in repo policy and re-onboard.

configCLAUDE_ENV_MEMORY_WRITE

configCLAUDE_ENV_CMD_TIMEOUT

configCLAUDE_ENV_APPROVAL_WAIT_S, default 120s) until you Approve/Deny. The decision

configCLAUDE_ENV_APPROVAL_PORT

configCLAUDE_ENV_APPROVAL_AUTO_UI

configCLAUDE_ENV_APPROVAL_SOUNDfalse), auto-opens the approvals web UI, and waits (up to

configCLAUDE_ENV_SCRATCH_TTL_HOURS

configCLAUDE_ENV_HOOK_AUDIT_ALL

configCLAUDE_ENV_HOOK_FAIL_CLOSEDtrue in the environment Claude Code runs under. Full

configCLAUDE_ENV_MCP_FIRST

configCLAUDE_CODE_SCRATCHPAD

configCLAUDE_SCRATCHPAD_DIR

configCLAUDE_ENV_LOG_MAX_BYTES

configCLAUDE_ENV_LOG_BACKUPS

configCLAUDE_ENV_LOG_LEVEL

configCLAUDE_ENV_FEEDBACK_BOOST

configRAG_CONFIG_YAML

configEMBED_BACKENDWhich embedder backend to use (registry key, rag/embeddings/registry.py) llama_cpp

configEMBED_MODEL_PATHPath to the .gguf file required — unset raises a clear error

configEMBED_MODEL_NAMEProvenance label recorded in rag_index_state filename

configEMBED_CTX/ EMBED_GPU_LAYERS / EMBED_DIM Context window / GPU offload / vector dim 2048 / -1 / 768

configEMBED_GPU_LAYERSEMBED_CTX / / EMBED_DIM Context window / GPU offload / vector dim 2048 / -1 / 768

configEMBED_DIMEMBED_CTX / EMBED_GPU_LAYERS / Context window / GPU offload / vector dim 2048 / -1 / 768

configEMBED_DOC_PREFIX/ EMBED_QUERY_PREFIX Per-task input prefixes ""

configEMBED_QUERY_PREFIXEMBED_DOC_PREFIX / Per-task input prefixes ""

configEMBED_POOLING_TYPEPooling applied to raw model output: mean\cls\last\none mean

configRERANKER_DIRONNX cross-encoder directory ("" disables) ""

configRERANKER_BACKENDWhich reranker backend to use (registry key, rag/rerankers/registry.py) onnx_cross_encoder

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployCLAUDE_ENV_DSN

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

26/26 tools missing one or more hints — call_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); documentation.search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); documentation.fetch (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +23 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

No hardcoded API keys

1 live-looking API key in source: 1 AWS access key

Move secrets to environment variables (process.env.X) or your secret manager.

Tool test coverage

Only 4/26 tools referenced in tests (15%)

Write tests that reference each tool by name so every tool has at least one test.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/atri10-claude-env-platform-1c6zm6?variant=verified)](https://m8ven.ai/mcp/atri10-claude-env-platform-1c6zm6)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 2bea98488bfe2827e2fb19929d22926de36c8fa5

code hash: 70c225c94dfc8146fe999f0794f7561f0f3b951cdd9590c62f8e0ee2501e2722

verified: 8/12/2026, 7:54:35 AM

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client