ctt-shell (MauricioPerera/ctt-shell) is an MCP server listed on the M8ven Trust Index. It scores 89 out of 100, grade B. It declares 9 tools. The publisher has proved control of what we score (Verified Publisher). It is connected through the M8ven GitHub App, so the listing is re-checked on every push.

Back to MCP Trust IndexM8ven
B
Emerging
89/100
1 hour ago

ctt-shell

Universal AI agent framework — 1B models compose multi-step plans like 12B with structured context (CTT). 6 domains, 8 MCP tools, 167 tests, zero runtime deps.

→ MauricioPerera/ctt-shell

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored

Monitored 0 days · every push re-verified

Who stands behind it

gmail.com (@MauricioPerera) · Verified Publisher

Source: github_app_install

Maintenance & responsiveness
as of 2026-08-20
Issues closed (90d): 0 · 0 open
Releases (90d): none
Active contributors (6mo): 1

Install from

GitHub

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

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 3 credentials: ANTHROPIC_API_KEY, CF_API_KEY, OPENAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
Are you the publisher? Confirm or correct these findings.
// 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.
🔐 secretANTHROPIC_API_KEYClaude
configCF_ACCOUNT_IDCloudflare Workers AI (free tier)
🔐 secretCF_API_KEYCloudflare Workers AI (free tier)
configCTT_WEB_PORTHTTP server port (default: 3700)
configEMBEDDING_BASE_URLServer URL (e.g., http://localhost:9999)
configEMBEDDING_CACHE_DIRCache directory (default: .ctt-shell/embeddings-cache)
configEMBEDDING_MODELModel name (default: embeddinggemma)
configEMBEDDING_PROVIDERopenai (llama-server, vLLM), ollama, or cloudflare
configLLAMACPP_PORT
configOLLAMA_MODELLocal Ollama (default: qwen2.5:3b)
🔐 secretOPENAI_API_KEYOpenAI
// 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

9/9 tools missing one or more hints — ctt_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ctt_execute (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ctt_extract (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 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.).

Shell command execution

1 call in production code run through a shell (src/shell/executor.ts:124)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets not logged

2 secret values sent to log

Redact or omit secret values from log output.

// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/mauricioperera/ctt-shell)](https://m8ven.ai/mcp/mauricioperera/ctt-shell)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 0d4faf7395641f26931409ce134de0de98a452e8
code hash: 478347831b85df6cddf15aa68b52870d6abab473c47270349ab1c5b2f95fb28f
verified: 9/10/2026, 3:46:36 PM
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