Back to MCP Trust Indexm8ven
66
/ 100
1 month ago
glama

CotForce-MCP

Give brains to your small models. MCP server that enforces step-by-step Chain-of-Thought — turns 4B models into methodical reasoners.

→ islobodan/cotforce-mcp· listed on glama
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.

Install from

Glama

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

// key findings
⚠️
Known vulnerabilities in dependencies: 2 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
⚠️
Tests do not pass
Either the test suite is broken or the code regressed. Either way the published behaviour can’t be verified by the publisher’s own tests.
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 1 credential: API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies2 high1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.0.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.0.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

lowzod@3.22.0GHSA-m95q-7qp3-xv42

Zod denial of service vulnerability

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configAPI_BASE_URL— "": "http://localhost:1234/v1",
🔐 secretAPI_KEY— Universal compatibility — works with MCP sampling (Claude Desktop) or direct LLM HTTP calls (OpenAI, LMStudio, Ollama, any OpenAI-compatible API). Set to use direct mode.
configBASE_TEMP— 0.1 Initial sampling temperature.
configCACHE_MAX_ENTRIES— 100 Maximum cached results before evicting oldest.
configCACHE_TTL— 3600000 Result cache TTL in ms (default 1 hour). Set to 0 to disable.
configCOT_PARSERS— (all) Comma-separated parser names to use (e.g., direct-json,fenced-block). Skips others.
configFALLBACK_MODELS— (not set) Comma-separated list of fallback models (e.g. gpt-4o,claude-3-5-sonnet). Cycled on failure.
configLOG_LEVEL— Structured logging — timestamped, level‑filtered logs to stderr (supports ).
configMAX_RETRIES— 2 Number of retry attempts before returning raw output.
configMODE— "": "direct",
configMODEL— "": "gemma-4-e4b-it-mlx"
configREASONING_OVERHEAD— Token budgeting with tiktoken — accurate token counting using OpenAI's cl100k_base encoding, with fallback to character heuristic. Tweak via .
configTIMEOUT— 60000 / 120000 Sampling timeout in ms (60s). Direct HTTP mode uses longer default (120s) since local models are slower.
configTRUNCATION_THRESHOLD— Output truncation detection — detects when the LLM response hits the token limit and retries with a conciseness hint ().
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// 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 Score](https://m8ven.ai/badge/mcp/islobodan-cotforce-mcp-ojtqwf)](https://m8ven.ai/mcp/islobodan-cotforce-mcp-ojtqwf)
commit: 4d5832fc09c9bc8c472a1911aeede93b43e57eaf
code hash: 44cd7bf5f836e1a6b600c6318e571e601fdb50bfaa4e2282b2d3c204d2886bf1
verified: 6/11/2026, 11:10:11 AM
view raw JSON →