CKBBLOCK
Code intelligence for AI assistants - MCP server, CLI, and HTTP API with symbol navigation, impact analysis, and architecture mapping
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Know your code. Change it safely. Ship with confidence.
[](https://www.npmjs.com/package/@tastehub/ckb) [](https://codeknowledge.dev) [](https://codeknowledge.dev/docs) [](https://lobehub.com/mcp/simplyliz-codemcp) [](https://crates.io/crates/lip-cli) [](https://lip-sigma.vercel.app/docs)
CKB transforms your codebase into a queryable knowledge base. Ask questions, understand impact, find owners, detect dead code—all through CLI, API, or AI assistants.
Think of it as a senior engineer who knows every line of code, every decision, and every owner—available 24/7 to answer your questions.
Instant Answers to Hard Questions
What You Can Do
🔍 Understand — Semantic search, call graphs, usage tracing, architecture maps
⚡ Analyze — Impact analysis, risk scoring, hotspot detection, coupling analysis
ded7aba7e959OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add ckb -- npx -y @tastehub/[email protected] mcp
Exposed tools (7)
7 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Core | read | Essential tools for navigation and analysis (14 tools, recommended) |
Docs | read | Documentation focused: doc coverage, staleness checks (20 tools) |
Federation | read | Multi-repo analysis and cross-repo search (28 tools) |
Full | read | All available tools (76 tools) |
Ops | read | Operations: jobs, webhooks, scheduling, metrics (25 tools) |
Refactor | read | Refactoring focused: impact analysis, coupling, complexity (19 tools) |
Review | read | Code review focused: PR summary, hotspots, ownership (19 tools) |
Trust audit
BLOCKgrade F · trust 51/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (10 observation(s))
- Network
- declared (11 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
Regex: regexp.MustCompile(`-----BEGIN EC PRIVATE KEY-----`),
Regex: regexp.MustCompile(`-----BEGIN OPENSSH PRIVATE KEY-----`),
Regex: regexp.MustCompile(`-----BEGIN DSA PRIVATE KEY-----`),
{regexp.MustCompile(`\beval\s*\(`), "eval() call"},{regexp.MustCompile(`\bexec\s*\(`), "exec() call"},func (db *DB) Exec(query string, args ...interface{}) (sql.Result, error) {"id_rsa",
"id_rsa.pub",
"id_ed25519",
"id_ed25519.pub",
"id_rsa",
{regexp.MustCompile(`(?i)verify\s*[=:]\s*(?:False|false|0)`), "TLS verification disabled (verify=False)"},index.scip
!strings.Contains(line, "http://127.0.0.1") && !strings.Contains(line, "http://0.0.0.0") &&
if strings.Contains(lower, "http://localhost") || strings.Contains(lower, "http://127.0.0.1") ||
strings.Contains(lower, "http://0.0.0.0") || strings.Contains(lower, "http://[::1]") ||
if strings.Contains(lower, "http://localhost") || strings.Contains(lower, "http://127.0.0.1") ||
strings.Contains(lower, "http://0.0.0.0") || strings.Contains(lower, "http://[::1]") ||
awsKey := "AKIAIOSFODNN7REALKEY"
{"AKIAIOSFODNN7REALKEY", false}, // Real-looking AWS key{"MongoDB URI", "mongodb://user:[email protected]/db", SecretTypeMongoDBURI, true},{"MongoDB SRV URI", "mongodb+srv://admin:[email protected]/", SecretTypeMongoDBURI, true},{"PostgreSQL URI variant", "postgresql://user:pass123@localhost/database", SecretTypePostgresURI, true},{"api_key = 'sk_live_abc123def456ghi789'", "sk_live_abc123def456ghi789", false},{"ghp_AbCdEfGhIjKlMnOpQrStUvWxYz123456", 3.5, true},Gates applied: critical_finding, no_behavioural_pass.
ded7aba7e959full audit observations/trust-audit/mcp-server/simplyliz__ckb-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | ded7aba7e959 | BLOCK | F | 51 | first audit |
Questions
What is the CKB MCP server?
Code intelligence for AI assistants - MCP server, CLI, and HTTP API with symbol navigation, impact analysis, and architecture mapping
What tools does CKB expose?
7 in total: 7 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is CKB safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (51/100) and found 12 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does CKB need?
It reads API_KEY, KEY, SECRET and TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does CKB run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as incremental-test at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (ded7aba7e959), read on 2026-10-07. The repository is watched and re-audited when it changes.