Skills/npm/embark-mcp

embark-mcp@1.1.6

VERIFIED

Publisher claims: "MCP server proxy for Embark code search" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher jetbrains · publishing for 493 daysInstalls 3,083Last detonated 12 h ago
$claude mcp add embark-mcp -- npx -y embark-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
GRAZIE_JWT_TOKENTYPE_TOKENConfiguration, not credentials: CLAUDE_CODE, CLAUDE_CODE_SERVER, ELECTRON_RUN_AS_NODE, EMBARK_CLIENT, EMBARK_MCP_CLIENT, ENABLE_LOCAL_LOGS, ENABLE_REMOTE_LOGS, EXCLUDE_REPOSITORY_URLS, INCLUDE_REPOSITORY_URLS, JETBRAINS_AI_URL, MCP_CLIENT, REPOSITORY_GIT_REMOTE_URL, REPOSITORY_ID, REPOSITORY_REVISION, SERVER_PATH, VSCODE_IPC_HOOK, WORKING_DIR
Where it talks to
no vendor host named in the codeAlso jetbrains.ai, jetbrains.com, jsdelivr.net — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names jetbrains.ai, jetbrains.com, jsdelivr.net as well as its own vendor. The guard injects GRAZIE_JWT_TOKEN, TYPE_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y embark-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-19 and scored it 85/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 26 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.7sprocessdependency install exit 0
26sfilesystemwrote ~/.embark/stats/2026-11-19.json
26sclaimed1 tool: semantic_code_search
26stools29566b280b0058dc
26sprocessscript backend runs setup only
26sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload action.github/WORKFLOWS.md:34 · File type combined with upload action — agent may exfiltrate local data files- **Automatically bumps version** in package.json based on inputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Unpinned dependency.github/workflows/publish.yml:50 · Unpinned dependencyrun: npm install -g npm@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06

Cost to the agent

Instructions loaded
≈738 tok
2 files · 44 in bundle
Tool list per prompt
≈363 tok
1 tool · 363 per tool
Handshake
262 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 543

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for embark-mcp@1.1.6 as of 12 h ago. This is the package itself, not its dependencies.

embark-mcp@1.1.6 safety verdict: Verified — KillerSkills