Skills/npm/tradeblocks-mcp

tradeblocks-mcp@4.6.2

VERIFIED· install only

Publisher claims: "MCP server for options trade analysis" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher tradeblocks-org · publishing for 301 daysInstalls 1,957Last detonated 19 h ago
$claude mcp add tradeblocks-mcp -- npx -y tradeblocks-mcp
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
TRADEBLOCKS_JWT_SECRETTRADEBLOCKS_NO_AUTHTRADEBLOCKS_PASSWORD or --no-authConfiguration, not credentials: BLOCKS_DIRECTORY, CLAUDE_CONFIG_DIR, CODEX_HOME, DUCKDB_IDLE_RELEASE_MS, DUCKDB_LOCK_RECOVERY, DUCKDB_LOCK_RECOVERY_TIMEOUT_MS, DUCKDB_MEMORY_LIMIT, DUCKDB_OPEN_WAIT_MS, DUCKDB_THREADS, DUCKDB_WRITE_LOCK_RETRIES, GEMINI_CLI_HOME, MARKET_DB_PATH, MASSIVE_DATA_TIER, PATHEXT, TRADEBLOCKS_BLOCKS_DIR, TRADEBLOCKS_DATA_ROOT, TRADEBLOCKS_ISSUER_URL, TRADEBLOCKS_JWT_EXPIRY, TRADEBLOCKS_PARQUET, TRADEBLOCKS_USERNAME
Where it talks to
no vendor host named in the codeAlso nodejs.org, githubusercontent.com, claude.com, geminicli.com, claude.ai — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names nodejs.org, githubusercontent.com, claude.com, geminicli.com, claude.ai as well as its own vendor. The guard injects TRADEBLOCKS_JWT_SECRET, TRADEBLOCKS_NO_AUTH, TRADEBLOCKS_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y tradeblocks-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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 83/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/auth/config.ts:32 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Set it in your .env file or pass --no-auth to disable authentication.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/setup.ts:247 · npx invocation of non-well-known package — may execute untrusted code// data folder keeps npx from resolving the invoking directory's npm project instead.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandsrc/db/connection.ts:290 · Process kill command — agent can terminate processes// Only kill non-orphaned processes if forceRecovery is explicitly enabled.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/tools/imports.ts:82 · npx invocation of non-well-known package — may execute untrusted code"For stdio (npx tradeblocks-mcp), use a local filesystem path; for Docker/HTTP, use a path inside the server's mounted data directory. " +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/auth/config.ts:37 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"TRADEBLOCKS_PASSWORD is required for HTTP mode.\n" + "Set it in your .env file.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/db/connection.ts:721 · Process kill command — agent can terminate processes// A confirmed kill means the path may be clear right now, so retryFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/setup.ts:565 · npx invocation of non-well-known package — may execute untrusted code"Verification may take up to 120 seconds. The first npx run may download TradeBlocks and native DuckDB binaries.",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/setup.ts:415 · npx invocation of non-well-known package — may execute untrusted codeconst npx = await executable("npx");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/tools/performance.ts:1066 · File type combined with upload action — agent may exfiltrate local data files…acktest_to_actual", { description: "Compare backtest (tradelog.csv) results to actual reported trades (reportinglog.csv) with scaling options for fair comparison. Matches trades by date and strategy. When no dateRange is specified, compari…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/db/connection.ts:595 · Process kill command — agent can terminate processes// Desktop run more than one copy — and killing it makes each restart kill theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/setup.ts:283 · npx invocation of non-well-known package — may execute untrusted code// A first npx launch may download the package and native DuckDB binaries.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/index.ts:427 · npx invocation of non-well-known package — may execute untrusted code// Some launchers (e.g. `npx tradeblocks-mcp ...`) sit between the realFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/parent-watchdog.ts:4 · npx invocation of non-well-known package — may execute untrusted code* Some launchers (e.g. `npx tradeblocks-mcp ...`) sit between the realFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/setup.ts:662 · npx invocation of non-well-known package — may execute untrusted code"Verifying the configured server (up to 120 seconds); the first npx run may download TradeBlocks and native DuckDB binaries.",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈47 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for tradeblocks-mcp@4.6.2 as of 18 h ago. This is the package itself, not its dependencies.

tradeblocks-mcp@4.6.2 safety verdict: Verified (install only) — KillerSkills