Skills/npm/mcp-server

mcp-server@0.72.0

VERIFIED

Publisher claims: "MCP server for DWLF market analysis platform — exposes market data, indicators, signals, strategies, backtests, portfolio, trade journal, and more as AI-accessible tools" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher dwlf · publishing for 295 daysInstalls 4,320Last detonated 12 min ago
$claude mcp add mcp-server -- npx -y @dwlf/mcp-server
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
DWLF_API_KEYConfiguration, not credentials: BLOCK_API_URL, DWLF_API_URL, DWLF_BLOCK_BACKEND, DWLF_BLOCK_KEY, DWLF_TOOL_PROFILE
Where it talks to
dwlf.co.uk (its own)
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. It asks for DWLF_API_KEY and talks to dwlf.co.uk. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --secrets DWLF_API_KEY=dwlf.co.uk -- npx -y @dwlf/mcp-server

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

What changed since 0.67.0

vet-skills diff mcp-server 0.67.0 0.72.0

This version reaches for something 0.67.0 did not: 17 rewritten tool descriptors (dwlf_compile_custom_event, dwlf_create_custom_event, dwlf_describe_strategy_nodes, dwlf_get_conditions, …). Compared from the two recorded runs, not from source.

Rewritten tool descriptors
dwlf_compile_custom_event, dwlf_create_custom_event, dwlf_describe_strategy_nodes, dwlf_get_conditions, dwlf_get_custom_event_notifications, dwlf_get_cycle_setups, dwlf_get_cycle_windows, dwlf_get_divergences, dwlf_get_events, dwlf_get_indicators, dwlf_get_market_data, dwlf_get_price_picture +5

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-21 and scored it 95/100 (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 · 27 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
6.8sprocessdependency install exit 0
27sclaimed118 tools: dwlf_get_market_data, dwlf_get_quote, dwlf_list_symbols, dwlf_get_support_resistance, dwlf_get_events, dwlf_get_price_picture, dwlf_get_cycle_setups, dwlf_get_ranges, dwlf_get_setup_transitions, dwlf_get_cycle_windows, dwlf_get_divergences, dwlf_get_stage, dwlf_get_conditions, dwlf_get_indicators, dwlf_get_trendlines, dwlf_get_active_signals, dwlf_get_recent_signals, dwlf_get_signal_stats, dwlf_get_watchlist, dwlf_add_to_watchlist, dwlf_get_briefing_list, dwlf_add_to_briefing_list, dwlf_remove_from_briefing_list, dwlf_list_symbol_tags, dwlf_get_symbol_tags
27stools127c4f5e9cd9cee3
27stools7fb7e0fa3c9e4dd1
27stools153730cec7c2d64f
27stools31fc15dc843b9afd
27stools474fcf319c351854
27stoolsa764673b459a7eb9
27stools50b15903afefefe8
27stools6d4bbd0f305f855a
27stools3e312070395a5f7f
27stoolscd4df862c5163f72
27stoolsbafff5b9ae3a0fce
27stoolsb1aa28b9294d2a84
27stools006c89f1f57f4fe5
27stoolsc79638e5f221bfe1
27stools445f344ac9b64333
27stoolsefab9da242b199c0
27stoolsff8c6eb0feabd040
27stools96e486b688ef7b7f
27stoolsdb990c6658528cf0
27stoolsda4f8f367c364da2
27stoolsb8173afb70ad7040
27stoolscbb3005c6195397e
27stoolsc30ac9592f8633d1
27stoolsd3a8aa7d83db8a89
27stoolsdef67dc2b2b80a51
27stoolsa35e798744d89de3
27stoolsfcb87ee5c57bfe09
27stoolsda73ac7c72f9d5d7
27stoolse66af1dd0167629a
27stoolsc2bb06a0a7fabad3
27stools881a5e54b62f9d30
27stoolsa765c2cf048431e6
27stools0239e97db573681a
27stools9ef0533b56dd24f9
27stoolsa3572ee1a94c0546
27stoolsb9a24439bf809ef9
27stools3b8c6d366334c235
27stools4755be13c6263297
27stools661e9612cb1109a2
27stools937bd6170286bae4
27stools6a943708c8aa0fff
27stools9e65002e9d0e38e0
27stools015b0e90f7859523
27stoolsc01ac1e72e0c3e2f
27stools332bc161d31b5710
27stoolsb9cefac706770cad
27stools49a9c5f7164dcef9
27stoolsddf8d876dacdada1
27stools063c23802d6389a2
27stools2a5df10edce16e30
27stools805b64616d08a979
27stoolscc2f8e6bcf99cd6f
27stoolsb7161495eeed95ab
27stoolsaf5857aeaa12bcf6
27stools04b5e3a5ebd4eeb9
27stools2470cde977aa129d
27stools3cdeb54dbcebe752
27stools0d7d483d00260d21
27stools85d933169ab63814
27stoolsdad09ec14ebe3742
27stools6d53f7d74104bc43
27stools3f51c5273fa2964e
27stoolse0a4fd9550a61b54
27stoolsf090711c8bb9d2ff
27stools73ec7d0e44347798
27stools9be19c938b434900
27stools8422be3ed3cbdf6d
27stoolsd08c021888c499e4
27stools4742a266c2abf320
27stools71012082e4662ed5
27stoolsaa70cf348d7b94d5
27stools7d7e54db2ae2f285
27stoolsa48aa2011062a523
27stoolsc318fa4cf512fe29
27stools256df76ace638755
27stoolsa7afd919b92762a2
27stools8f038033208396a3
27stools071c8dc2ee94caa1
27stools32d7b67d7038a45f
27stoolscc3ece0ccdbb5ab6
27sprocessscript backend runs setup only
27sprocessno install scripts to re-run

Static findings

No findings across 9,883 lines in 81 files.

Cost to the agent

Instructions loaded
≈79 tok
1 file · 81 in bundle
Tool list per prompt
≈40,622 tok
118 tools · 344 per tool
Handshake
3799 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 592

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

Not checked against OSV yet; the weekly check has not reached this version.