mcp@4.12.0

VERIFIED

Publisher claims: "Crypto social intelligence from X and Telegram, plus the Elfa Auto condition engine" Observed in sandbox: calls api.elfa.ai only, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher elfa-ai · publishing for 106 daysInstalls 1,818Last detonated 33 min ago
$claude mcp add mcp -- npx -y @elfa-ai/mcp
WatchReport an issue

Coverage

Started with a decoy ELFA_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in ELFA_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
ELFA_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
ELFA_API_KEYELFA_MCP_AUTHELFA_OAUTH_INTROSPECTION_TOKENELFA_OAUTH_INTROSPECTION_URLELFA_OAUTH_ISSUERELFA_OAUTH_SCOPESConfiguration, not credentials: ELFA_BASE_URL, ELFA_EXTRA_HEADERS, ELFA_MCP_ALLOWED_HOSTS, ELFA_MCP_ALLOWED_ORIGINS, ELFA_MCP_HOST, ELFA_MCP_MAX_RESPONSE_CHARS, ELFA_MCP_OPENAI_APPS_CHALLENGE, ELFA_MCP_PORT, ELFA_MCP_RESOURCE_URL, ELFA_MCP_TRANSPORT, ELFA_RETRIES, ELFA_TIMEOUT
Where it talks to
elfa.ai (its own)
What the honeypot saw
no credential files read · reached only api.elfa.ai (its own)
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard. It asks for ELFA_API_KEY, ELFA_MCP_AUTH, ELFA_OAUTH_INTROSPECTION_TOKEN, ELFA_OAUTH_INTROSPECTION_URL, ELFA_OAUTH_ISSUER, ELFA_OAUTH_SCOPES and talks to elfa.ai. 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 ELFA_API_KEY=elfa.ai,ELFA_MCP_AUTH=elfa.ai,ELFA_OAUTH_INTROSPECTION_TOKEN=elfa.ai,ELFA_OAUTH_INTROSPECTION_URL=elfa.ai,ELFA_OAUTH_ISSUER=elfa.ai,ELFA_OAUTH_SCOPES=elfa.ai -- npx -y @elfa-ai/mcp

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

What changed since 4.11.0

vet-skills diff mcp 4.11.0 4.12.0

This version reaches for something 4.11.0 did not: 3 new tools (monitors, monitors_write, verify). Compared from the two recorded runs, not from source.

New tools
monitors, monitors_write, verify

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 2026-11-18 and scored it 93/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: calls api.elfa.ai only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 52 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
11sprocessdependency install exit 0
31sprocessrelaunched with a decoy ELFA_API_KEY (tagged; nothing real)
52snetworkCONNECT tcp://api.elfa.ai:443
52sclaimed21 tools with a decoy ELFA_API_KEY: api_status, entities, events, calendar, prediction_markets, market, calls, top_accounts, verify, monitors, monitors_write, auto_build, auto_validate, auto_query, auto_query_write, auto_draft, auto_draft_write, mentions, trending, narratives, market_chat
52stools679d0c242f4a6a96
52stoolsd2810cbc9d96bbe0
52stools1af4ab6b506d4d8f
52stools0dbcd9e06403add5
52stools985431d16dee8eca
52stools90c180071b86079c
52stools12e2512bdbd457ea
52stools19815bcbfc3deb85
52stoolsfe97e23c9d907345
52stools71e2331dbaf2b69b
52stoolsfabae48e77197928
52stoolsa273fc900df4d335
52stoolsd5cb077b51dc39ff
52stoolsc12cdae974e8b76b
52stoolsf05e94daf24e1a7c
52stools751df2cf63caf62b
52stools82cac0c707661976
52stools7485a71fbbe9fa94
52stools6fbf4bd409f8fefc
52stoolsce46a140a4766494
52stoolsd3d11d4473cae7e1
52sprocessscript backend runs setup only
52sprocessno install scripts to re-run

Static findings

No findings across 3,629 lines in 8 files.

Cost to the agent

Instructions loaded
≈60 tok
1 file · 8 in bundle
Tool list per prompt
≈9,220 tok
21 tools · 439 per tool
Handshake
1455 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 472

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.